MOF algorithm for moving target detection on mobile platform

Chen Haixin; Gu Guohua; Qian Weixian; Chen Qian; Xu Fuyuan

Based on the global motion of the scene caused by the movement of the camera focus, a method named MOF(Motion Of Focus) was established. As the camera moved freely, the compensation of the overall movement was needed for the strong parallax caused by the depth of field. From the perspective of the camera, analysis of the compensation was performed which emphasized on the movement relation between the moving camera and optical field, and a MOF Model was given to show the characterization of the overall movement of the scene. With the camera movement speculated by the overall movement, optical flow constraints were deduced to exclude the parallax false alarm by projective geometry from the perspective of the moving camera. At the end, experiments were performed based on actual image data. And the results compared with other algorithms show that this model is practical under the translation and rotation of camera.

1. School of Electronic & Optical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China

Received Date: 2013-06-25

Rev Recd Date: 2013-07-03

Publish Date: 2014-02-25

Key words:

Abstract: Based on the global motion of the scene caused by the movement of the camera focus, a method named MOF(Motion Of Focus) was established. As the camera moved freely, the compensation of the overall movement was needed for the strong parallax caused by the depth of field. From the perspective of the camera, analysis of the compensation was performed which emphasized on the movement relation between the moving camera and optical field, and a MOF Model was given to show the characterization of the overall movement of the scene. With the camera movement speculated by the overall movement, optical flow constraints were deduced to exclude the parallax false alarm by projective geometry from the perspective of the moving camera. At the end, experiments were performed based on actual image data. And the results compared with other algorithms show that this model is practical under the translation and rotation of camera.

HTML

Reference (15)

[1]
[2]	Zhang Y, Kiselewich S J, Bauson W A, et al. Robust moving object detection at distance in the visible spectrum and beyond using a moving camera[C]//CVPRW'06 Conference on IEEE, 2006: 131-131.
[3]
[4]	Micheloni C, Rinner B, Foresti G L. Video analysis in pan-tilt-zoom camera networks[J]. Signal Processing Magazine IEEE, 2010, 27(5): 78-90.
[5]
[6]	Xu Zhang, Wang Shengjin, Ding Xiaoqing. Beyond dominant plane assumption: moving objects detection in severe dynamic scenes with Multi-Classes RANSAC[C]//Audio, Language and Image Processing (ICALIP), 2012 International Conference on IEEE, 2012:
[7]
[8]	Wang Song, Wang Huiyuan, Wang Xiufen, et al. Approach of tracking moving targets in videos based on FOE and modified MCMC[J]. Computer Application and Software, 2012, 29(1): 38-41. (in Chinese)
[9]	Fernndez-Caballero A, Castillo J C, Martnez-Cantos J, et al. Optical flow or image subtraction in human detection from infrared camera on mobile robot[J]. Robotics and Autonomous Systems, 2010, 58(12): 1273-1281.
[10]
[11]
[12]	Huang Can, Zhang Dayu. The target location ranging based on monocular vision of mobile robot[J]. Software, 2012, 33(10): 49-51. (in Chinese)
[13]
[14]	Breitenstein M D, Reichlin F, Leibe B, et al. Online multiperson tracking-by-detection from a single, uncalibrated camera[J]. Pattern Analysis and Machine Intelligence, 2011, 33(9): 1820-1833.
[15]	Bay H, Tuytelaars T, Van Gool L. Surf: Speeded up robust features[M] Berlin: Springer, 2006: 404-417.

MOF algorithm for moving target detection on mobile platform

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views