期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 30, 期 -, 页码 2876-2887出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3055632
关键词
Detectors; Training; Annotations; Object detection; Decoding; Feature extraction; Location awareness; Convolutional neural network (CNN); object detection; crowd counting; self-training; weak supervision
资金
- Hong Kong Research Grants Council [CityU 11219019, CityU 11202320]
The article introduces a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations to estimate the center points and sizes of crowded objects. The method significantly improves object detection and counting capabilities and achieves outstanding results on multiple benchmark datasets.
In this article, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we utilize the available point annotations to supervise the estimation of the center points of objects directly. Based on a locally-uniform distribution assumption, we initialize pseudo object sizes from the point-level supervisory information, which are then leveraged to guide the regression of object sizes via a crowdedness-aware loss. Meanwhile, we propose a confidence and order-aware refinement scheme to continuously refine the initial pseudo object sizes such that the ability of the detector is increasingly boosted to detect and count objects in crowds simultaneously. Moreover, to address extremely crowded scenes, we propose an effective decoding method to improve the detector's representation ability. Experimental results on the WiderFace benchmark show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks, i.e., our method improves the average precision by more than 10% and reduces the counting error by 31.2%. Besides, our method obtains the best results on the crowd counting and localization datasets (i.e., ShanghaiTech and NWPU-Crowd) and vehicle counting datasets (i.e., CARPK and PUCPR+) compared with state-of-the-art counting-by-detection methods. The code will be publicly available at https://github.com/WangyiNTU/Point-supervised-crowd-detection.
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