YOLOpeds: Efficient Real-Time Single-Shot Pedestrian Detection for Smart Camera Applications

TL;DR

YOLOpeds is a novel, efficient deep learning model for real-time pedestrian detection on resource-constrained smart cameras, achieving high accuracy and speed suitable for various surveillance and autonomous applications.

Contribution

This work introduces YOLOpeds, a lightweight neural network architecture with multi-scale features and an anchor-less detection approach for improved efficiency and accuracy.

Findings

Real-time detection at over 30 fps

Detection accuracy of approximately 86% on PETS2009 dataset

Outperforms existing deep learning pedestrian detectors

Abstract

Deep Learning-based object detectors can enhance the capabilities of smart camera systems in a wide spectrum of machine vision applications including video surveillance, autonomous driving, robots and drones, smart factory, and health monitoring. Pedestrian detection plays a key role in all these applications and deep learning can be used to construct accurate state-of-the-art detectors. However, such complex paradigms do not scale easily and are not traditionally implemented in resource-constrained smart cameras for on-device processing which offers significant advantages in situations when real-time monitoring and robustness are vital. Efficient neural networks can not only enable mobile applications and on-device experiences but can also be a key enabler of privacy and security allowing a user to gain the benefits of neural networks without needing to send their data to the server to be evaluated. This work addresses the challenge of achieving a good trade-off between accuracy and speed for efficient deployment of deep-learning-based pedestrian detection in smart camera applications. A computationally efficient architecture is introduced based on separable convolutions and proposes integrating dense connections across layers and multi-scale feature fusion to improve representational capacity while decreasing the number of parameters and operations. In particular, the contributions of this work are the following: 1) An efficient backbone combining multi-scale feature operations, 2) a more elaborate loss function for improved localization, 3) an anchor-less approach for detection, The proposed approach called YOLOpeds is evaluated using the PETS2009 surveillance dataset on 320x320 images. Overall, YOLOpeds provides real-time sustained operation of over 30 frames per second with detection rates in the range of 86% outperforming existing deep learning models.