Technography for trajectory prediction. Part of the Surfacing Suspicion project.
Find a file
2023-05-09 16:46:19 +02:00
utils Rename to different notebooks, make GPU detector 2023-05-09 14:30:10 +02:00
01_detect_objects.ipynb Rename to different notebooks, make GPU detector 2023-05-09 14:30:10 +02:00
02_track_objects.ipynb Collect tracks and project them 2023-05-09 16:46:19 +02:00
poetry.lock Rename to different notebooks, make GPU detector 2023-05-09 14:30:10 +02:00
pyproject.toml Rename to different notebooks, make GPU detector 2023-05-09 14:30:10 +02:00
README.md Initial Notebook with RetinaNet Object Detection 2023-05-08 17:26:51 +02:00
sort_abewley.py Add original SORT implementation 2023-05-08 21:32:55 +02:00
sort_cfotache.py Rename to different notebooks, make GPU detector 2023-05-09 14:30:10 +02:00

Trajectory Prediction

Use object detector (e.g. RetinaNET, YOLO), and multi-object-tracker (e.g. SORT, DeepSORT) to capture trajectories. Then tinker with Weighted Networks (Hunger 2023) to create predictions of new movements.

Initiate

The project uses poetry. So to set it up:

poetry install

If using python notebook with Jupyter it might be useful to do:

poetry run python -m ipykernel install --user --name trajpred