基于区域预测和视觉注意计算的快速目标检测

刘琼; 秦世引

doi:CNKI:11-2625/V.20111013.1436.004

基于区域预测和视觉注意计算的快速目标检测

doi: CNKI:11-2625/V.20111013.1436.004

刘琼,
秦世引

北京航空航天大学自动化科学与电气工程学院, 北京 100191

基金项目: 国家自然科学基金资助项目(60875072); 中澳国际合作资助项目(2007DFA11530)

详细信息

中图分类号: TP 391
计量
- 文章访问数: 2189
- HTML全文浏览量: 51
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2010-06-17
- 网络出版日期: 2011-10-30

Fast target detection based on area prediction and visual attention computation

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 提出了一种结合区域预测与视觉注意模型化计算的快速目标检测方法.通过分析图像近似均匀的3个水平子区域的方向特征图之灰度比率,灰度特征图之信息熵和子区域位置,建立了目标区域预测的判定准则.同时,通过优选特征和优化特征图之权重,改进了视觉注意计算模型.对于一幅待检测图像,根据区域预测的判定准则,实现目标区域的快速预测,并利用改进的视觉注意计算模型对目标区域进行视觉注意计算,实现特定目标的快速精确定位.实验结果表明:针对户外场景中的行人目标,与通过整幅图像的视觉注意计算来实现目标检测的传统方法相比较,该检测方法可使检测时间缩短30%,同时还能使检测准确率提高9%.
- 目标检测 /
- 区域预测 /
- 视觉注意模型化计算 /
- 户外场景行人目标
Abstract: A new method of fast target detection was proposed with combination of area prediction and modeling computation of visual attention (VA). A rule set to predict target area was established based on the analysis of three feature parameters in three horizontal subareas: grayscale rate, entropy and its position. Meanwhile, the VA computational model was improved by optimizing the selected features and optimizing contribution weights of feature maps. Given an image to be detected, the target area was predicted according to the rule set. Then, the VA modeling computation was carried out only in the predicted areas. The experiment results demonstrate that in the task of detecting pedestrian in outdoor scene, the proposed method can reduce the detection time by 30% and enhance the detection accuracy by 9% in comparison with the traditional method.
- target detection /
- area prediction /
- computational modeling of visual attention /
- pedestrian in outdoor scene

HTML全文

参考文献(1)

[1] 郑南宁.认知过程的信息处理和新型人工智能系统[J].中国基础科学,2000(8):11-20 Zheng Nanning.Information processing for cognition process and new artificial intelligent systems[J].China Basic Science,2000(8):11-20(in Chinese) [2] 王璐,蔡自兴.未知环境中基于视觉显著性的自然路标检测[J].模式识别与人工智能,2006,19(1):100-105 Wang Lu,Cai Zixing.Visual saliency based natural landmarks detection under unknown environments[J].Pattern Recognition and Artificial Intelligence,2006,19(1):100-105(in Chinese) [3] Mutch J,Lowe D G.Object class recognition and localization using sparse features with limited receptive fields[J].International Journal of Computer Vision,2008,80(1):45-57 [4] 李志成,秦世引,Itti L.遥感图像的显著-概要特征提取与目标检测[J].北京航空航天大学学报,2010,36(6):659-662 Li Zhicheng,Qin Shiyin,Itti L.Extraction of saliency-gist features and target detection for remote sensing images[J].Journal of Beijing University of Aeronautics and Astronautics,2010,36(6):659-662(in Chinese) [5] Yantis S.Stimulus-driven attentional capture and attentional control settings[J].Journal of Experimental Psychology:Human Perception and Performance,1993,19(3):676-681 [6] Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259 [7] 张菁,沈兰荪,高静静.基于视觉注意模型和进化规划的感兴趣区检测方法[J].电子与信息学报,2009,31(7):1646-1652 Zhang Jing,Shen Lansun,Gao Jingjing.Region of interest detection based on visual attention model and evolutionary programming[J].Journal of Electronics & Information Technology,2009,31(7):1646-1652(in Chinese) [8] Pollmann S,Manginelli A A.Repeated contextual search cues lead to reduced bold-onset times in early visual and left inferior frontal cortex[J].Open Neuroimag J,2010(4):9-15 [9] Oliva A,Torralba A,Castelhano M S,et al.Top-down control of visual attention in object detection //SuviSofi Oy Ltd.Proceedings of the IEEE International Conference on Image Processing.Barcelona,Spain:IEEE Signal Processing Society,2003:253-256 [10] Durrie D,Mcminn P S.Computer-based primary visual cortex training for treatment of low myopia and early presbyopia[J].Trans Am Ophthalmol Soc,2007,105:132-140 [11] Li Jia.Photography image database.University Park:The Pennsylvania State University,2001.http://www.stat.psu.edu/~jiali/index.download.html [12] Torralba A.LabelMe image database.Cambridge,MA:Computer Science and Artificial Intelligence Laboratory,Massachusetts Institute of Technology,2006.http://people.csail.mit.edu/torralba/GlobalFeaturesAndAttention/

施引文献

资源附件(0)

访问统计