security_vision
/
Towards-Realtime-MOT
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Fork from https://github.com/Zhongdao/Towards-Realtime-MOT for surfacing suspicion (PhD. research project)
92 Commits 1 Branch 0 Tags 45 MiB
Jupyter Notebook 99.7%
Python 0.3%
Go to file
Ruben van de Ven e4ac1c3aab Add torchreid (deep-person-reid) to docker and Readme 2023-05-01 15:56:14 +02:00
assets add gif demo 2019-10-02 20:04:00 +08:00
cfg change minor log annoyance 2023-04-05 17:17:35 +02:00
data fixed a spelling mistake 2020-01-10 13:26:52 +08:00
docker Add torchreid (deep-person-reid) to docker and Readme 2023-05-01 15:56:14 +02:00
tracker Store embeddings 2023-04-05 17:17:15 +02:00
utils change minor log annoyance 2023-04-05 17:17:35 +02:00
.gitignore ignore OUT 2023-04-13 13:12:07 +02:00
DATASET_ZOO.md Update DATASET_ZOO.md 2020-04-20 19:42:01 +08:00
LICENSE replace maskrcnn-benchmark nms with torchvision nms 2020-01-09 22:48:17 +08:00
README.md Add torchreid (deep-person-reid) to docker and Readme 2023-05-01 15:56:14 +02:00
README.original.md Add torchreid (deep-person-reid) to docker and Readme 2023-05-01 15:56:14 +02:00
demo.py save to temp folder, in higher quality 2023-04-24 18:20:22 +02:00
extract_ped_per_frame.py replace maskrcnn-benchmark nms with torchvision nms 2020-01-09 22:48:17 +08:00
live_track.ipynb pototype for live tracking 2023-04-24 18:20:35 +02:00
models.py Merge branch 'master' of https://github.com/Zhongdao/Towards-Realtime-MOT 2020-01-29 21:47:41 +08:00
test.py 1.Accelerate the association step. 2020-01-29 21:45:07 +08:00
track.py save to temp folder, in higher quality 2023-04-24 18:20:22 +02:00
train.py Documentation (#95) 2020-03-14 10:24:27 +08:00
visualise_embeddings.ipynb Not really live track yet, but test how it could work out 2023-04-21 17:23:20 +02:00

README.md

Repo built on Towards-Realtime-MOT, but now used to work with multiple (multiple) object trackers.

Towards Realtime MOT

See also Original Readme.

Torchreid Feature Extractor

See documentation.

Torchreid offers various pretrained models

# osnet_ain_x1_0
wget --content-disposition https://drive.google.com/uc?id=1-CaioD9NaqbHK_kzSMW8VE4_3KcsRjEo
# osnet_ain_x1_0_msmt17_256x128_amsgrad_ep50_lr0.0015_coslr_b64_fb10_softmax_labsmth_flip_jitter.pth
wget --content-disposition https://drive.google.com/uc?id=1SigwBE6mPdqiJMqhuIY4aqC7--5CsMal

TODO: