You can draw the corresponding bounding box into the image and save it according to the result file (txt format) run by the tracker.

Last update: Dec 06, 2022

Related tags

Deep Learning SOTDrawRect

Overview

SOTDrawRect

The purpose of this repo is to provide evaluation API of Current Single Object Tracking Dataset, including

Install

git clone https://github.com/Giveupfree/SOTDrawRect.git
pip install -r requirements.txt
cd toolkit/utils/
python setup.py build_ext --inplace

Update toolkit(optional)

The contents of the entire toolkit folder can be replaced directly from pysot-toolkit

Download Dataset

Download json files used in our toolkit baidu pan or Google Drive

Put CVRP13.json, OTB100.json, OTB50.json in OTB100 dataset directory (you need to copy Jogging to Jogging-1 and Jogging-2, and copy Skating2 to Skating2-1 and Skating2-2 or using softlink)

The directory should have the below format

| -- OTB100/

| -- Basketball

| ......

| -- Woman

| -- OTB100.json

| -- OTB50.json

| -- CVPR13.json
Put all other jsons in the dataset directory like in step 1

Usage

Draw rectangular boxes

cd /path/to/SOTDrawRect
python draw_rect.py \                     
	--dataset_dir /path/to/dataset/root \		# dataset path
	--dataset VOT2018 \				# dataset name(VOT2018, VOT2016, OTB100, GOT10k)
	--tracker_result_dir /path/to/tracker/dir \	# tracker dir
    	--format pdf \                              # save fomat (pdf,png,jpg)
	--trackers ours ECO UPDT SiamRPNpp \ 			# tracker names 
    	--save_dir \                                  # save dir

Draw a bounding box for a video sequence

cd /path/to/SOTDrawRect
python draw_rect.py \    
    	-- video videoname \                 
	--dataset_dir /path/to/dataset/root \		# dataset path
	--dataset VOT2018 \				# dataset name(VOT2018, VOT2016, OTB100, GOT10k)
	--tracker_result_dir /path/to/tracker/dir \	# tracker dir
    	--format pdf \                              # save fomat (pdf,png,jpg)
	--trackers ours ECO UPDT SiamRPNpp \ 			# tracker names 
    	--save_dir \                                  # save dir

You can draw the corresponding bounding box into the image and save it according to the result file (txt format) run by the tracker.

Related tags

Overview

SOTDrawRect

Install

Update toolkit(optional)

Download Dataset

Usage

Draw rectangular boxes

Draw a bounding box for a video sequence

Owner

Huiyiqianli

GAN-generated image detection based on CNNs

People log into different sites every day to get information and browse through these sites one by one

B-cos Networks: Attention is All we Need for Interpretability

Pre-trained Deep Learning models and demos (high quality and extremely fast)

Source Code for AAAI 2022 paper "Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching"

PyTorch Implementation of Vector Quantized Variational AutoEncoders.

Speech Recognition using DeepSpeech2.

Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)

Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms

PyTorch implementations of neural network models for keyword spotting

MapReader: A computer vision pipeline for the semantic exploration of maps at scale

An implementation of the WHATWG URL Standard in JavaScript

PyTorch-Geometric Implementation of MarkovGNN: Graph Neural Networks on Markov Diffusion

On Generating Extended Summaries of Long Documents

Code for the paper BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

A general python framework for visual object tracking and video object segmentation, based on PyTorch

From this paper "SESNet: A Semantically Enhanced Siamese Network for Remote Sensing Change Detection"

This repository provides the code for MedViLL(Medical Vision Language Learner).

Framework for evaluating ANNS algorithms on billion scale datasets.