Accurate Corner Detection : An Analytical Study

('iiJiicrs aic vcry attractive fca.tiircs for iiiaily applicat.iolls in coinpii tcr vision, including scene analysis, stcreovison, mot.ion aad bl i'ricturr froiu motion analysis. IJI this paper. we consider a. corner ~iiodc~l aiid study analytically its behaviour in the scale-space. \Ve cli>i,iix$ rw1111s tlrai clariry completely t,he 1)cliaviour of some \vel1 Liiowii aproaches iised to detect cornels. In pal ticular. we will \Iim t1ia1 some of tlicin arc iiiadequate for an exact localization of 111~' corner. .A new approach is tlien proposed iii order to correct tlic tlisplaceilient clfect a.nd detect exactly the corner position. Some promising esperimental results obtained on real data. will 111: >llo\vll.

[1]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[2]  Antonio Guiducci,et al.  Corner characterization by differential geometry techniques , 1988, Pattern Recognit. Lett..

[3]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  J. Alison Noble,et al.  Finding Corners , 1988, Alvey Vision Conference.

[5]  Azriel Rosenfeld,et al.  Gray-level corner detection , 1982, Pattern Recognit. Lett..

[6]  Hans P. Morevec.  Towards automatic visual obstacle avoidance , 1977, IJCAI 1977.

[7]  V. Berzins.  Accuracy of laplacian edge detectors , 1984 .

[8]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[9]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.