Ultralytics
modes/track/ #7906
giscus[bot]
bot
Replies: 139 comments 343 replies
-
|
Can I run two models simultaneously in one video? I want that two models will works simultaneously with cumulative results? Is it possible? Please let me know. Thanks in advance!! |
Beta Was this translation helpful? Give feedback.
-
|
@AdadAlShabab yes, you can run two models simultaneously on one video, but you'll need to manage the inference in a way that allows both models to process the video frames concurrently. Here's a simplified example using threading to achieve this: import threading
from ultralytics import YOLO
# Load the models
model1 = YOLO('E:/Ultralytics/best.pt')
model2 = YOLO('yolov8m-pose.pt')
# Function to run tracking
def track_video(model, source, conf, show, save):
results = model.track(source=source, show=show, conf=conf, save=save)
# Process results here or return them
# Create threads for each model
thread1 = threading.Thread(target=track_video, args=(model1, "file.mp4", 0.3, True, False))
thread2 = threading.Thread(target=track_video, args=(model2, "file.mp4", 0.3, True, False))
# Start the threads
thread1.start()
thread2.start()
# Wait for both threads to finish
thread1.join()
thread2.join()This script will run both models in separate threads. If you want to combine the results from both models, you'll need to implement a mechanism to synchronize and merge the results from both threads. Keep in mind that displaying the results ( Remember to handle the GPU memory usage carefully, as running two models simultaneously will require more memory. If you encounter any issues, consider running the models sequentially or on separate GPUs if available. |
Beta Was this translation helpful? Give feedback.
-
|
Hi, First of all, I have been loving working with Yolov8. Great tool! However, I have been having difficulties with a certain task. I want to use model.track on videos that I have, and then use save_crop = True, but save with a naming convention where I can track each persons ID. Currently, save_crop just gives me the cropped images of the objectes detected, but there is not way to know from which frame of the video are the crops, also, which ID is attached which cropped image. The visualization through cv2.imshow shows the IDs accross the different frames, but I cant find a way to save them. The naming convention I am looking for is something like this: "frame_30_ID_1.jpg" My current code looks something like this: from ultralytics import YOLO model = YOLO("yolov8n.pt") # load model video_path = "path/to/video.mp4" ret = True while ret: cap.release() Any help would be greatly apprecitated! Thanks! |
Beta Was this translation helpful? Give feedback.
-
|
@Rid1Whitehead hello! I'm glad to hear you're enjoying working with YOLOv8! 😊 For your task of saving cropped images with a specific naming convention that includes the frame number and ID, you'll need to customize the saving part of the code. The Here's a modified version of your code that manually saves the cropped images with the desired naming convention: from ultralytics import YOLO
import cv2
import os
model = YOLO("yolov8n.pt") # load model
video_path = "path/to/video.mp4"
cap = cv2.VideoCapture(video_path)
ret = True
frame_count = 0 # Initialize a frame counter
save_dir = "path/to/save/crops" # Directory to save the crops
os.makedirs(save_dir, exist_ok=True) # Create the directory if it doesn't exist
while ret:
ret, frame = cap.read()
frame_count += 1 # Increment the frame counter
if ret:
results = model.track(frame, persist=True)
for i, det in enumerate(results[0].boxes.xyxy):
# Extract bounding box coordinates
x1, y1, x2, y2 = map(int, det[:4])
crop = frame[y1:y2, x1:x2] # Crop the detected object
# Save the cropped image with the desired naming convention
crop_name = f"frame_{frame_count}_ID_{results[0].boxes.id[i]}.jpg"
crop_path = os.path.join(save_dir, crop_name)
cv2.imwrite(crop_path, crop)
frame_ = results[0].plot()
cv2.imshow("frame", frame_)
if cv2.waitKey(25) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()In this code, we loop through each detection in the current frame, extract the bounding box coordinates, crop the detected object from the frame, and save it with the naming convention you specified. Make sure to replace Please note that this code assumes that the I hope this helps! If you have any more questions or need further assistance, feel free to ask. Happy coding! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hi @pderrenger . Can I run the models using my phones camera? Can you please share the code to invoke my mobile's camera to test the model? Thanks in advance. |
Beta Was this translation helpful? Give feedback.
-
|
@AdadAlShabab hi there! 👋 Yes, you can use your phone's camera to test the YOLO models. If you're looking to connect directly from your phone, you might need an app that can stream your camera feed to a URL. Then, you can use that URL as the from ultralytics import YOLO
# Load your trained model
model = YOLO('path/to/your/model.pt')
# Replace 'your_stream_url' with the URL from your phone's camera stream
results = model.track(source='your_stream_url', show=True)Make sure your phone and the computer running the model are on the same network. Happy tracking! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
There's no problem at all using your way, but when I use it, the video streaming latency is extraordinarily high, why is that? |
Beta Was this translation helpful? Give feedback.
