A general python framework for training and running visual object trackers, based on PyTorch.
News: Code released for DiMP!!!
Code now released for our new tracker DiMP, accepted as an Oral at ICCV 2019.
This release also includes many new features, including:
- Visualization with Visdom
- VOT integration
- Many new network modules
- Multi GPU training
- PyTorch v1.2 support
DiMP and ATOM Trackers
Official implementation of the DiMP (ICCV 2019), and ATOM (CVPR 2019) trackers, including complete training code and trained models.
Libraries for implementing and evaluating visual trackers. It includes
- All common tracking datasets.
- General building blocks, including deep networks, optimization, feature extraction and utilities for correlation filter tracking.
LTR (Learning Tracking Representations) is a general framework for training your visual tracking networks. It is equipped with
- All common training datasets for visual tracking.
- Functions for data sampling, processing etc.
- Network modules for visual tracking.
- And much more...
The toolkit contains the implementation of the following trackers.
Official implementation of the DiMP tracker. DiMP is an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction. It is based on a target model prediction network, which is derived from a discriminative learning loss by applying an iterative optimization procedure. The model prediction network employs a steepest descent based methodology that computes an optimal step length in each iteration to provide fast convergence. The model predictor also includes an initializer network that efficiently provides an initial estimate of the model weights.
Official implementation of the ATOM tracker. ATOM is based on (i) a target estimation module that is trained offline, and (ii) target classification module that is trained online. The target estimation module is trained to predict the intersection-over-union (IoU) overlap between the target and a bounding box estimate. The target classification module is learned online using dedicated optimization techniques to discriminate between the target object and background.
An unofficial implementation of the ECO tracker. It is implemented based on an extensive and general library for complex operations and Fourier tools. The implementation differs from the version used in the original paper in a few important aspects.
- This implementation uses features from vgg-m layer 1 and resnet18 residual block 3.
- As in our later UPDT tracker, seperate filters are trained for shallow and deep features, and extensive data augmentation is employed in the first frame.
- The GMM memory module is not implemented, instead the raw projected samples are stored.
Please refer to the official implementation of ECO if you are looking to reproduce the results in the ECO paper or download the raw results.
The tracker models trained using PyTracking, along with their results on standard tracking benchmarks are provided in the model zoo.
Clone the GIT repository.
git clone https://github.com/visionml/pytracking.git
Clone the submodules.
In the repository directory, run the commands:
git submodule update --init
Run the installation script to install all the dependencies. You need to provide the conda install path (e.g. ~/anaconda3) and the name for the created conda environment (here
bash install.sh conda_install_path pytracking
This script will also download the default networks and set-up the environment.
Note: The install script has been tested on an Ubuntu 18.04 system. In case of issues, check the detailed installation instructions.
Let's test it!
Activate the conda environment and run the script pytracking/run_webcam.py to run ATOM using the webcam input.
conda activate pytracking cd pytracking python run_webcam.py dimp dimp50