FCHD-Fully-Convolutional-Head-Detector

Code for FCHD - A fast and accurate head detector

This is the code for FCHD - A Fast and accurate head detector. See the paper for details and video for demo.

Dependencies

• The code is tested on Ubuntu 16.04.

• install PyTorch >=0.4 with GPU (code are GPU-only), refer to official website

• install cupy, you can install via pip install cupy-cuda80 or(cupy-cuda90,cupy-cuda91, etc).

• install visdom for visualization, refer to their github page

Installation

1. Install Pytorch

2. Clone this repository

git clone https://github.com/aditya-vora/FCHD-Fully-Convolutional-Head-Detector

3. Build cython code for speed:

cd src/nms/
python build.py build_ext --inplace

Training

1. Download the caffe pre-trained VGG16 from the following link. Store this pre-trained model in data/pretrained_model folder. The filename is vgg16_caffe.pth.

2. Download the BRAINWASH dataset from the official website. Unzip it and store the dataset in the data/ folder.

3. Make appropriate settings in src/config.py file regarding the updated paths.

4. Start visdom server for visualization:

python -m visdom.server

5. Run the following command to train the model: python train.py .

Demo

1. Download the best performing model from the following link. The filename is head_detector_final.

2. Store the head detection model in checkpoints/ folder.

3. Run the following python command from the root folder.

python head_detection_demo.py --img_path  --model_path 

Results

Runtime

• Runs at 5fps on NVidia Quadro M1000M GPU with 512 CUDA cores.

Acknowledgement

This work builds on many of the excellent works:

• Simple faster rcnn pytorch implementation by Yun Chen.
• py-faster-rcnn by Ross Girshick.

Reference

[1] Stewart, Russell, Mykhaylo Andriluka, and Andrew Y. Ng. "End-to-end people detection in crowded scenes." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.