Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
arXiv:1807.01438
Abstract
A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias. Motivated by this, we propose a novel method integrated with somatic topological line localization (TLL) and temporal feature aggregation for detecting multi-scale pedestrians, which works particularly well with small-scale pedestrians that are relatively far from the camera. Moreover, a post-processing scheme based on Markov Random Field (MRF) is introduced to eliminate ambiguities in occlusion cases. Applying with these methodologies comprehensively, we achieve best detection performance on Caltech benchmark and improve performance of small-scale objects significantly (miss rate decreases from 74.53% to 60.79%). Beyond this, we also achieve competitive performance on CityPersons dataset and show the existence of annotation bias in KITTI dataset.
Accepted by ECCV18
References in corpus (8)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
- CityPersons: A Diverse Dataset for Pedestrian Detection
- Mobile Video Object Detection with Temporally-Aware Feature Maps
- Repulsion Loss: Detecting Pedestrians in a Crowd
Cited by in corpus (9)
- The Adaptability and Challenges of Autonomous Vehicles to Pedestrians in Urban China
- SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection
- Hybrid Channel Based Pedestrian Detection
- Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
- Semantic Head Enhanced Pedestrian Detection in a Crowd
- Pedestrian Detection with Autoregressive Network Phases
- Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection
- Pedestrian Detection by Exemplar-Guided Contrastive Learning
- Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor