Stereo-based preprocessing for human shape localization in unstructured environments

被引：21

作者：

Broggi, A ^{[1
]}

Fascioli, A ^{[1
]}

Fedriga, I ^{[1
]}

Tibaldi, A ^{[1
]}

Del Rose, M ^{[1
]}

机构：

[1] Univ Parma, Dipartimento Ingn Informaz, I-43100 Parma, Italy

来源：

IEEE IV2003: INTELLIGENT VEHICLES SYMPOSIUM, PROCEEDINGS | 2003年

关键词：

pedestrian detection; stereo vision; symmetry; obstacle detection;

D O I：

10.1109/IVS.2003.1212946

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Ibis paper describes the research activities for the localization of human shapes using visual information carried on at the University of Parma, Italy, in the frame of a common project with the TACOM Department of U. S. Army. The paper proposes the application of a stereoscopic technique as a preprocessing for the localization of humans in generic unstructured environments. Each row of the left image is matched with the epipolar row of the right image. This creates a map of each object in the scene as well as the slope of the road. Preliminary results have proved to be promising.

引用

页码：410 / 415

页数：6

共 9 条

[1]

BERTOZZI M, 2002, P IEEE INT VEH S 200

[2]

BRENDLE B, 2003, P SPIE AER C 2003, V5080

[3]

BRENDLE B, 2002, P SPIE AER C 2002 OR, V4715

[4] Shape-based pedestrian detection [J].

Broggi, A ;

Bertozzi, M ;

Fascioli, A ;

Sechi, M .

PROCEEDINGS OF THE IEEE INTELLIGENT VEHICLES SYMPOSIUM 2000, 2000, :215-220

[5]

Kang S, 2002, LECT NOTES COMPUT SC, V2388, P268

[6]

LABAYRADE R, 2002, P IEEE INT VEH S 200

[7] Pedestrian tracking from a moving vehicle [J].

Philomin, V ;

Duraiswami, R ;

Davis, L .

PROCEEDINGS OF THE IEEE INTELLIGENT VEHICLES SYMPOSIUM 2000, 2000, :350-355

[8]

Song Y, 2000, PROC CVPR IEEE, P810, DOI 10.1109/CVPR.2000.855904

[9] Stereo- and Neural Network-Based Pedestrian Detection [J].

Zhao, Liang ;

Thorpe, Charles E. .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2000, 1 (03) :148-154

← 1 →