Special Offer: Get 50% off your first 2 months when you do one of the following
Personalized offer codes will be given in each session

(AIMS 2020) OSAF_e: One-Stage Anchor Free Object Detection Method Considering Effective Area

About This Webinar

Abstract: The task of object detection is to identify the bounding box of the object and its corresponding category in images. In this paper, we propose a new one-stage anchor free object detection algorithm OSAF_e, with the consideration of effective mapping area. A feature extraction network is used to obtain high level feature, and the true bounding box of the object in the original image is mapped to the grid of feature map, in order to perform category prediction and bounding box regression. The proposed algorithm is evaluated with the Pascal Voc dataset, and the experiments indicate that it has a better result.

Authors: Z. Yong and Lizong Zhang (University of Electronic Science and Technology of China, China); ZhiHong Rao (China Electronic Technology Cyber Security Co., Ltd & Cyberspace Security Key Laboratory of Sichuan Province, China); Guiduo Duan and Chunyu Wang (University of Electronic Science and Technology of China, China)

Email: 201922080934@std.uestc.edu.cn, l.zhang@uestc.edu.cn, 13608184980@139.com, duanguiduo@163.com, wcy633985@163.com

Who can view: Everyone
Webinar Price: Free
Featured Presenters
Hosted By
Services Society webinar platform hosts (AIMS 2020) OSAF_e: One-Stage Anchor Free Object Detection Method Considering Effective Area
Services Society's Channel