Giter Club home page Giter Club logo

sort-cpp's Introduction

Introduction

C++ implementation of SORT: Simple, online, and real-time tracking of multiple objects in a video sequence.

Kuhn-Munkres (Hungarian) Algorithm in C++ is forked from: https://github.com/saebyn/munkres-cpp

Dependencies

  • Ubuntu 16.04
  • Docker 18.09.4
  • OpenCV 3.4.2
  • Boost 1.58.0

All of the 3rd party libraries are included in the provided docker image

Build Docker Image

  1. Open Dockerfile, change line #19 ARG USERNAME to your host user name (echo $USER)
  2. Open a terminal and run:
    $ cd /path/to/sort-cpp
    $ docker build -t sort .
    $ ./docker_run.sh

Demo:

Screenshot-1

To run the tracker with the provided detections and visualize the results:

  1. Download the 2D MOT 2015 benchmark dataset
  2. Create a symbolic link to the dataset
    $ ln -s /path/to/MOT2015_challenge/data/2DMOT2015 /path/to/sort-cpp/mot_benchmark
  3. Run the demo
    $ cd /path/to/sort-cpp
    $ mkdir build && cd "$_"
    $ cmake .. && make
    $ cd /path/to/sort-cpp/bin
    # Without display
    $ ./sort-cpp
    # With display
    $ ./sort-cpp -d

Evaluate Metrics

Using the Python implementation of metrics for benchmarking multiple object trackers (MOT) to evaluate metrics.

Dataset Structure

Layout for ground truth data
    <GT_ROOT>/<SEQUENCE_1>/gt/gt.txt
    <GT_ROOT>/<SEQUENCE_2>/gt/gt.txt
    ...

Layout for test data
    <TEST_ROOT>/<SEQUENCE_1>.txt
    <TEST_ROOT>/<SEQUENCE_2>.txt
    ...

Example:
mot_benchmark
├── test
│   ├── ADL-Rundle-6.txt
│   └── ADL-Rundle-8.txt
└── train
    ├── ADL-Rundle-6
    │   └── gt
    │       └── gt.txt
    └── ADL-Rundle-8
        └── gt
            └── gt.txt


Sequences of ground truth and test will be matched according to the `<SEQUENCE_X>`
string.

Example

# Optional for virtualenv
$ source ~/env/bin/activate
$ pip install motmetrics
# Usage
$ python -m motmetrics.apps.eval_motchallenge --help
# Format: python -m motmetrics.apps.eval_motchallenge groundtruths tests
$ python -m motmetrics.apps.eval_motchallenge mot_benchmark/train output/

Result

Screenshot-1

FPS is around 1900 with Debug build.

References

  1. https://github.com/abewley/sort
  2. https://github.com/mcximing/sort-cpp
  3. https://github.com/saebyn/munkres-cpp

sort-cpp's People

Contributors

yasenh avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.