A motion and shape-based pedestrian detection algorithm

被引：42

作者：

Elzein, H ^{[1
]}

Lakshmanan, S ^{[1
]}

Watta, P ^{[1
]}

机构：

[1] Univ Michigan, Dept Elect & Comp Engn, Vehicle Elect Lab, Dearborn, MI 48128 USA

来源：

IEEE IV2003: INTELLIGENT VEHICLES SYMPOSIUM, PROCEEDINGS | 2003年

关键词：

D O I：

10.1109/IVS.2003.1212962

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：

In this paper, we investigate a vision-based pedestrian detection algorithm which can be used in the design of intelligent vehicle systems. The input to the algorithm is video data obtained from a camera mounted on the vehicle. In the proposed method, a wavelet transform is computed on the video frames, and multiscale template matching is used to determine whether or not a pedestrian is present in the frame. Motion detection and localization is used to reduce the computational requirements. Experimental results are presented for several different video sequences. The results show that this method is able to reliably detect pedestrians in cluttered scenes.

引用

页码：500 / 504

页数：5

共 13 条

[1] Walking Pedestrian Recognition [J].

Curio, Cristobal ;

Edelbrunner, Johann ;

Kalinke, Thomas ;

Tzomakas, Christos ;

von Seelen, Werner .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2000, 1 (03) :155-163

[2]

Gavrila D. M., 1999, INT C COMP VIS CORF

[3]

MALLAT S, 1989, IEEE T PATTERN ANAL, P674

[4] ONLINE VEHICLE AND PEDESTRIAN DETECTIONS BASED ON SIGN PATTERN [J].

MORI, H ;

CHARKARI, NM .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1994, 41 (04) :384-391

[5]

OREN M, 1997, COMPUTER VISION PATT, P193

[6]

RAMARATHNAM N, 2001, THESIS U MICHIGAN DE

[7]

ROHR K, 1993, COMPUTER VISION PATT, P8

[8]

SINHA P, 1994, INVEST OPHTHALMOL, V35, P1735

[9]

SINHA P, 1994, 1505 MIT AI LAB

[10]

STOLLNITZ E, 1994, TR940911 U WASH

← 1 2 →