Despite pedestrian detectors having made significant progress by introducing convolutional neural networks, their performance still suffers degradation, especially in occlusion scenes with more false positives (FPs) and false negatives (FNs). To alleviate the problem, we propose a novel Sequential Attention-based Distinct Part Modeling (SA-DPM) for balanced pedestrian detection. It takes one step further in constructing more robust representation that supports detection with fewer FNs and FPs. Specifically, the Sequential Attention serves as one internal perception process that captures several distinct part areas step by step from each pedestrian proposal (full-body). Different from the previous either-or feature selection, the following Joint Learning attempts to seek a reasonable trade-off between part and full-body features, and combines both features for more accurate classification and regression. Evaluation on the widely used pedestrian datasets including Caltech and Citypersons shows that the proposed SA-DPM achieves promising performance for both non-occluded and occluded pedestrian detection tasks, especially on Caltech Heavy Occlusion set, which yields a new state-of-the-art miss rate by 30.18% and outperforms the second best detector by 6.32%.
Sequential Attention-Based Distinct Part Modeling for Balanced Pedestrian Detection
IEEE Transactions on Intelligent Transportation Systems ; 23 , 9 ; 15644-15654
2022-09-01
4075693 byte
Article (Journal)
Electronic Resource
English
SEQUENTIAL PEDESTRIAN TRAJECTORY PREDICTION USING STEP ATTENTION FOR COLLISION AVOIDANCE
European Patent Office | 2023
|Two-stage part-based pedestrian detection
IEEE | 2012
|Part based pedestrian detection based on Logic inference
IEEE | 2013
|