BrainPotter / SANVOT

Official code for the paper "Siamese Adaptive Network-based Accurate and Robust Visual Object Tracking Algorithm for Quadrupedal Robots"

SANVOT

This probject hosts the code for implementing the SANVOT algorithm for visual tracking on a Unitree quadruped robot.

The code based on the PySOT and SiamBAN.

Installation

Please find installation instructions in INSTALL.md.

Quick Start: Using SANVOT

Add SANVOT to your PYTHONPATH

export PYTHONPATH=/path/to/sanvot:$PYTHONPATH

Webcam demo

python tools/demo.py \
    --config experiments/sanvot_r50_l234/config.yaml \
    --snapshot experiments/sanvot_r50_l234/model.pth
    # --video demo/bag.avi # (in case you don't have webcam)

Download testing datasets

Download datasets and put them into testing_dataset directory. Jsons of commonly used datasets can be downloaded from here or here, extraction code: 8fju. If you want to test tracker on new dataset, please refer to pysot-toolkit to setting testing_dataset.

Test tracker

cd experiments/sanvot_r50_l234
python -u ../../tools/test.py 	\
	--snapshot model.pth 	\ # model path
	--dataset VOT2018 	\ # dataset name
	--config config.yaml	  # config file

The testing results will in the current directory(results/dataset/model_name/)

Eval tracker

assume still in experiments/sanvot_r50_l234

python ../../tools/eval.py 	 \
	--tracker_path ./results \ # result path
	--dataset VOT2018        \ # dataset name
	--num 1 		 \ # number thread to eval
	--tracker_prefix 'model'   # tracker_name

Eval on untriee quadrupedal robot with a RealSense D455 Depth Camera

assume in tools

python demo.py