-
|
Hi there! 🙌 The high latency you're experiencing during video streaming might be due to a few factors. Here are a couple of things you could check or adjust to potentially reduce the latency:
Here’s a quick example of reducing image size which might help speed up the process: import cv2
from ultralytics import YOLO
# Load the YOLOv8 model
model = YOLO('weights/det/yolov8n.pt')
# Reduce frames size to increase performance
def resize_frame(frame, scale=0.5):
width = int(frame.shape[1] * scale)
height = int(frame.shape[0] * scale)
dimensions = (width, height)
return cv2.resize(frame, dimensions, interpolation=cv2.INTER_AREA)
# Open the video file
cap = cv2.VideoCapture("http://192.168.9.123:4747/video")
# Loop through the video frames
while cap.isOpened():
success, frame = cap.read()
if success:
# Resize frame
frame = resize_frame(frame, scale=0.5)
# Run YOLOv8 tracking on the frame
results = model.track(frame, persist=True)
# Visualize the results
annotated_frame = results[0].plot()
cv2.imshow("YOLOv8 Tracking", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
else:
break
cap.release()
cv2.destroyAllWindows()This adjusts the frame size being processed, which could potentially reduce the latency you're experiencing. Hope this helps! 😊 If issues persist, feel free to provide more information about your setup. |
Beta Was this translation helpful? Give feedback.
-
|
@pderrenger Thanks for your reply! What puzzles me is that when I use the first method, the picture is smooth and when I use the second method, the picture has a high latency, why is that? I don't think it's a network or hardware acceleration issue. Way 1 Way2 |
Beta Was this translation helpful? Give feedback.
-
|
Hey @Liuchunxiao111! 🌟 The difference in latency between the two methods might be due to how the frames are processed and displayed. In the first method, the To reduce latency in the second method, you might consider:
These tweaks can help align the processing speed more closely with the incoming frame rate, reducing the noticeable lag. Hope this helps! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Hi, help me understand why I get this error when tracking with segmentation model . My ultimate goal is to use a custom car plate segmentation model for tracking. Thank you very much |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It looks like you're encountering a shape mismatch error when plotting your tracking results. This often happens when the image dimensions don't align with the mask dimensions expected by the To resolve this, ensure that the image size you're using for tracking matches the size expected by the model. If you're using a custom model, double-check that the image size during training and inference is consistent. Here's a quick fix you might try: # Before plotting, resize your frame to match the model's expected input size
frame_resized = cv2.resize(frame, (model.imgsz[1], model.imgsz[0]))
# Now use the resized frame for tracking and plotting
results = model.track(frame_resized, show=False, verbose=False, conf=0.4, classes=class_list, persist=True)Make sure to replace Give this a shot, and if you're still stuck, feel free to share more details or reach out again! Happy tracking! 🚗💨 |
Beta Was this translation helpful? Give feedback.
-
|
Thank you more for such a quick response, it worked |
Beta Was this translation helpful? Give feedback.
-
|
@Boaruzhanchik hey, that's awesome to hear it worked out for you! 🎉 If you dive into tracking with your custom car plate segmentation model and have any more questions or cool results to share, don't hesitate to reach out. Happy tracking! 🚗🔍 |
Beta Was this translation helpful? Give feedback.
-
|
@glenn-jocher Hey, how do you implement with custom seg modem, kindly illustrate |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! Implementing tracking with a custom segmentation model is pretty straightforward. You'll want to load your model and then use the from ultralytics import YOLO
# Load your custom segmentation model
model = YOLO('path/to/your/custom-seg-model.pt')
# Run tracking on your video source
results = model.track(source='path/to/your/video.mp4', classes=[your_car_plate_class_id])Just replace |
Beta Was this translation helpful? Give feedback.
-
|
Yolov8 has very high overall practicality. Can I implement tracking with two cameras? I hope that when a car tracked by camera A moves to camera B, its frame ID remains the same. However, currently there is always an ID switch happening. Is it because of the model's accuracy? def cam2(): cap=cam a = threading.Thread(target=cam1) a.start() |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! Tracking continuity across multiple cameras, especially to maintain the same ID as an object moves from camera A to camera B, is indeed a complex task that involves more than just the accuracy of the model. It requires a method to correlate tracks across the different camera views, often referred to as multi-camera tracking or re-identification (Re-ID). Regarding access to the global track ID or maintaining consistent IDs across cameras, it's correct that basetrack.py (or similar files, depending on the tracking implementation you're using) manages these IDs. However, for multi-camera setups, you might need to implement or use an existing Re-ID system that can match IDs based on features or appearance. A simplistic approach could involve:
This can get quite involved, as it requires managing the timing and spatial-correlation of detections across cameras, and the model's accuracy is just one of many factors. For directly accessing or setting the track ID, if you're using a specific tracker that has its global track ID in I hope that sheds a bit more light on it! Let me know if you delve into the re-identification approach or if you have other questions. 😊👍 |
Beta Was this translation helpful? Give feedback.
-
|
I have a new question, can I know the distance to the camera while tracking? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! Regarding your question about knowing the distance to the camera while tracking, YOLOv8 or most object tracking algorithms, including those implemented in Ultralytics YOLO, primarily focus on detecting objects and potentially tracking their movement across frames. They don't inherently provide distance measurements since that would require additional depth-sensing hardware or methods. However, if you have a calibrated camera setup or additional information about the scene, you might estimate distances using object sizes or other cues. For instance, in specific, controlled environments, the apparent size of known objects can give clues about distance based on their expected real-world size. Alternatively, employing depth cameras or stereo vision setups can directly provide depth information. If using such sensors, depth data can be combined with tracking data to estimate distances of tracked objects. I hope that helps a bit! If you're diving deeper into this, consider exploring topics like camera calibration, depth sensing technologies, and stereo vision. 😊📏🎥 |
Beta Was this translation helpful? Give feedback.
