Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
This work addresses a critical issue in pedestrian detection for applications like autonomous driving and surveillance, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of detecting small-scale pedestrians in images and videos, which suffer from low contrast and motion blur, by proposing a novel method integrating somatic topological line localization and temporal feature aggregation, achieving a significant reduction in miss rate from 74.53% to 60.79% on the Caltech benchmark.
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.