Implementation of our IEEE AVSS 2018 paper "Person Retrieval in Surveillance Video using Height, Color, and Gender". If you find this code useful in your research, please consider citing:
title={Person retrieval in surveillance video using height, color and gender},
author={Galiyawala, Hiren and Shah, Kenil and Gajjar, Vandit and Raval, Mehul S},
booktitle={2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)},
pages={1--6},
year={2018},
organization={IEEE}
}
This code was initially tested on an Ubuntu 16.04 system using Keras 2.0.8 with Tensorflow 1.12 backend.
The paper proposes a deep learning-based linear filtering approach for person retrieval using height, cloth color, and gender.
- Clone this repository.
git clone https://github.com/Vanditg/Person-Retrieval-AVSS-2018.git
-
In the repository, execute
pip install -r requirements.txt
to install all the necessary libraries. -
Three deep learning models are used inorder to filter out the desired person.
- Mask_RCNN:- Used to determine the coordinates of the person and fetch the pixelwise segmentation
- gender_model:- Used to determine gender of the person
- color_model:- Used to determine torso color of the person
-
Download the pretrained weights.
- Mask_RCNN pretrained weights and save it in root directory
- gender_model pretrained weights and save it in /modalities/gender/
- color_model pretrained weight and save it in /modalities/torso_color/
To use run
python Video_demo_person_identification.py
This will read the input video file and based on the queries produces the Bounding-Box and Person Coordinates text file under the output folder.
Many thanks to Matterport for the Mask R-CNN code.
New Scientist, The Next Web, Digital Trends, Make Tech Easier, Tech The Lead, Outerplaces, IMPORT AI by Jack Clark, Business Recorder, Inshorts, and RT