-
|
Hello, I would like to ask, my current tracking program is as shown below I need the X1X2Y1Y2 of the tracking frame in each frame to calculate the distance. Is there a way to get it? |
Beta Was this translation helpful? Give feedback.
-
|
Hello! To get the bounding box coordinates (X1, Y1, X2, Y2) for each tracked object, you can access the def cam1():
global shard_track
model = YOLO('updated-model.pt')
shard_track = model.track(source="http://192.168.50.204:8080/?action=stream", show=True)
cv2.waitKey(0)
cv2.destroyAllWindows()
def track_and_print_cam1():
global shard_track
if hasattr(shard_track, 'xyxy'):
for det in shard_track.xyxy[0]: # Assuming shard_track is the results object
x1, y1, x2, y2, conf, cls, track_id = det
print(f'Track ID: {track_id.item()}, BBox: ({x1.item()}, {y1.item()}, {x2.item()}, {y2.item()})')
else:
print("No tracking data found.")This modification ensures you're extracting the bounding box coordinates directly from the detection results, which should help you calculate distances or any other metrics based on the positions of the objects. If you have any more questions or need further assistance, feel free to ask! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Hey there, |
Beta Was this translation helpful? Give feedback.
-
|
@samyak197 hey there! 😊 Absolutely, YOLO can assist with tracking employees in a shop. You can use our tracking models to assign unique IDs and track them throughout the day. For long-term tracking, make sure your video feed is continuous and the model is configured for persistent tracking. Here's a quick example using YOLOv8: from ultralytics import YOLO
# Load your custom trained model or an official YOLOv8 model
model = YOLO('path/to/your/custom-model.pt') # Custom trained model
# Track employees in a video
results = model.track(source="path/to/shop/video.mp4", persist=True)This will keep the identities consistent across frames. For more details, check out our tracking documentation. If you have any more questions or need further assistance, feel free to ask. Happy tracking! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hi I saw that I can use an openvino IR format model just like any other pytorch model and then run tracking like normal. I was wondering how I would load the IR '.xml' and '.bin' files as arguments into YOLO(), or if I should load my model using openvino library? Thanks. |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 To load OpenVINO IR '.xml' and '.bin' files into YOLO(), you'll want to simply point to their containing directory, i.e.: from ultralytics import YOLO
# Load your YOLOv8 OpenVINO model
model = YOLO('path/to/yolov8n_openvino_model/') # exported with YOLO('yolov8n.pt').export(format='openvino')
# Track employees in a video
results = model.track(source="path/to/shop/video.mp4", persist=True)Once you have your model loaded with OpenVINO, you can then proceed with tracking as you would normally with the YOLO model. You might want to use |
Beta Was this translation helpful? Give feedback.
-
|
Will give this a try, appreciate the timely response! |
Beta Was this translation helpful? Give feedback.
-
|
@ParkerLischwe glad to hear you're giving it a try! If you have any questions or need a hand with the tracking setup, just drop a message. Happy tracking! 😊🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Can i use yolov8 model to track and reidentify person with same id assigned to it in multiple camera feed ? |
Beta Was this translation helpful? Give feedback.
-
|
@ANIRUDH1080Z yes, you can use YOLOv8 models for multi-object tracking across multiple camera feeds. Each detected person can be assigned a unique ID that persists as they move through the field of view of different cameras. You can choose from different trackers like BoT-SORT and ByteTrack, and even customize the tracker configurations to suit your specific needs. Here's a simple example using the default tracker: from ultralytics import YOLO
# Load a YOLOv8 model
model = YOLO('yolov8n.pt')
# Perform tracking on a video source
results = model.track(source="path/to/camera_feed.mp4", show=True)For tracking across multiple cameras, you might need to synchronize the cameras and handle the ID reidentification logic, as the trackers maintain IDs within a single video stream. If you have a custom solution or improvements, consider contributing to our Trackers section! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Thank u so much for enlightening me about this. |
Beta Was this translation helpful? Give feedback.
-
|
You're welcome! I'm glad the information was helpful. If you're looking to implement multi-object tracking across multiple camera feeds, you can certainly use YOLOv8 models. While YOLOv8 can assign unique IDs within a single video stream, tracking across multiple cameras (especially with non-overlapping fields of view) typically requires additional logic to handle ID reidentification. For such cases, you might consider integrating your YOLOv8 tracking with a reidentification (ReID) system that can match IDs based on appearance features. Here's a simple example of how you might set up tracking for a single camera feed: from ultralytics import YOLO
# Load a YOLOv8 model
model = YOLO('yolov8n.pt')
# Perform tracking on a video source
results = model.track(source="path/to/camera_feed.mp4", show=True)For multi-camera setups, after tracking, you would extract features from detected objects and use a ReID model to match identities across different camera feeds. If you're developing a solution or have improvements, we'd love to see your contributions to our tracking capabilities! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
How can we only track moving objects in the Plotting Tracks Over Time code: from collections import defaultdict import cv2 from ultralytics import YOLO Load the YOLOv8 modelmodel = YOLO('yolov8n.pt') Open the video filevideo_path = "path/to/video.mp4" Store the track historytrack_history = defaultdict(lambda: []) Loop through the video frameswhile cap.isOpened(): Release the video capture object and close the display windowcap.release() |
Beta Was this translation helpful? Give feedback.
