From Handcrafted to Deep Features for Pedestrian Detection: A Survey

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.

arXiv commentIEEE TPAMI, Projects: https://github.com/JialeCao001/PedSurvey

References in corpus (34)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SSD: Single Shot MultiBox Detector
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Generative Adversarial Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Squeeze-and-Excitation Networks
• What makes for effective detection proposals?
• CrowdHuman: A Benchmark for Detecting Human in a Crowd
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Learning Multilayer Channel Features for Pedestrian Detection
• Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
• Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
• TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
• Domain Adaptation for Object Detection via Style Consistency
• Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry
• Learning Sampling Distributions for Efficient Object Detection
• DETR for Crowd Pedestrian Detection
• Hybrid Channel Based Pedestrian Detection
• A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
• Exploring Human Vision Driven Features for Pedestrian Detection
• Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
• Person Recognition in Personal Photo Collections
• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
• Monocular Pedestrian Orientation Estimation Based on Deep 2D-3D Feedforward
• CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection
• Double Anchor R-CNN for Human Detection in a Crowd
• SAM-RCNN: Scale-Aware Multi-Resolution Multi-Channel Pedestrian Detection
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
• Attribute-aware Pedestrian Detection in a Crowd
• Semantic Head Enhanced Pedestrian Detection in a Crowd
• Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
• Triply Supervised Decoder Networks for Joint Detection and Segmentation

Cited by in corpus (6)

• Towards Large-Scale Small Object Detection: Survey and Benchmarks
• Oriented object detection in optical remote sensing images using deep learning: a survey
• Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
• Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey
• The Impact of Partial Occlusion on Pedestrian Detectability
• Can Human Sex Be Learned Using Only 2D Body Keypoint Estimations?