From Handcrafted to Deep Features for Pedestrian Detection: A Survey

TL;DR

This survey comprehensively reviews recent advances in pedestrian detection, covering handcrafted and deep features, multi-spectral approaches, datasets, and future research directions in computer vision.

Contribution

It provides an extensive overview of both handcrafted and deep feature-based pedestrian detection methods, including statistical analysis and future research insights.

Findings

Handcrafted features with high shape and space freedom perform better.

Deep learning approaches include pure CNN and hybrid methods.

Multi-spectral detection enhances robustness under illumination changes.

Abstract

Pedestrian detection is an important but challenging problem in computer vision, especially in human-centric tasks. Over the past decade, significant improvement has been witnessed with the help of handcrafted features and deep features. Here we present a comprehensive survey on recent advances in pedestrian detection. First, we provide a detailed review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches. For handcrafted features based methods, we present an extensive review of approaches and find that handcrafted features with large freedom degrees in shape and space have better performance. In the case of deep features based approaches, we split them into pure CNN based methods and those employing both handcrafted and CNN based features. We give the statistical analysis and tendency of these methods, where feature enhanced, part-aware, and post-processing methods have attracted main attention. In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance. Furthermore, we introduce some related datasets and evaluation metrics, and compare some representative methods. We conclude this survey by emphasizing open problems that need to be addressed and highlighting various future directions. Researchers can track an up-to-date list at https://github.com/JialeCao001/PedSurvey.