-
|
I forgot to write "only " so its MOVING OBJECTS ONLY |
Beta Was this translation helpful? Give feedback.
-
|
@kshweikeh hey there! 👋 To track only moving objects, you can modify the code to calculate the displacement of each object between frames and only plot the tracks for those with significant movement. Here's a quick example of how you might do that: # ... [previous code]
# Define a movement threshold (this value may need tuning)
movement_threshold = 5 # pixels
# Loop through the video frames
while cap.isOpened():
# ... [previous code]
# Get the previous and current center points
for track_id in track_ids:
if len(track_history[track_id]) >= 2:
prev_center = track_history[track_id][-2]
curr_center = track_history[track_id][-1]
displacement = np.sqrt((curr_center[0] - prev_center[0]) ** 2 + (curr_center[1] - prev_center[1]) ** 2)
# Only plot the track if the displacement is above the threshold
if displacement > movement_threshold:
points = np.array(track_history[track_id], dtype=np.int32).reshape((-1, 1, 2))
cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10)
# ... [previous code]This snippet calculates the Euclidean distance between the previous and current positions of each tracked object and only draws the track if the object has moved more than the |
Beta Was this translation helpful? Give feedback.
-
|
Thanks!! |
Beta Was this translation helpful? Give feedback.
-
|
@kshweikeh hey there! 👋 Absolutely, happy to help! For tracking moving objects with YOLOv8, you can utilize the from ultralytics import YOLO
# Load your model
model = YOLO('path/to/your/model.pt')
# Run the tracker
results = model.track(source='path/to/your/video.mp4', tracker='custom_tracker.yaml')In your If you need more guidance or have specific requirements, feel free to share, and we can dive deeper! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
import cv2 model = YOLO('yolov8_custom_train.engine', task="detect") Path to the input video fileinput_video_path = '/content/gdrive/MyDrive/yolov8-tensorrt/inference/output_video.mp4' Path to the output video fileoutput_video_path = 'outputtest_video.mp4' Define the coordinates of the polygonpolygon_points = [(670, 66), (1237, 550), (514, 1054), (161, 295)] Open the input video filecap = cv2.VideoCapture(input_video_path) Get video propertiesframe_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) Define the codec and create VideoWriter objectfourcc = cv2.VideoWriter_fourcc(*'mp4v') Function for finding the centroiddef calculate_centroid(box): Function to check if two bounding boxes overlapdef check_overlap(box1, box2): Read until video is completedwhile cap.isOpened(): Release video objectscap.release() Close all OpenCV windowscv2.destroyAllWindows() In this, I am tracking a label Person but in the next 2 to 3 frames, ids are changing so any solution for this? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It looks like you're experiencing some ID consistency issues with your custom-trained model during tracking. This can happen due to various reasons, such as similar-looking objects or occlusions. One approach to mitigate this is to fine-tune your tracker's hyperparameters. If you're using the default BoT-SORT tracker, you might want to experiment with the from ultralytics import YOLO
# Load your custom-trained model
model = YOLO('yolov8_custom_train.engine', task="detect")
# Perform tracking with ByteTrack
results = model.track(source="your_video.mp4", tracker="bytetrack.yaml")If you've already tried adjusting the tracker settings and the issue persists, consider revisiting your training dataset to ensure it's diverse and representative enough to handle the scenarios where ID switches occur. Keep us posted on your progress, and if you need more assistance, we're here to help! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
I have already used the bytetrack.yaml and this is ouput video , https://drive.google.com/file/d/1E95m456dbZAUDRrodfrvrsSA4zcs3KiA/view?usp=sharing , please analyze it |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! Thanks for reaching out and sharing the video link. 🎥 I took a look, and it seems like the ID switches might be due to occlusions or similar-looking objects. Here are a couple of quick suggestions:
If you've already fine-tuned these without success, consider:
If you're still facing issues, feel free to share more details or reach out for further assistance. We're here to help! 😊👍 |
Beta Was this translation helpful? Give feedback.
-
|
What is the difference between these attributes of results[0].boxes: |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 The attributes you're asking about represent different formats of bounding box coordinates:
The tensors being empty ( |
Beta Was this translation helpful? Give feedback.
-
|
is it possible to use our own weighs as a model to track? or we must include the yolov8n.pt? |
Beta Was this translation helpful? Give feedback.
-
|
Absolutely, you can use your own custom weights for tracking! Just load your trained model instead of the default from ultralytics import YOLO
# Load your custom trained model
model = YOLO('path/to/your/custom-weights.pt')
# Perform tracking with your model
results = model.track(source="path/to/your/video.mp4", show=True)And that's it! Your custom model will now be used for tracking objects in your video stream. 🚀 If you have any more questions or need further assistance, feel free to ask. Happy tracking! |
Beta Was this translation helpful? Give feedback.
