QQ客服 官方微博 反馈留言

	Efficient object detection based on selective attention
	Yu, Huapeng1,2,3; Chang, Yongxin1,2,3; Lu, Pei1,3; Xu, Zhiyong1; Fu, Chengyu1; Wang, Yafei2
刊名	Computers and Electrical Engineering
	2014
卷号	40期号:3页码:907-919
ISSN号	00457906
通讯作者	Yu, H. (yuhuapeng@uestc.edu.cn)
中文摘要	In this paper, we make use of biologically inspired selective attention to improve the efficiency and performance of object detection under clutter. At first, we propose a novel bottom-up attention model. We argue that heuristic feature selection based on bottom-up attention can stably select out invariant and discriminative features. With these selected features, performance of object detection can be improved apparently and stably. Then we propose a novel concept of saccade map based on bottom-up attention to simulate the saccade (eye movements) in vision. Sliding within saccade map to detect object can significantly reduce computational complexity and apparently improve performance because of the effective filtering for distracting information. With these ideas, we present a general framework for object detection through integrating bottom-up attention. Through evaluating on UIUC cars and Weizmann-Shotton horses we show state-of-the-art performance of our object detection model. © 2013 Elsevier Ltd. All rights reserved.
英文摘要	In this paper, we make use of biologically inspired selective attention to improve the efficiency and performance of object detection under clutter. At first, we propose a novel bottom-up attention model. We argue that heuristic feature selection based on bottom-up attention can stably select out invariant and discriminative features. With these selected features, performance of object detection can be improved apparently and stably. Then we propose a novel concept of saccade map based on bottom-up attention to simulate the saccade (eye movements) in vision. Sliding within saccade map to detect object can significantly reduce computational complexity and apparently improve performance because of the effective filtering for distracting information. With these ideas, we present a general framework for object detection through integrating bottom-up attention. Through evaluating on UIUC cars and Weizmann-Shotton horses we show state-of-the-art performance of our object detection model. © 2013 Elsevier Ltd. All rights reserved.
学科主题	Information filtering - Object recognition
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000336187000014
内容类型	期刊论文
源URL	[http://ir.ioe.ac.cn/handle/181551/5073]
专题	光电技术研究所_光电探测与信号处理研究室（五室）
作者单位	1.5th Lab, Institute of Optics and Electronics, Chinese Academy of Sciences, P.O. Box 350, Shuangliu, Chengdu 610209, Sichuan Province, China 2.School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu 610054, China 3.Graduate University of Chinese Academy of Sciences, Beijing 100039, China
推荐引用方式 GB/T 7714	Yu, Huapeng,Chang, Yongxin,Lu, Pei,et al. Efficient object detection based on selective attention[J]. Computers and Electrical Engineering,2014,40(3):907-919.
APA	Yu, Huapeng,Chang, Yongxin,Lu, Pei,Xu, Zhiyong,Fu, Chengyu,&Wang, Yafei.(2014).Efficient object detection based on selective attention.Computers and Electrical Engineering,40(3),907-919.
MLA	Yu, Huapeng,et al."Efficient object detection based on selective attention".Computers and Electrical Engineering 40.3(2014):907-919.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。