Multiple object detection for pick-and-place applications
Abstract: This paper presents a novel approach for detecting multiple instances of the same object for pick-and-place automation. The working conditions are very challenging, with complex objects, arranged at random in the scene, and heavily occluded. This approach exploits SIFT to obtain a set of correspondences between the object model and the current image. In order to segment the multiple instances of the object, the correspondences are clustered among the objects using a voting scheme which determines the best estimate of the object's center through mean shift. This procedure is compared in terms of accuracy with existing homography-based solutions which make use of RANSAC to eliminate outliers in the homography estimation.
Citation:Piccinini, P.; Prati, A.; Cucchiara, R. "Multiple object detection for pick-and-place applications" Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009, Yokohama, jpn, pp. 362 -365 , 2009, 2009