-
|
do you a discord so we can discuss about my project? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 We don't have an official Discord channel, but we're happy to help you right here or on our GitHub discussions page. If you have any questions about your project or need assistance with object tracking using YOLOv8, feel free to drop your questions, and we'll do our best to assist you! 🚀 If it's code-specific, you can also share snippets or error messages, and we'll take a look. Happy tracking! |
Beta Was this translation helpful? Give feedback.
-
|
i had an error when everytime i try to run a code, it crashed on 4xx/600, and i must restart it, and 2nd question can we make a custom annotator? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It sounds like you're encountering a crash during your code execution. To better assist you, could you please share the specific error message you're getting? This will help us pinpoint the issue more accurately. Regarding your second question, yes, you can create a custom annotator. If you're working with YOLOv8, you can use tools like CVAT or LabelImg for annotation, and then train your model with these custom annotations. Here's a quick example of how you might load and use your custom model for tracking: from ultralytics import YOLO
# Load your custom trained model
model = YOLO('path/to/your/custom_model.pt')
# Perform tracking on your video
results = model.track(source='path/to/your/video.mp4', show=True)This will use your custom weights for tracking objects in the video. If you have any more questions or need further assistance, feel free to ask! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
So I am using Yolov8 for my current project, it's been a breeze so far. I do have a question on the tracking method provided by the Yolov8. When I am using the generic yolov8n model(or even a custom model mixed with few objects), I know I can specifically filter out things that doesn't interest me by their ID as below: But, when I caught the an object that I am interested, can I at that time or at that frame, issue a track command to start tracking it? if it can be done, can you tell me how? an short example will be even better! thanks in advance. |
Beta Was this translation helpful? Give feedback.
-
|
@tumitoto007 hey there! 😊 It's great to hear that YOLOv8 has been a breeze for your project. Regarding your question about initiating tracking on a specific object at a certain frame, YOLOv8's tracking functionality is designed to automatically track all detected objects continuously across frames. However, if you're interested in tracking a specific object after its detection, you can filter detections by their IDs as you've mentioned and then focus on tracking that specific object ID across the frames. Here's a simplified example to illustrate how you might approach this: from ultralytics import YOLO
# Load your model
model = YOLO('yolov8n.pt') # or your custom model
# Assuming you're processing video frames in a loop
interested_object_id = None # Placeholder for the ID of the object you're interested in tracking
for frame in video_frames:
results = model.track(frame, persist=True)
for box in results[0].boxes:
objectID = box.id.item() # Get the ID of the current object
if objectID == interested_object_id:
# This is the object you're interested in, now you can track it specifically
# Process the tracking data as needed
passIn this example, Remember, the tracking starts automatically for all detected objects, so the key is filtering and focusing on the object of interest in your processing loop. Hope this helps! If you have any more questions or need further assistance, feel free to ask. Happy tracking! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Cool! I will give this a try once I get back to town. Thanks again for your great support. |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 🎉 I'm thrilled to hear you're planning to give tracking a try with YOLOv8 once you're back in town. It sounds like you're on an exciting journey with your project! If you have any questions or need further assistance when you dive into it, don't hesitate to reach out. Our community and docs are here to support you every step of the way. Happy tracking, and safe travels back to town! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hi, I want some detailed help and guidance on how to use custom tracker models with my custom yolov8 pose model, the Re-identification problem is being face using bytetrack.yaml so I think I should use StrongSORT or DeepSORT. Therefore, I want the ultralytics team to help me on selecting my tracker model or use multiple tracker models, and guide me properly on how to use them with my YOLOv8 custom trained model. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
@KhizarHashmi hi there! 👋 It sounds like you're exploring advanced tracking options for your custom YOLOv8 pose model. If ByteTrack isn't meeting your re-identification needs, exploring StrongSORT or DeepSORT could indeed be beneficial. These trackers offer sophisticated mechanisms for handling occlusions and maintaining identity across frames, which might be what you're looking for. To integrate a custom tracker like StrongSORT or DeepSORT with your YOLOv8 model, you'll typically need to:
Here's a simplified example of how you might set this up in Python, assuming you have a function from ultralytics import YOLO
# Load your custom trained YOLOv8 model
model = YOLO('path/to/your/custom_model.pt')
# Function to perform detection and tracking on a frame
def detect_and_track(frame):
# Perform detection
results = model(frame)
# Extract detections (example format, adjust as needed)
detections = results.pandas().xyxy[0] # DataFrame of detections
# Perform tracking with your custom tracker
tracked_objects = custom_tracker(detections)
return tracked_objects
# Example usage with a video stream
# ... video capture setup here ...
while True:
ret, frame = cap.read()
if not ret:
break
tracked_objects = detect_and_track(frame)
# ... visualization and further processing here ...Regarding using multiple trackers, it's possible to switch between trackers based on the scenario or even combine their strengths, though this can get complex. You might start with one tracker and evaluate its performance thoroughly before experimenting with combining them. For more detailed guidance on integrating specific trackers or handling complex tracking scenarios, the documentation and community forums for those trackers can be valuable resources. Additionally, our Ultralytics Docs provide further insights into tracking configurations and options. If you're developing new tracking capabilities or have insights to share, we'd love to see your contributions to our GitHub repo. Your expertise could greatly benefit the YOLO and tracking community! 🚀 Hope this helps! Let us know if you have more questions. |
Beta Was this translation helpful? Give feedback.
