https://github.com/cj-mills/cjm-byte-track
A standalone Python implementation of the ByteTrack multi-object tracker based on the official implementation.
https://github.com/cj-mills/cjm-byte-track
Last synced: 8 months ago
JSON representation
A standalone Python implementation of the ByteTrack multi-object tracker based on the official implementation.
- Host: GitHub
- URL: https://github.com/cj-mills/cjm-byte-track
- Owner: cj-mills
- License: mit
- Created: 2023-10-25T23:06:32.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-10-27T19:33:52.000Z (almost 2 years ago)
- Last Synced: 2025-02-12T19:43:03.891Z (8 months ago)
- Language: Jupyter Notebook
- Homepage: https://cj-mills.github.io/cjm-byte-track/
- Size: 438 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# cjm-byte-track
A standalone Python implementation of the
[ByteTrack](https://arxiv.org/abs/2110.06864) multi-object tracker based
on the [official
implementation](https://github.com/ifzhang/ByteTrack/tree/main/yolox/tracker).
## Install
``` sh
pip install cjm_byte_track
```
## Tutorial:
- [**Real-Time Object Tracking with YOLOX and
ByteTrack:**](https://christianjmills.com/posts/pytorch-train-object-detector-yolox-tutorial/byte-track/)
Learn how to track objects across video frames with YOLOX and
ByteTrack.
## How to use
``` python
# Import ByteTrack package
from cjm_byte_track.core import BYTETracker
from cjm_byte_track.matching import match_detections_with_tracks
```
``` python
# Initialize a ByteTracker object
tracker = BYTETracker(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=frame_fps)
with tqdm(total=frames, desc="Processing frames") as pbar:
while video_capture.isOpened():
ret, frame = video_capture.read()
if ret:
# Prepare an input image for inference
rgb_img, input_dims, offsets, min_img_scale, input_img = prepare_image_for_inference(frame, test_sz, max_stride)
# Convert the existing input image to NumPy format
input_tensor_np = np.array(input_img, dtype=np.float32).transpose((2, 0, 1))[None]/255
# Start performance counter`m
start_time = time.perf_counter()
# Run inference
outputs = session.run(None, {"input": input_tensor_np})[0]
# Process the model output
proposals = process_outputs(outputs, input_tensor_np.shape[input_dim_slice], bbox_conf_thresh)
# Apply non-max suppression to the proposals with the specified threshold
proposal_indices = nms_sorted_boxes(calc_iou(proposals[:, :-2]), iou_thresh)
proposals = proposals[proposal_indices]
bbox_list = (proposals[:,:4]+[*offsets, 0, 0])*min_img_scale
label_list = [class_names[int(idx)] for idx in proposals[:,4]]
probs_list = proposals[:,5]
# Update tracker with detections.
track_ids = [-1]*len(bbox_list)
# Convert to tlbr format
tlbr_boxes = bbox_list.copy()
tlbr_boxes[:, 2:4] += tlbr_boxes[:, :2]
# Update tracker with detections
tracks = tracker.update(
output_results=np.concatenate([tlbr_boxes, probs_list[:, np.newaxis]], axis=1),
img_info=rgb_img.size,
img_size=rgb_img.size)
track_ids = match_detections_with_tracks(tlbr_boxes=tlbr_boxes, track_ids=track_ids, tracks=tracks)
# End performance counter
end_time = time.perf_counter()
# Calculate the combined FPS for object detection and tracking
fps = 1 / (end_time - start_time)
# Display the frame rate in the progress bar
pbar.set_postfix(fps=fps)
# Filter object detections based on tracking results
bbox_list, label_list, probs_list, track_ids = zip(*[(bbox, label, prob, track_id)
for bbox, label, prob, track_id
in zip(bbox_list, label_list, probs_list, track_ids) if track_id != -1])
# Annotate the current frame with bounding boxes and tracking IDs
annotated_img = draw_bboxes_pil(
image=rgb_img,
boxes=bbox_list,
labels=[f"{track_id}-{label}" for track_id, label in zip(track_ids, label_list)],
probs=probs_list,
colors=[int_colors[class_names.index(i)] for i in label_list],
font=font_file,
)
annotated_frame = cv2.cvtColor(np.array(annotated_img), cv2.COLOR_RGB2BGR)
video_writer.write(annotated_frame)
pbar.update(1)
else:
break
video_capture.release()
video_writer.release()
```