期刊
PATTERN RECOGNITION LETTERS
卷 131, 期 -, 页码 91-97出版社
ELSEVIER
DOI: 10.1016/j.patrec.2019.12.010
关键词
Pedestrian detection; Occlusion; Convolutional neural networks; Attention networks; Recurrent neural networks
资金
- National Natural Science Foundation of China (NSFC) [61572107, 61572112]
- National Key Research and Development Program of China [2017YFC1703905]
- Applied Basic Research Program of Science and Technology Department in Sichuan Province [2019YJ0185]
Occluded pedestrian detection has been a research difficulty in computer vision for a long time. The conventional approach to solve this problem is to learn partial detectors, which can be properly integrated for occlusion handling. However, the efficiency of this type of methods is limited in practical applications since the partial detectors can not cover all occlusion patterns. In this paper, an attention guided neural network model (AGNN) is proposed for the occlusion handling of pedestrian detections, which is inspired by the approaches of sentiment classification. Firstly, a fixed-size window slides on a still image without overlapping to generate a set of sub-images. Secondly, a convolutional neural network is employed to extract the high-level features from resulting sub-images. Then, the attention network performs local feature weighting, from which the features representing the body parts of pedestrians are selected. Finally, the feature sequences are classified by recurrent neural network in proper order based on the weighted results. In addition, we explore different mechanisms of attention guidance on the detector for the detections. Compared with the state-of-the-art methods on two standard pedestrian datasets, experimental results demonstrate the comparable performance of our approach in terms of miss rates. (C) 2019 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据