-
|
import random opening the file in read modemy_file = open("utils/coco.txt", "r") reading the filedata = my_file.read() replacing end splitting the text | when newline ('\n') is seen.class_list = data.split("\n") Generate random colors for class listdetection_colors = [] load a pretrained YOLOv8n modelmodel = YOLO("weights/yolov8n.pt", "v8") Vals to resize video frames | small frame optimise the runframe_wid = 640 def CarBehaviour(frame, color_threshold=1100): def detect_and_draw(frame, model, class_list, detection_colors): Open video capturecap = cv2.VideoCapture("/home/opencv_env/Vehicle-rear-lights-analyser-master/testing_data/road_2.mp4") if not cap.isOpened(): while True: When everything done, release the capturecap.release() |
Beta Was this translation helpful? Give feedback.
-
|
Absolutely, you can add tracking IDs to your detections using YOLOv8! 🚀 To do this, you'll want to utilize the Here's a simplified example to get you started: from ultralytics import YOLO
# Load your model
model = YOLO("weights/yolov8n.pt")
# Assuming 'frame' is your input frame
results = model.track(source=[frame])
# Now, each detected object in 'results' has a unique tracking ID
for det in results[0].boxes:
# Extract tracking ID
track_id = det.id.cpu().numpy()
print(f"Tracking ID: {track_id}")This will print the tracking ID for each detected object in the frame. Make sure to loop over your video frames to continuously track objects. Happy tracking! 🎉 |
Beta Was this translation helpful? Give feedback.
-
|
Hello, thank you very much for your work on computer vision. I had a problem in development. For the same test video, the same model is used. When I use predict mode and track mode, there is a large performance gap in target recognition. This is reflected in that fewer target boxes are detected in track mode than in predict mode. I used the default byteTrack tracker or BoT Tracker. I have adjusted the tracker's hyperparameters for many times, but the problem has not been solved. May I ask why? |
Beta Was this translation helpful? Give feedback.
-
|
I can provide my predict output at conf=0.5 and the track output(same conf=0.5) using the default bytetrack parameter. As down below, you can see, the ball detected were many times ignored in track mode. predict output: track output: |
Beta Was this translation helpful? Give feedback.
-
|
@BlackiePiggy it seems the issue might be related to the tracker's confidence threshold settings. In tracking mode, objects with confidence scores below |
Beta Was this translation helpful? Give feedback.
-
|
I'm trying to use the above example to track hockey players. I have tried many different configurations without great success. (ByteTrack and Botsort) As well as trying to use norrfair. If you watch the video you can see ID:4 changes many times after occlusion with another player. I have uploaded my examples to https://github.com/clearpaint/yolo/ |
Beta Was this translation helpful? Give feedback.
-
|
@clearpaint to address the ID switching and reassignment issues, consider adjusting the |
Beta Was this translation helpful? Give feedback.
-
|
so tired some different setting # Ultralytics YOLO 🚀, AGPL-3.0 license Optimized YOLO tracker settings for improved ID consistency with ByteTrack trackerhttps://github.com/ifzhang/ByteTracktracker_type: bytetrack # tracker type, ['botsort', 'bytetrack'] Tracking thresholdstrack_high_thresh: 0.5 # Increased threshold for the first association track_buffer: 60 # Extended buffer to maintain tracks longer fuse_score: False # Disabled score fusion to prevent misassociation and : Ultralytics YOLO 🚀, AGPL-3.0 licenseOptimized YOLO tracker settings for improved ID consistency with BoT-SORT trackerhttps://github.com/NirAharon/BoT-SORTtracker_type: botsort # tracker type, ['botsort', 'bytetrack'] Tracking thresholdstrack_high_thresh: 0.4 # Increased threshold for the first association track_buffer: 60 # Extended buffer to maintain tracks longer fuse_score: False # Disabled score fusion to prevent misassociation BoT-SORT settingsgmc_method: sparseOptFlow # Method of global motion compensation ReID model settingsproximity_thresh: 0.4 # Adjusted proximity threshold for spatial matching neither yielded much better results. |
Beta Was this translation helpful? Give feedback.
-
|
It sounds like you're facing challenges with ID consistency in your tracking setup. Consider adjusting the |
Beta Was this translation helpful? Give feedback.
-
|
Hi @glenn-jocher , Is it possible for someone to help try run this example? I have tried many configuration all without great success. Most of the changes have actually made it worse. Its curious how good the example looks maybe its just the speed and repeated occlusions are just not trackable? https://www.youtube.com/watch?v=OrTciwKdSdA https://www.youtube.com/embed/OrTciwKdSdA?si=QrNWbCytZV3ebWka |
Beta Was this translation helpful? Give feedback.
-
|
It seems like you're encountering challenges with maintaining consistent tracking IDs. This could be due to rapid movements or occlusions in your video. Consider fine-tuning parameters like |
Beta Was this translation helpful? Give feedback.
