PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection

Abstract

Detecting pedestrians, especially under heavy occlusions, is a challenging computer vision problem with numerous real-world applications. This paper introduces a novel approach, termed as PSC-Net, for occluded pedestrian detection. The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a Graph Convolutional Network (GCN). Both inter and intra-part co-occurrence information contribute towards improving the feature representation for handling varying level of occlusions, ranging from partial to severe occlusions. Our PSC-Net exploits the topological structure of pedestrian and does not require part-based annotations or additional visible bounding-box (VBB) information to learn part spatial co-occurrence. Comprehensive experiments are performed on two challenging datasets: CityPersons and Caltech datasets. The proposed PSC-Net achieves state-of-the-art detection performance on both. On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4.0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision. Further, PSC-Net improves the state-of-the-art from 37.9 to 34.8 in terms of log-average miss rate on Caltech (\textbf{HO}) test set.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Two-Stream Convolutional Networks for Action Recognition in Videos
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Mask-Guided Attention Network for Occluded Pedestrian Detection
• Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
• 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
• Adaptive NMS: Refining Pedestrian Detection in a Crowd
• Object Counting and Instance Segmentation with Image-level Supervision

Cited by in corpus (1)

• From Handcrafted to Deep Features for Pedestrian Detection: A Survey