Smart Surveillance as an Edge Network Service: from Harr-Cascade, SVM to a Lightweight CNN

TL;DR

This paper evaluates traditional and machine learning-based human detection methods on edge devices, introducing a lightweight CNN that balances accuracy and resource efficiency for real-time surveillance.

Contribution

It proposes a novel lightweight CNN leveraging depthwise separable convolutions for human detection at the edge, improving efficiency over traditional methods.

Findings

Lightweight CNN achieves real-time human detection on edge devices.

Traditional methods like Harr-Cascade and SVM are feasible but less efficient.

The proposed L-CNN balances accuracy and computational cost effectively.

Abstract

Edge computing efficiently extends the realm of information technology beyond the boundary defined by cloud computing paradigm. Performing computation near the source and destination, edge computing is promising to address the challenges in many delay-sensitive applications, like real-time human surveillance. Leveraging the ubiquitously connected cameras and smart mobile devices, it enables video analytics at the edge. In recent years, many smart video surveillance approaches are proposed for object detection and tracking by using Artificial Intelligence (AI) and Machine Learning (ML) algorithms. This work explores the feasibility of two popular human-objects detection schemes, Harr-Cascade and HOG feature extraction and SVM classifier, at the edge and introduces a lightweight Convolutional Neural Network (L-CNN) leveraging the depthwise separable convolution for less computation, for human detection. Single Board computers (SBC) are used as edge devices for tests and algorithms are validated using real-world campus surveillance video streams and open data sets. The experimental results are promising that the final algorithm is able to track humans with a decent accuracy at a resource consumption affordable by edge devices in real-time manner.