stvir/pysot

★ 4,600PythonAudience · researcherComplexity · 4/5LicenseSetup · hard

Mindmap

mindmap
  root((PySOT))
    What It Does
      Single object tracking
      Pixel segmentation SiamMask
      Bounding box output
    Algorithms
      SiamFC
      SiamRPN++
      DaSiamRPN
      SiamMask
    Tech Stack
      Python
      PyTorch
      ResNet backbone
    Benchmarks
      OTB2015
      VOT2018
      LaSOT
    Use Cases
      Webcam demos
      Benchmark evaluation

mindmap root((PySOT)) What It Does Single object tracking Pixel segmentation SiamMask Bounding box output Algorithms SiamFC SiamRPN++ DaSiamRPN SiamMask Tech Stack Python PyTorch ResNet backbone Benchmarks OTB2015 VOT2018 LaSOT Use Cases Webcam demos Benchmark evaluation

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run a live webcam demo to track a chosen object in real time using a pretrained model.

USE CASE 2

Evaluate a Siamese tracker on standard benchmarks like OTB2015 or VOT2018 using built-in test scripts.

USE CASE 3

Use SiamMask to produce pixel-level segmentation masks around a tracked object, not just a bounding box.

USE CASE 4

Download pretrained models from the model zoo and test them on your own video files.

Tech stack

PythonPyTorchResNetMobileNetV2

Getting it running

Difficulty · hard Time to first run · 1h+

Requires a CUDA-compatible GPU, PyTorch with the matching CUDA version, and manual download of pretrained models from the model zoo.

Free to use for any purpose, including commercial, as long as you keep the copyright and license notices.

In plain English

PySOT is a Python toolkit from SenseTime's video intelligence research team for tracking a single object across video frames. Given a video and a starting bounding box around an object, a tracker follows that object through subsequent frames even when it moves, changes appearance, or becomes partially obscured. This is a research platform, meaning it is designed for academics and engineers experimenting with new tracking algorithms rather than as a finished product. The toolkit implements several tracking algorithms from published research papers, all belonging to a family of approaches called Siamese networks. These methods work by learning to compare two image patches: a small crop of the target object from the first frame, and candidate regions from later frames. The algorithms included are SiamFC, SiamRPN, DaSiamRPN, SiamRPN++, and SiamMask. SiamMask is notable because it also produces a pixel-level segmentation mask of the tracked object, not just a bounding box. The system is built on top of PyTorch and supports several neural network backbone architectures including variants of ResNet and MobileNetV2. Pretrained models for the included algorithms are available to download from a model zoo linked in the repository. The toolkit includes command-line scripts for running a webcam demo, testing a tracker against a downloaded benchmark dataset, and evaluating the results. It supports evaluation on several standard tracking benchmarks including OTB2015, VOT2016, VOT2018, LaSOT, and UAV123. Training instructions are in a separate file. The codebase has supported multiple published papers from SenseTime, including work presented at CVPR 2018, CVPR 2019, and ECCV 2018. It is released under the Apache 2.0 license.

Copy-paste prompts

Prompt 1

I want to track a moving car in a video using PySOT's SiamRPN++ model. Show me the setup steps and how to run inference on a video file.

Prompt 2

Help me evaluate a SiamMask tracker on the VOT2018 benchmark using PySOT, what commands do I run?

Prompt 3

I have a bounding box for an object in frame 1 of a video. How do I use DaSiamRPN in PySOT to track it through subsequent frames?

Prompt 4

Show me how to download and use a pretrained SiamRPN++ model from PySOT's model zoo for tracking objects in my own footage.

Open on GitHub → Explain another repo

← stvir on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.