Object tracking using Roboflow Inference API and zeroshot CLIP Deep SORT. More on CLIP
Example object tracking courtesy of the Roboflow Universe public playing cards model and dataset. You can adapt this to your own dataset on Roboflow.
Upload, annotate, and train your model on Roboflow with Roboflow Train. Your model will be hosted on an inference URL.
Clone repositories
git clone https://github.com/roboflow-ai/roboflow-object-tracking
cd roboflow-object-tracking
git clone https://github.com/openai/CLIP.git CLIP-repo
cp -r ./CLIP-repo/clip ./clip
Install requirements (python 3.7+)
pip install --upgrade pip
pip install -r requirements.txt
Install requirements (anaconda python 3.8)
conda install pytorch torchvision torchaudio -c pytorch
conda install ftfy regex
pip install opencv pycocotools tensorflow
Run
python clip_object_tracker.py --source data/video/cards.mp4 --url https://detect.roboflow.com/playing-cards-ow27d/1 --api_key ROBOFLO_API_KEY
(by default, output will be in runs/detect/exp[num])
Help
python clip_object_tracker.py -h
Huge thanks to: