An improved one-stage pedestrian detection method based on multi-scale attention feature extraction

• DOI: 10.1007/s11554-021-01074-2
• Publication Date: 2021-01-22T18:40:40Z
• Authors: Jun Ma; Honglin Wan; Junxia Wang; Hao Xia; Chengjie Bai
• Keywords: Pedestrian detection; Minimum bounding box; Convolution (computer science); Feature (linguistics); Bounding overwatch; Scale space

In recent years, the performance of the convolutional neural network-based pedestrian detection method has improved significantly. However, an imbalance remains between detection accuracy and speed. In this paper, we employ a one-stage object detection framework and propose a pedestrian detection method based on the multi-scale attention mechanism of a convolutional neural network to improve the imbalance between accuracy and speed. First, a multi-scale convolution module is designed to extract corresponding features at different scales. Second, using the attention module, association information between features is mined from space and channel perspectives to strengthen the original features. Then, the enhanced features are passed through a classification and regression module to perform object positioning and bounding box regression. Finally, to learn more pedestrian location information, we improve the loss function to realise better network training. The proposed method achieved considerable results on the challenging CityPersons and Caltech pedestrian detection datasets.