• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Zhang, Hui (Zhang, Hui.) | Yuan, Haiying (Yuan, Haiying.) | Li, Jianke (Li, Jianke.)

Indexed by:

CPCI-S EI Scopus

Abstract:

A moving object detection algorithm with sparse motion field estimation, motion classification and pixel-wise segmentation is proposed. Firstly, sparse motion field is recovered by fast corner detection and tracking. The corners that belong to the same motion pattern are classified according to their motion consistency, then, the resulting corner group is used to reconstructed scene image, and the foreground corners are identified by getting rid of the group with the least reconstruction error. Finally, optimal dense segmentation of the foreground is performed by using graph cuts, the energy function of which integrates corner motion, local color distribution and image edges. The proposed method is tested on the dataset of real complex scenarios and its effectiveness is demonstrated in the results.

Keyword:

segmentation graph cut corner grouping moving object detection

Author Community:

  • [ 1 ] [Zhang, Hui]Beijing Univ Technol, Coll Elect Informat & Control Engn, Beijing, Peoples R China
  • [ 2 ] [Yuan, Haiying]Beijing Univ Technol, Coll Elect Informat & Control Engn, Beijing, Peoples R China
  • [ 3 ] [Zhang, Hui]Univ Calif San Diego, ECE Dept, La Jolla, CA 92093 USA
  • [ 4 ] [Li, Jianke]Univ Calif San Diego, ECE Dept, La Jolla, CA 92093 USA

Reprint Author's Address:

  • [Zhang, Hui]Beijing Univ Technol, Coll Elect Informat & Control Engn, Beijing, Peoples R China

Email:

Show more details

Related Keywords:

Related Article:

Source :

FIFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2012): COMPUTER VISION, IMAGE ANALYSIS AND PROCESSING

ISSN: 0277-786X

Year: 2013

Volume: 8783

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 2

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 3

Affiliated Colleges:

Online/Total:736/5314149
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.