How to print the all the pedestrian trajectories within a period of time

[ArielZhanghj]

Search before asking

• I have searched the YOLOv8 issues and discussions and found no similar questions.

Question

Thank you for your time in advance. There are two questions in print save trajectory and tracking details.
Firstly, I found add the ‘save_txt’ to ‘results = model track( )’ can put the text as s shown in the figure below. The last column shows all the pedestrian IDs recognized for each frame, but I'd like to also be able to derive what frame the recognition resulted in. I should know the time factor later. Is there anything that can be done？
Secondly, in order to get the trajectory and show all the pedestrian trajectories which are recognized within a period of time in the picture, How should it be done? Is there a better way than the previous one (my plan was to get the coordinate information of all pedestrians in each frame and concatenate the coordinates of pedestrians with the same id, but in reality, when the video is outputted, the trajectory is actually outputted)

Additional

No response

[glenn-jocher]

Hello! Thanks for reaching out with your questions. Let's tackle them one by one:

1. Frame Information in Tracking Output: To include frame information in your tracking output, you can modify the output format in your tracking script. For each detection, append the frame number to the saved text file. Here's a quick example of how you might adjust your tracking loop:

   for frame_idx, frame in enumerate(video_frames):
       results = model.track(frame)
       for result in results:
           with open('output.txt', 'a') as f:
               f.write(f'{frame_idx} {result}\n')

   This will prepend the frame index to each line of the output file, allowing you to track when each detection occurs.

2. Visualizing Pedestrian Trajectories: To visualize trajectories over a period, you can accumulate the coordinates for each pedestrian ID over frames and then plot them. Here’s a simplified approach:

   import matplotlib.pyplot as plt
   
   trajectories = {}
   for frame_idx, frame in enumerate(video_frames):
       results = model.track(frame)
       for result in results:
           id = result.id
           if id not in trajectories:
               trajectories[id] = []
           trajectories[id].append((frame_idx, result.xyxy[0], result.xyxy[1]))  # Assuming xyxy format
   
   # Plotting
   for id, trajectory in trajectories.items():
       x = [coord[1] for coord in trajectory]
       y = [coord[2] for coord in trajectory]
       plt.plot(x, y, label=f'ID {id}')
   
   plt.legend()
   plt.show()

This script collects coordinates for each ID and plots them. Adjust the coordinate extraction based on your specific bbox format (xyxy, xywh, etc.).

I hope this helps! Let me know if you have any more questions. 😊