-
|
Hi we found that object id fluctuating within 19000 - 24000 is there any solution or controllable variable? |
Beta Was this translation helpful? Give feedback.
-
|
Solved by link
|
Beta Was this translation helpful? Give feedback.
-
|
@tofulim thank you for sharing your observations. The issue with fluctuating object IDs could be related to the tracker configuration or the confidence threshold settings. You might want to adjust the |
Beta Was this translation helpful? Give feedback.
-
|
@tofulim , I don't understand what you mean ? How does using reset correct the ids? |
Beta Was this translation helpful? Give feedback.
-
|
hi @clearpaint , i didn't mean that using reset correct object's id. but it prevent object id's inconsistency my hypothesis was when object_id getting bigger, it overflowed. at first i tested with short mp4 files, infinitely streaming with RTSP. i found that object_id was consistent but after some times passed(more than 1 day) object id increased over 18k and i found that object_id's fluctuation. so i reset the tracker when object_id reached over 10k. then obejct_id changing has gone. (i tested this morning) |
Beta Was this translation helpful? Give feedback.
-
|
sry, our engine has fast FPS(nearby 7) when it initialized then slowly converge to lower FPS(nearby 5). and i found that on lower FPS we got track id fluctuation because each frames of sequence has more time gap. so i thought increasing track_id was the problem but it was not true. time gap on input frame sequence was the problem. so glenn was right
|
Beta Was this translation helpful? Give feedback.
-
|
I have a problem with the tracker. I trained Segmentation Model 11, and tried the tracker with the model, but the tracker gives different IDs for the same object. How can I fix that? Are there any tips to solve the problem? Note: I read all the documents on the site but did not find a solution to my problem thank you for your help ! |
Beta Was this translation helpful? Give feedback.
-
|
@NasserAlqeifi it sounds like the tracker may be losing track of the object between frames, which can cause inconsistent IDs. You can try adjusting the |
Beta Was this translation helpful? Give feedback.
-
|
Hi, I'm using yolo11, with weights I trained myself. For some reason, the predict and track results are completely the same: model = YOLO(weights) After printing / plotting the annotations, it seems it exactly the same. Thank you in advance! |
Beta Was this translation helpful? Give feedback.
-
|
@guetaro it sounds like the ByteTrack tracker might not be configured or functioning as expected. Please check the |
Beta Was this translation helpful? Give feedback.
-
|
@glenn-jocher you keep referencing the "Documentation" but its not really documented how each parameter is to be used or interpreted. The answer seems to always be "play with the parameters." |
Beta Was this translation helpful? Give feedback.
-
|
@clearpaint thank you for your feedback. We understand your concern, and while experimenting with parameters is often necessary due to the variability of use cases, we're continuously working to enhance our documentation. For specific guidance, please visit the Track Mode documentation for examples and detailed parameter descriptions. |
Beta Was this translation helpful? Give feedback.
-
|
Hi @glenn-jocher, Thanks for your answer. I kept debugging this issue, and maybe got my solution. It seems the tracker's output contain both tracked and predicted results (results from predict and from tracker), Am I right? Thanks again. |
Beta Was this translation helpful? Give feedback.
-
|
Yes, you're correct. In the tracking results, |
Beta Was this translation helpful? Give feedback.
-
|
I have a model trained on about 1200 images (including augmented images) my project is to detect if there are 0,1 or 2 monkeys within each frame of the video. However if for example there is only one monkey seen in the frame the label will switch randomly between the two label names I have (for now we will say “monkey1” and “monkey2”). This is a problem for me because I save all the cropped images of each label and play it as a video for a closeup view. So then my cropped images will not be consistent. I have done the model.track(persist=True, agnostic_nms=True, iou=0.50) in order to try and reduce the likelihood of this happening however it still does more often then I would like. What options do I have in order to fix this or reduce the likelihood? I am also using Yolov11 fyi. Thank you so much for anything you come up with I’ve been stuck for weeks |
Beta Was this translation helpful? Give feedback.
-
|
@tylerfrisinger01 it sounds like you're encountering issues with label consistency during tracking. To improve this, you might try using a more robust tracker like ByteTrack, which can be enabled with |
Beta Was this translation helpful? Give feedback.
-
|
i want to know the yolo model can process every resolution images as it is. or the process only for decided resolution (640,640). do you convert image size before the inference internally? |
Beta Was this translation helpful? Give feedback.
-
|
@Ranjith3436 ultralytics YOLO models internally resize input images to a default resolution (e.g., 640x640 for most configurations) before inference, ensuring consistency in preprocessing and performance optimization. This resizing happens automatically, so users can input images of any resolution without manual adjustments. |
Beta Was this translation helpful? Give feedback.
-
|
Can we use tracker mode other than bot sort and bytetrack? for example with deepsort tracker. |
Beta Was this translation helpful? Give feedback.
-
|
@ds-dinis007 currently, Ultralytics YOLO supports BoT-SORT and ByteTrack trackers out of the box. To use a custom tracker like DeepSORT, you would need to modify or create a new tracker configuration file in the |
Beta Was this translation helpful? Give feedback.
