ByteTrack is a simple, fast and strong multi-object tracker.

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang

arXiv 2110.06864

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories. To solve this problem, we present a simple, effective and generic association method, tracking by associating every detection box instead of only the high score ones. For the low score detection boxes, we utilize their similarities with tracklets to recover true objects and filter out the background detections. When applied to 9 different state-of-the-art trackers, our method achieves consistent improvement on IDF1 score ranging from 1 to 10 points.To put forwards the state-of-the-art performance of MOT, we design a simple and strong tracker, named ByteTrack. For the first time, we achieve 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU.

Step1. Install ByteTrack.

git clone https://github.com/ifzhang/ByteTrack.git
cd ByteTrack
pip3 install -r requirements.txt
python3 setup.py develop

Step2. Install pycocotools.

pip3 install cython; pip3 install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

Step3. Others

pip3 install cython_bbox

docker build -t bytetrack:latest .

# Startup sample
mkdir -p pretrained && \
mkdir -p YOLOX_outputs && \
xhost +local: && \
docker run --gpus all -it --rm \
-v $PWD/pretrained:/workspace/ByteTrack/pretrained \
-v $PWD/datasets:/workspace/ByteTrack/datasets \
-v $PWD/YOLOX_outputs:/workspace/ByteTrack/YOLOX_outputs \
-v /tmp/.X11-unix/:/tmp/.X11-unix:rw \
--device /dev/video0:/dev/video0:mwr \
--net=host \
-e XDG_RUNTIME_DIR=$XDG_RUNTIME_DIR \
-e DISPLAY=$DISPLAY \
--privileged \
bytetrack:latest

Download MOT17, MOT20, CrowdHuman, Cityperson, ETHZ and put them under <ByteTrack_HOME>/datasets in the following structure:

datasets
   |——————mot
   |        └——————train
   |        └——————test
   └——————crowdhuman
   |         └——————Crowdhuman_train
   |         └——————Crowdhuman_val
   |         └——————annotation_train.odgt
   |         └——————annotation_val.odgt
   └——————MOT20
   |        └——————train
   |        └——————test
   └——————Cityscapes
   |        └——————images
   |        └——————labels_with_ids
   └——————ETHZ
            └——————eth01
            └——————...
            └——————eth07

Then, you need to turn the datasets to COCO format and mix different training data:

cd <ByteTrack_HOME>
python3 tools/convert_mot17_to_coco.py
python3 tools/convert_mot20_to_coco.py
python3 tools/convert_crowdhuman_to_coco.py
python3 tools/convert_cityperson_to_coco.py
python3 tools/convert_ethz_to_coco.py

Before mixing different datasets, you need to following the operations in mix_xxx.py to create data folder and link. Finally you can mix the training data:

cd <ByteTrack_HOME>
python3 tools/mix_data_ablation.py
python3 tools/mix_data_test_mot17.py
python3 tools/mix_data_test_mot20.py

Train on CrowdHuman and MOT17 half train, evaluate on MOT17 half val

Train on CrowdHuman, MOT17, Cityperson and ETHZ, evaluate on MOT17 train

Train on CrowdHuman and MOT20, evaluate on MOT20 train

The COCO pretrained YOLOX model can be downloaded from their model zoo. After downloading the pretrained models, you can put them under <ByteTrack_HOME>/pretrained.

• Train ablation model (MOT17 half train and CrowdHuman)

cd <ByteTrack_HOME>
python3 tools/train.py -f exps/example/mot/yolox_x_ablation.py -d 8 -b 48 --fp16 -o -c pretrained/yolox_x.pth

• Train MOT17 test model (MOT17 train, CrowdHuman, Cityperson and ETHZ)

cd <ByteTrack_HOME>
python3 tools/train.py -f exps/example/mot/yolox_x_mix_det.py -d 8 -b 48 --fp16 -o -c pretrained/yolox_x.pth

• Train MOT20 test model (MOT20 train, CrowdHuman)

For MOT20, you need to clip the bounding boxes inside the image.

Add clip operation in line 134-135 in data_augment.py, line 122-125 in mosaicdetection.py, line 217-225 in mosaicdetection.py, line 115-118 in boxes.py.

cd <ByteTrack_HOME>
python3 tools/train.py -f exps/example/mot/yolox_x_mix_mot20_ch.py -d 8 -b 48 --fp16 -o -c pretrained/yolox_x.pth

• Evaluation on MOT17 half val

Run ByteTrack:

cd <ByteTrack_HOME>
python3 tools/track.py -f exps/example/mot/yolox_x_ablation.py -c pretrained/bytetrack_ablation.pth.tar -b 1 -d 1 --fp16 --fuse

You can get 76.6 MOTA using our pretrained model.

Run other trackers:

python3 tools/track_sort.py -f exps/example/mot/yolox_x_ablation.py -c pretrained/bytetrack_ablation.pth.tar -b 1 -d 1 --fp16 --fuse
python3 tools/track_deepsort.py -f exps/example/mot/yolox_x_ablation.py -c pretrained/bytetrack_ablation.pth.tar -b 1 -d 1 --fp16 --fuse
python3 tools/track_motdt.py -f exps/example/mot/yolox_x_ablation.py -c pretrained/bytetrack_ablation.pth.tar -b 1 -d 1 --fp16 --fuse

• Test on MOT17

Run ByteTrack:

cd <ByteTrack_HOME>
python3 tools/track.py -f exps/example/mot/yolox_x_mix_det.py -c pretrained/bytetrack_x_mot17.pth.tar -b 1 -d 1 --fp16 --fuse
python3 tools/interpolation.py

Submit the txt files to MOTChallenge website and you can get 79+ MOTA (For 80+ MOTA, you need to carefully tune the test image size and high score detection threshold of each sequence).

• Test on MOT20

We use the input size 1600 x 896 for MOT20-04, MOT20-07 and 1920 x 736 for MOT20-06, MOT20-08. You can edit it in yolox_x_mix_mot20_ch.py

Run ByteTrack:

cd <ByteTrack_HOME>
python3 tools/track.py -f exps/example/mot/yolox_x_mix_mot20_ch.py -c pretrained/bytetrack_x_mot20.pth.tar -b 1 -d 1 --fp16 --fuse --match_thresh 0.7 --mot20
python3 tools/interpolation.py

Submit the txt files to MOTChallenge website and you can get 77+ MOTA (For higher MOTA, you need to carefully tune the test image size and high score detection threshold of each sequence).

See tutorials.

cd <ByteTrack_HOME>
python3 tools/demo_track.py video -f exps/example/mot/yolox_x_mix_det.py -c pretrained/bytetrack_x_mot17.pth.tar --fp16 --fuse --save_result

1. ONNX export and ONNXRuntime
2. TensorRT in Python
3. TensorRT in C++
4. ncnn in C++

@article{zhang2021bytetrack,
  title={ByteTrack: Multi-Object Tracking by Associating Every Detection Box},
  author={Zhang, Yifu and Sun, Peize and Jiang, Yi and Yu, Dongdong and Yuan, Zehuan and Luo, Ping and Liu, Wenyu and Wang, Xinggang},
  journal={arXiv preprint arXiv:2110.06864},
  year={2021}
}

A large part of the code is borrowed from YOLOX, FairMOT, TransTrack and JDE-Cpp. Many thanks for their wonderful works.