https://github.com/myfavouritekk/vdetlib

Video detection library
https://github.com/myfavouritekk/vdetlib

computer-vision deep-learning detection object-detection python-library video video-object-detection

Last synced: about 2 months ago
JSON representation

Video detection library

• Host: GitHub
• URL: https://github.com/myfavouritekk/vdetlib
• Owner: myfavouritekk
• Created: 2015-09-26T15:07:46.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2017-01-23T14:47:16.000Z (almost 8 years ago)
• Last Synced: 2024-08-01T20:37:09.432Z (5 months ago)
• Topics: computer-vision, deep-learning, detection, object-detection, python-library, video, video-object-detection
• Language: Python
• Size: 5.51 MB
• Stars: 183
• Watchers: 16
• Forks: 76
• Open Issues: 3
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

• awesome-semantic-understanding-for-aerial-scene - vdetlib

README

        
# vdetlib - Python library for object detection in videos

## Introduction

The `vdetlib` python library serves to detection objects in videos. It was originally developed for the [ImageNet VID](http://image-net.org/challenges/LSVRC/2015/index#vid) challenge introduced in [ILSVRC2015](http://image-net.org/challenges/LSVRC/2015/). It contains components such as **region proposal**, **still-image object detection**, **generic object tracking**, **spatial max-pooling** and **temporal convolution**.

The [T-CNN](https://github.com/myfavouritekk/T-CNN) framework contains many tools that utilizes `vdetlib`. Please checkout that repository if you are interested.

## Citing vdetlib

If you find vdetlib useful in your research and related project, please consider citing the following work accepted in CVPR 2016.

```latex

@inproceedings{kang2016object,

  Title = {Object Detection from Video Tubelets with Convolutional Neural Networks},

  Author = {Kang, Kai and Ouyang, Wanli and Li, Hongsheng and Wang, Xiaogang},

  Booktitle = {CVPR},

  Year = {2016}

}

```

## License

This project is released under the MIT License.

## Installations

### Prerequisites

1. [caffe](https://github.com/BVLC/caffe) with `Python layer` and `pycaffe`

2. [FCN tracker](https://github.com/scott89/FCNT)

3. `Matlab` with python [engine](http://www.mathworks.com/help/matlab/matlab-engine-for-python.html?refresh=true)

### Instructions

1. Clone the repository

    ```bash

        $ git clone https://github.com/myfavouritekk/vdetlib.git

    ```

2. Compilation

    ```bash

        $ cd vdetlib

        $ make

    ```

    

## Protocols

There are some basic protocol types for using this library. All of them are defined as python dictionaries and are saved as `JSON` files. The definitions are written in the [`protocol.py`](utils/protocol.py).

## To-do list

- [ ] detailed documentation

- [ ] demo script