LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance

TL;DR

This paper introduces LCDnet, a lightweight crowd density estimation model designed for real-time video surveillance on resource-limited devices, utilizing curriculum learning to balance accuracy and efficiency.

Contribution

The paper presents a novel lightweight CNN model, LCDnet, combined with an improved training method using curriculum learning for efficient crowd density estimation.

Findings

LCDnet achieves good accuracy on benchmark datasets.

LCDnet significantly reduces inference time and memory usage.

The model is suitable for deployment on edge devices with limited resources.

Abstract

Automatic crowd counting using density estimation has gained significant attention in computer vision research. As a result, a large number of crowd counting and density estimation models using convolution neural networks (CNN) have been published in the last few years. These models have achieved good accuracy over benchmark datasets. However, attempts to improve the accuracy often lead to higher complexity in these models. In real-time video surveillance applications using drones with limited computing resources, deep models incur intolerable higher inference delay. In this paper, we propose (i) a Lightweight Crowd Density estimation model (LCDnet) for real-time video surveillance, and (ii) an improved training method using curriculum learning (CL). LCDnet is trained using CL and evaluated over two benchmark datasets i.e., DroneRGBT and CARPK. Results are compared with existing crowd models. Our evaluation shows that the LCDnet achieves a reasonably good accuracy while significantly reducing the inference time and memory requirement and thus can be deployed over edge devices with very limited computing resources.