Scale-Aware Fast R-CNN for Pedestrian Detection

Jianan Li, Xiaodan Liang, Shengmei Shen, Tingfa Xu*, Jiashi Feng, Shuicheng Yan

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

650 引用 (Scopus)
Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 654
    • Patent Family Citations: 2
  • Captures
    • Readers: 457
see details

摘要

In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges. Outputs from all of the subnetworks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech, and obtains competitive results on INRIA, ETH, and KITTI.

源语言英语
页(从-至)985-996
页数12
期刊IEEE Transactions on Multimedia
20
4
DOI
出版状态已出版 - 4月 2018

指纹

探究 'Scale-Aware Fast R-CNN for Pedestrian Detection' 的科研主题。它们共同构成独一无二的指纹。

引用此

Li, J., Liang, X., Shen, S., Xu, T., Feng, J., & Yan, S. (2018). Scale-Aware Fast R-CNN for Pedestrian Detection. IEEE Transactions on Multimedia, 20(4), 985-996. https://doi.org/10.1109/TMM.2017.2759508