Corner-based keypoints for scale-invariant detection of partially visible objects

• Autorzy: Śluzek A.
• Konferencja: International Conference on Computer Vision and Graphics ICCVG 2006 (25-27.09.2006 ; Warsaw, Poland)
• Języki publikacji: EN

Abstrakty

EN

Local features (also known as interest points, keypoints, etc.) are a popular and powerful tool for matching images and detecting partially occluded objects. While the problems of photometric distortions of images and rotational invariance of the features have satisfactory solutions, satisfactorily simple scale-invariant algorithms do not exist yet. Generally, either computationally complex methods of scale-space (multi-scale approach) are used, or the correct scale is estimated using additional mechanisms. The paper proposes a new category of keypoints that can be used to develop a simple scale-invariant method for detecting known objects in analyzed images. Keypoints are defined as locations at which selected moment-based parameters are consistent over a wide range of different-size circular patches around the keypoint. While the database of known objects (i.e. the keypoints and their descriptions) is still built using a multi-scale approach, analyzed images are scanned using only a single-scale window and its sub-window. The paper focuses on the keypoint building and keypoint matching principles. Higher-level issues of hypotheses building and verification (regarding the presence of objects in analyzed images) are only briefly discussed.

Słowa kluczowe

EN

local features; keypoints; moment invariants; scale-invariance; geometric approximation

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2006
• Tom: Vol. 15, No. 3/4
• Strony: 639--647
• Opis fizyczny: Bibliogr. 13 poz., il., wykr.

Twórcy

autor

Śluzek A.

• Nanyang Technological University, Singapore; SWPS, Warszawa

Bibliografia

• [1] Maitra S.: Moment invariants. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, New York, 697-699, 1979.
• [2] Moravec H.: Rover visual obstacle avoidance. Proc. Int. Joint Conf. on Artificial Intelligence, Vancouver, 785-790, 1981.
• [3] Harris C., Stephens M.: A combined corner and edge detector. Proc. 4th Alvey Vision Conference, Manchester, 147-151, 1988.
• [4] Lindeberg T.: Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention. Int. Journal of Computer Vision, 11(3), 283-318, 1993.
• [5] Zhang Z., Deriche R., Faugeras O., Luong Q. T.: A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Artificial Intelligence, 78, 87-119, 1995.
• [6] Schmid C., Mohr R.: Local grayvalue invariants for image retrieval. IEEE Trans. PAMI, 19(5), 530-534, 1997.
• [7] Rosin P.L.: Measuring corner properties. Computer Vision & Image Understanding, 73, 291-307, 1999 .
• [8] Mikolajczyk K., Schmid C.: An affine invariant interest point detector. Proc. European Conf. on Computer Vision (ECCV-2002), Copenhagen, 128-142, 2002.
• [9] Lowe D.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision, 60(2), 91-110, 2004.
• [10] Mindru F., Tuytelaars T., Van Gool L., Moons Th.: Moment invariants for recognition under changing viewpoint and illumination. Computer Vision & Image Understanding, 94, 3-27, 2004.
• [11] Śluzek A.: On moments-based local operators for detecting image patterns. Image & Vision Computing, 23, 287-298, 2005.
• [12] Islam M. S.: Recognition and localization of objects in relative scale for robotic applications. PhD thesis, NTU (SCE), Singapore, 2006.
• [13] Śluzek A., Islam M. S., Palaniappan A.: Using interest points for visual detection and identification of objects in complex scenes. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems IROS-2006, Beijing, 5321-5326, 2006.