Using Interest Points for Robust Visual Detection and Identification of Objects in Complex Scenes

Abstract

We propose novel tools that reduce complexity and improve performances of visual detection and identification of known objects randomly located in complex cluttered environments. Generally, the propose mechanisms are based on local shape features (interest points, visual saliencies) detected in images and characterized by compact descriptors invariant to geometric and photometric transformations. In particular, a novel invariant for intensity changes is proposed, and the problem of over-exposed and under-exposed images is discussed. Both models of known objects and images of real scenes are represented using interest points, though in different scales (reference scale for models and relative scale for images). By matching interest point detected in images to interest points from the model database, known objects present in the scene can be detected and identified. The methodology can be used both for robot-mounted navigation modules and for distributed visual surveillance systems since the proposed mechanisms minimize the amount of visual data to be transmitted, thus preventing communicational saturation of such systems. In the paper, we focus on the image processing aspects of the problems. Image acquisition issues and high-level identification algorithms are only briefly mentioned.

Object recognition by effective methods and means of computer vision

“…Therefore, the nonhierarchical k-means cluster analysis was applied for sorting [10]. In this way a list of clusters was found, each representing the recognized object A.…”

“…The degree of similarity was represented by the Euclidean distance. [10]. The closer the points of interest were (as to their shapes), the greater similarity was identified.…”

“…Therefore, it was reasonable to define a maximum tolerated measure of dissimilarity. According to [10], such an approach is not recommended because some descriptors require different ranges of tolerance. Therefore another approach was applied [9], in which not only the first but also the second most similar descriptors was searched for.…”