Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention
share
Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras. Inspired by the success of attention modules for deep neural networks, we first propose a Homography Attention Module (HAM) which is shown to boost the performance of existing end-to-end multiview detection approaches by utilizing a novel channel gate and spatial gate. Additionally, we propose Booster-SHOT, an end-to-end convolutional approach to multiview pedestrian detection incorporating our proposed HAM as well as elements from previous approaches such as view-coherent augmentation or stacked homography transformations. Booster-SHOT achieves 92.9 and 94.2 state-of-the-art by 1.4 state-of-the-art performance overall for standard evaluation metrics used in multi-view pedestrian detection.
READ FULL TEXT