Artificial Target Location on Mars Exploration

A new location method is proposed to locate the artificial targets on curiosity rover. Firstly, considering the influence of dust particles and non-uniform illumination on Mars, median filtering and adaptive thresholding image segmentation based on integral image are used for edge detection. Then, a two-step location method is proposed to recognize and locate these artificial targets: least square ellipse fitting is used for preliminary location and Hough transform is used for precise location. Experiments are carried out based on artificial target images of curiosity rover, which indicate that the method proposed can be used on the targets with largely deformation, and the location accuracy is within 1 pixel. The method is robust to the dust adhesion, and illumination and shadows effect. It can satisfy the Mars exploration system requirements of resolution and robustness.

[1]  J. Carrascosa,et al.  Template location in noisy pictures , 1988 .

[2]  Fan Sheng-hong,et al.  Subpixel Accuracy Artificial Target Location Using Canny Operator , 2006 .

[3]  Derek Bradley,et al.  Adaptive Thresholding using the Integral Image , 2007, J. Graph. Tools.

[4]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[5]  Bidyut Baran Chaudhuri,et al.  A survey of Hough Transform , 2015, Pattern Recognit..

[6]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[7]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[10]  Linda G. Shapiro,et al.  Computer Vision , 2001 .