中国物理B ›› 2010, Vol. 19 ›› Issue (10): 104203-104203.doi: 10.1088/1674-1056/19/10/104203

• • 上一篇    下一篇

Spin-image surface matching based target recognition in laser radar range imagery

王丽, 孙剑峰, 王骐   

  1. National Key Laboratory of Tunable Laser Technology, Harbin Institute of Technology, Harbin 150001, China
  • 收稿日期:2010-02-01 修回日期:2010-03-16 出版日期:2010-10-15 发布日期:2010-10-15
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant No. 60901046).

Spin-image surface matching based target recognition in laser radar range imagery

Wang Li(王丽)†, Sun Jian-Feng(孙剑峰), and Wang Qi(王骐)   

  1. National Key Laboratory of Tunable Laser Technology, Harbin Institute of Technology, Harbin 150001, China
  • Received:2010-02-01 Revised:2010-03-16 Online:2010-10-15 Published:2010-10-15
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant No. 60901046).

PDF (PC)

753

赞

摘要： We explore the problem of in-plane rotation-invariance existing in the vertical detection of laser radar (Ladar) using the algorithm of spin-image surface matching. The method used to recognize the target in the range imagery of Ladar is time-consuming, owing to its complicated procedure, which violates the requirement of real-time target recognition in practical applications. To simplify the troublesome procedures, we improve the spin-image algorithm by introducing a statistical correlated coefficient into target recognition in range imagery of Ladar. The system performance is demonstrated on sixteen simulated noise range images with targets rotated through an arbitrary angle in plane. A high efficiency and an acceptable recognition rate obtained herein testify the validity of the improved algorithm for practical applications. The proposed algorithm not only solves the problem of in-plane rotation-invariance rationally, but also meets the real-time requirement. This paper ends with a comparison of the proposed method and the previous one.

Abstract: We explore the problem of in-plane rotation-invariance existing in the vertical detection of laser radar (Ladar) using the algorithm of spin-image surface matching. The method used to recognize the target in the range imagery of Ladar is time-consuming, owing to its complicated procedure, which violates the requirement of real-time target recognition in practical applications. To simplify the troublesome procedures, we improve the spin-image algorithm by introducing a statistical correlated coefficient into target recognition in range imagery of Ladar. The system performance is demonstrated on sixteen simulated noise range images with targets rotated through an arbitrary angle in plane. A high efficiency and an acceptable recognition rate obtained herein testify the validity of the improved algorithm for practical applications. The proposed algorithm not only solves the problem of in-plane rotation-invariance rationally, but also meets the real-time requirement. This paper ends with a comparison of the proposed method and the previous one.

Key words: Ladar, automatic target recognition, spin-image, statistical correlation coefficient

中图分类号:  (Image forming and processing)

  • 42.30.Va
42.62.Eh (Metrological applications; optical frequency synthesizers for precision spectroscopy) 42.79.Qx (Range finders, remote sensing devices; laser Doppler velocimeters, SAR, And LIDAR)