Landmark Selection for Vision-Based Navigation

Abstract

Recent work in the object recognition community has yielded a class of interest-point-based features that are stable under significant changes in scale, viewpoint, and illumination, making them ideally suited to landmark-based navigation. Although many such features may be visible in a given view of the robot's environment, only a few such features are necessary to estimate the robot's position and orientation. In this paper, we address the problem of automatically selecting, from the entire set of features visible in the robot's environment, the minimum (optimal) set by which the robot can navigate its environment. Specifically, we decompose the world into a small number of maximally sized regions, such that at each position in a given region, the same small set of features is visible. We introduce a novel graph theoretic formulation of the problem, and prove that it is NP-complete. Next, we introduce a number of approximation algorithms and evaluate them on both synthetic and real data. Finally, we use the decompositions from the real image data to measure the localization performance versus the undecomposed map.

Manifold based map representation for mobile robot using Euclidean data difference dimension reduction

“…As LDA is a supervised method (Sala et al, 2006), therefore it can be used for generating a robot map in unknown environment.…”

“…In this method, the local neighborhood geometry is preserved however this method cannot be applied for the kidnaped robot problem. By Sala et al (2006), an appearance based map is presented with a landmark selection technique. The selection method does not guarantee orthogonality or independence of the selected features.…”

Region and constellations based categorization of images with unsupervised graph learning

“…RANSAC can be also used as a standalone global localization method [38], when 3D data is available. The problem of learning a set of features for pose estimation has been investigated in [39], and the problem of selecting the minimal set of features for navigation is tackled in [40]. Finally, a method for reducing the number of images in the data set with the minimal loss of information is proposed in [41].…”

Saliency prediction in the coherence theory of attention

“…In general, approaches have exploited the simulation of saccades either by active cameras, as in Butko, Zhang, Cottrell, and Movellan (2008), Mancas, Pirri, and Pizzoli (2011), or via biologically founded prior models of saliency as in Pichon and Itti (2002), Ackerman and Itti (2005), Hügli, Jost, and Ouerhani (2005), Cerf, Harel, Einhäuser, and Koch (2007), Sala, Sim, Shokoufandeh, and Dickinson (2006), Mahadevan and Vasconcelos (2010), to cite some of the works from the wide literature on saliency prediction.…”