-
|
Hello, First, thank you for providing such excellent documentation! It has been incredibly helpful. I’m currently working on using the tracking model with my custom dataset, saving the tracking results, and eventually evaluating the performance using the TrackEval tool. Below is a snippet of my script that runs inference on video frames and writes the results to an output text file: cap = cv2.VideoCapture(video_path)
with open(output_file, 'w') as f:
frame_id = 0
while cap.isOpened():
success, frame = cap.read()
if not success:
break
results = model.track(frame, persist=True, tracker=tracker, conf=0.2, iou=0.25, classes=[0], verbose=False)
if results[0].boxes is not None:
for box in results[0].boxes:
bbox = box.xyxy[0].tolist()
track_id = int(box.id.item()) # if box.id is not None else -1
conf = box.conf.item() if box.conf is not None else -1
f.write(f'{frame_id+1},{track_id},{bbox[0]:.2f},{bbox[1]:.2f},{bbox[2]-bbox[0]:.2f},{bbox[3]-bbox[1]:.2f},{conf:.2f},-1,-1,-1\n')However, I encountered an issue with the line: track_id = int(box.id.item())This results in the error: "AttributeError: 'NoneType' object has no attribute 'item'". To work around this, I assigned arbitrary IDs to entities without a box.id. Unfortunately, this led to another issue: Could you kindly advise on how to resolve this issue? I would greatly appreciate your guidance. Thank you in advance! |
Beta Was this translation helpful? Give feedback.
-
|
@jaehongk thank you for your detailed question! The error occurs because if box.id is not None:
track_id = int(box.id.item())
# Write track_id and other details to the fileThis should prevent duplicate ID issues. Let me know if you encounter further challenges! |
Beta Was this translation helpful? Give feedback.
-
|
I have a question. When using the tracking module for target tracking and counting, is the processing time for each image printed just the YOLO time or does it include the post-tracking processing time? |
Beta Was this translation helpful? Give feedback.
-
|
@GItWPP to measure the post-tracking processing time, you can use Python's |
Beta Was this translation helpful? Give feedback.
-
|
Thanks again for your reply! As per your suggestion I tried to write this part of the code and got the following result. But I'm not so sure that's right(I'm a rookie, HHHH). print: sample code: def obj_count(): |
Beta Was this translation helpful? Give feedback.
-
|
Your implementation to measure post-tracking processing time using |
Beta Was this translation helpful? Give feedback.
-
|
Thank you for your answer！ |
Beta Was this translation helpful? Give feedback.
-
|
@GItWPP you're welcome! Your approach to measuring the post-tracking processing time looks solid. For further customization of the tracking process, you can explore the |
Beta Was this translation helpful? Give feedback.
-
|
Hi , I have fine tuned a segmentation model on my dataset, can I use it as my model in tracking or it must be a detection model? |
Beta Was this translation helpful? Give feedback.
-
|
@shahedmomenzadeh yes, you can use your fine-tuned segmentation model for tracking. Ultralytics YOLO supports tracking with detection, segmentation, and pose models. For detailed usage, refer to the tracking documentation. |
Beta Was this translation helpful? Give feedback.
-
|
Hi everyone, I'm working with YOLOv8 and would like to use a tracker that's not natively implemented in the ultralytics library, such as Samurai or BoostTrack++. Could someone provide an example of how to integrate one of these external trackers with YOLOv8? Any guidance or example code would be greatly appreciated. Thank you in advance! |
Beta Was this translation helpful? Give feedback.
-
|
@AxionMax thank you for your inquiry! While YOLOv8 natively supports trackers like BoT-SORT and ByteTrack, integrating external trackers like Samurai or BoostTrack++ requires modifying the codebase. You can implement this by adapting the tracker logic in the |
Beta Was this translation helpful? Give feedback.
-
|
Hi everyone, |
Beta Was this translation helpful? Give feedback.
-
|
@rohith-aiunika object IDs in YOLO tracking are assigned by the selected tracker, such as BoT-SORT or ByteTrack, based on consistent detections across frames. To reduce the confidence threshold for assigning IDs, set the |
Beta Was this translation helpful? Give feedback.
-
|
Hi, can you please tell me if the tracker works better on more modern version of ultralytics or version 8.3.68 is no different from 8.1.34 ? (When using botsort.yaml) |
Beta Was this translation helpful? Give feedback.
-
|
@Boaruzhan the performance of trackers like BoT-SORT (via |
Beta Was this translation helpful? Give feedback.
-
|
Is it good to have more points in my label file? my dataset size is 30k images having total of 16 classes |
Beta Was this translation helpful? Give feedback.
-
|
@rohith-aiunika thank you for your question! For segmentation tasks, having more points in your labels can provide higher precision but may increase computational load. We recommend reviewing a sample of your auto-annotated masks - if they maintain good object boundaries while being reasonably efficient, they're likely acceptable. For optimal performance, ensure your annotations balance precision with simplicity. You might consider using polygon simplification tools if points are excessively redundant while preserving mask accuracy. |
Beta Was this translation helpful? Give feedback.
and others
-
modes/track/
Learn how to use Ultralytics YOLO for object tracking in video streams. Guides to use different trackers and customise tracker configurations.
https://docs.ultralytics.com/modes/track/
Beta Was this translation helpful? Give feedback.
All reactions