Collaborative Cross-Domain $k$ NN Search for Remote Sensing Image Processing

Abstract

$k$ NN search is a fundamental function in image processing, which is useful in many real applications, including image cluster, image classification, and image understanding and analysis in general. In this light, we propose and study a novel collaborative cross-domain $k$ NN search (CD- $k$ NN) in multidomain space. Given a query location $q$ in a multidomain space (e.g., spatial domain, temporal domain, textual domain, and so on), the CD- $k$ NN finds top- $k$ data points with the minimum distance to $q$ . This problem is challenging due to two reasons. First, how to define practical distance measures to evaluate the distance in multidomain space. Second, how to prune the search space efficiently in multiple domains. To address the challenges, we define a linear combination method-based distance measure for multidomain space. Based on the distance measure, a collaborative search method is developed to constrain the CD search space in a comparable smaller range. A pair of upper and lower bounds is defined to prune the search space in multiple domains effectively. Finally, we conduct extensive experiments to verify that the developed methods can achieve a high performance.