Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

tensorworksio/mot.cpp

Repository files navigation

Multi Object Tracking

Yet another C++ adaptation of SOTA multi-object tracking algorithm

Demo

Supported Trackers

Dataset

Get the MOT dataset of your choice from MOT website

cd data
wget https://motchallenge.net/data/MOT20.zip
unzip MOT20.zip && rm MOT20.zip

Configure

In config folder, add your custom tracker config

SORT
tracker = "sort"
max_time_lost = 15
match_thresh = 0.3
[kalman]
time_step = 1
process_noise_scale = 1.0
measurement_noise_scale = 1.0
BoTSORT
tracker = "botsort"
max_time_lost = 15
track_high_thresh = 0.5
track_low_thresh = 0.1
new_track_thresh = 0.6
first_match_thresh = 0.3
second_match_thresh = 0.1
unconfirmed_match_thresh = 0.2
proximity_thresh = 0.5
appearance_thresh = 0.9
[kalman]
time_step = 1
process_noise_scale = 1.0
measurement_noise_scale = 1.0

πŸ–₯️ Local

Compile

# Ensure to reset the deps
meson subprojects update --reset
meson setup build --wipe
meson compile -C build
meson test -C build

Run

cd build/app
./mot -h
# Example
./mot -i data/MOT20/train/<seq-name> -c config/sort.toml --display

Evaluate

First, set up your Python environment and dependencies:

python3 -m venv venv
./venv/bin/pip install -r requirements.txt

Then run the evaluation script:

chmod +x mot-eval.sh
./mot-eval.sh --dataset data/MOT20 --split train --config app/config/sort.toml --save
# experiment output available in runs folder

🐳 Docker

Build the image:

docker build -t mot.cpp .

Run the tracker on a dataset sequence mounted from the host:

# Allow Docker to connect to the X11 display server
xhost +local:docker
docker run --rm \
 --user $(id -u):$(id -g) \
 --env DISPLAY=$DISPLAY \
 -v /tmp/.X11-unix:/tmp/.X11-unix:ro \
 -v $(pwd)/data:/data \
 -v $(pwd)/app/config:/opt/mot.cpp/app/config \
 mot.cpp -i /data/MOT20/train/MOT20-01 -c /opt/mot.cpp/app/config/sort.toml --display

Run evaluation across a full dataset split:

docker run --rm \
 --user $(id -u):$(id -g) \
 -v $(pwd)/data:/data \
 -v $(pwd)/runs:/opt/mot.cpp/runs \
 --entrypoint /opt/mot.cpp/mot-eval.sh \
 mot.cpp --dataset /data/MOT20 --split train --config /opt/mot.cpp/app/config/sort.toml --save

Run with your detector

https://github.com/tensorworksio/TensorRT-Vision/tree/main/app/mot

About

SOTA Multi Object Tracker in Cpp

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

Contributors

AltStyle γ«γ‚ˆγ£γ¦ε€‰ζ›γ•γ‚ŒγŸγƒšγƒΌγ‚Έ (->γ‚ͺγƒͺγ‚ΈγƒŠγƒ«) /