Detection of Color Indicators under Complex Circumstances

Abstract:

A color indicator detection algorithm under different illumination conditions is proposed. First, based on the similarity between consecutive video frames in channel L of Lab color space, background image can be determined. Differentiation of a frame and the background can identify the motion region, and thus the search area for the color indicator is greatly reduced. Second, the convex hull of motion region is specified and sampling is taken within it. By assigning the weight, seeds can be determined using clustering method. Finally, region growing is implemented by applying Bayesian decision with minimal error ratio. The method is applicable to more different conditions and produces better results compared with traditional color-threshold vector method.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 6157-6161
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.6157
• Online since: January 2012
• Authors: Lu Ping Fang, Yuan Jie Wei, Fei Lu
• Keywords: Bayesian Decision, Convex Hull, Lab Color Space, Region Growing

References

[1] Lee H K, Kim J H. An HMM-based threshold model approach of gesture recognition[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence, 1999, 21(10): 961~973.

DOI: 10.1109/34.799904

[2] Brethes L, Menezes P, Lerasle F, et al. Face tracking and hand gesture recognition for human-robot interaction[A]. Proceedings of IEEE International Conference on Robotics and Automation[C]. Piscataway, NJ, USA: IEEE, 2004: 1901~(1906).

DOI: 10.1109/robot.2004.1308101

[3] Chen Yimin，zhang Yunhua; Research on Human-Robot Interaction Technique Based on Hand Gesture Recognition [A]. ROBOT, 2009, 31(4): 351~356.

[4] Xiao Zhi-yong; QIN Hua-biao. Human-computer Interaction Based on Gaze Tracking and Gesture Recognition [A]. Computer Engineering, 2009, 35(15): 198-200.

[5] Xiang You-jun LEI Na YU Wei-yu XIE Sheng-li. Research of Block Matching Criterion for Motion Estimation [A]. Computer Science, 2009, 9(36): 278~280.

[6] Yang Hui. Research on Thresholding Methods for Image Segmentation [J]. Journal of Liaoning University(Natural Sciences Edition), 2006, 33(2): 135-137.

[7] Gao Shouchua, Yao lingtian. Visual C++ Practice and Improvement—Digital image processing and Engineering Application. China Railway Press, (2006).