Human Density Estimation by Exploiting Deep Spatial Contextual Information

• Published in: 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) pp. 1 - 5
• Main Authors: Phan, Chau-Phuc-Thinh, Hoang, Anh, Phan, Doan-Phuc, Dao, Huu-Hung, Huynh, Van-Nam
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-12-2019
• Subjects: Convolutional Neural Network (CNN); Crowd Density Estimate; Long Short-Term Memory (LSTM)
• ISSN: 2151-2205
• DOI: 10.1109/IVCNZ48456.2019.8961033

We propose in this paper a deep learning method for human density estimation, targeted to sparse density scenarios. We divide the image into a grid of cells and realize that a person does not span in one cell but several cells. To estimate the human density appeared in one cell, the information of surrounding cells plays a crucial role, so-called spatial contextual information. The key insight of our approach is the employment of Convolutional Neural Networks (CNN) to extract image features and Long Short-Term Memory (LSTM) to exploit the spatial contextual information. The shared-weight mechanism of CNN models generalizes the learned features of humanity in all corners of the images. The feedback mechanism of LSTM captures spatial contextual information of neighboring cells in a sub-grid of 3x3 cells to estimate the human density of the central cell. We demonstrate the validity of the proposed method on Mall dataset with a competitive performance in comparison with state-of-the-art methods, validated on the same dataset.