The Method of Mobile Robot Visual Contaminant Detection Based on Five-frame Difference and Visual Background Extractor

Visual contamination of mobile robots can easily affect the information acquisition and function realization of the robot. And the video sequence detection of objects is susceptible to various interferences．In this paper, a contaminant detection method based on five-frame difference and visual background extractor (ViBe) is proposed to detect the contaminant. At the same time, this paper proposes a denoising method for small-area and multi-regional contaminants. Moreover, feasibility of the method was verified by experiments on the automatic detection of contaminants for gun-type camera.

[1]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[2]  Howie Choset,et al.  Design and architecture of the unified modular snake robot , 2012, 2012 IEEE International Conference on Robotics and Automation.

[3]  Daniel E. Koditschek,et al.  RHex: A Simple and Highly Mobile Hexapod Robot , 2001, Int. J. Robotics Res..

[4]  Andrés Faiña,et al.  Lappa: A new type of robot for underwater non-magnetic and complex hull cleaning , 2013, 2013 IEEE International Conference on Robotics and Automation.