Salient human detection for robot vision

被引:8
作者
Kwak, Sooyeong
Ko, ByoungChul
Byun, Hyeran [1 ]
机构
[1] Yonsei Univ, Dept Comp Sci, Seoul, South Korea
[2] Keimyung Univ, Dept Comp Engn, Taegu, South Korea
关键词
salient human detection; pre-attentive features; support vector machine; color map; luminance map; motion map;
D O I
10.1007/s10044-007-0068-8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a salient human detection method that uses pre-attentive features and a support vector machine (SVM) for robot vision. From three pre-attentive features (color, luminance and motion), we extracted three feature maps and combined them as a salience map. By using these features, we estimated a given object's location without pre-assumptions or semi-automatic interaction. We were able to choose the most salient object even if multiple objects existed. We also used the SVM to decide whether a given object was human (among the candidate object regions). For the SVM, we used a new feature extraction method to reduce the feature dimensions and reflect the variations of local features to classifiers by using an edged-mosaic image. The main advantage of the proposed method is that our algorithm was able to detect salient humans regardless of the amount of movement, and also distinguish salient humans from non-salient humans. The proposed algorithm can be easily applied to human robot interfaces for human-like vision systems.
引用
收藏
页码:291 / 299
页数:9
相关论文
共 14 条
[1]  
[Anonymous], IEEE INT VEH S
[2]   W4:: Real-time surveillance of people and their activities [J].
Haritaoglu, I ;
Harwood, D ;
Davis, LS .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) :809-830
[3]  
ITTI L, 2000, IEEE T PAMI, V20, P1254
[4]  
Jung B., 2004, 8th Conference on Intelligent Autonomous Systems, P980
[5]  
Kanade T., 1987, P INT JOINT C ART IN, P674
[6]  
MOGHADDAM B, 2006, IEEE INT C AUT FAC G, P306
[7]   Example-based object detection in images by components [J].
Mohan, A ;
Papageorgiou, C ;
Poggio, T .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (04) :349-361
[8]   Pedestrian detection using wavelet templates [J].
Oren, M ;
Papageorgiou, C ;
Sinha, P ;
Osuna, E ;
Poggio, T .
1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :193-199
[9]   A general framework for object detection [J].
Papageorgiou, CP ;
Oren, M ;
Poggio, T .
SIXTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, 1998, :555-562
[10]   Theory of mind for a humanoid robot [J].
Scassellati, B .
AUTONOMOUS ROBOTS, 2002, 12 (01) :13-24