Localization using a Region-Based k-Nearest Neighbour Search
نویسنده
چکیده
This paper explores a method of performing localization on local vision mobile robots. It describes a method of processing images, extracting regions, and comparing those regions against a database of preprocessed images. Localization is achieved using the k-nearest neighbour algorithm as the basis for approximating the current position. Initial results are provided that show the potential of this method.
منابع مشابه
Some improvements on NN based classifiers in metric spaces
The nearest neighbour (NN) and k-nearest neighbour (k-NN) classification rules have been widely used in Pattern Recognition due to its simplicity and good behaviour. Exhaustive nearest neighbour search may become unpractical when facing large training sets, high dimensional data or expensive dissimilarity measures (distances). During the last years a lot of fast NN search algorithms have been d...
متن کاملEecient Nearest-neighbour Searches Using Weighted Euclidean Metrics
Building an index tree is a common approach to speed up the k nearest neighbour search in large databases of many-dimensional records. Many applications require varying distance metrics by putting a weight on diierent dimensions. The main problem with k nearest neighbour searches using weighted euclidean metrics in a high dimensional space is whether the searches can be done eeciently We presen...
متن کاملAn efficient approximation-elimination algorithm for fast nearest-neighbour search based on a spherical distance coordinate formulation
Ramasubramanian, V. and K.K. Paliwal, An efficient approximation-elimination algorithm for fast nearest-neighbour search based on a spherical distance coordinate formulation, Pattern Recognition Letters 13 (1992) 471-480. An efficient approximation-elimination search algorithm for fast nearest-neighbour search is proposed based on a spherical distance coordinate formuTation, where a vector in K...
متن کاملExtending Fast Nearest Neighbour Search Algorithms for Approximate k-NN Classification
The nearest neighbour (NN) and k-nearest neighbour (kNN) classi cation rules have been widely used in pattern recognition due to its simplicity and good behaviour. Exhaustive nearest neighbour search can become unpractical when facing large training sets, high dimensional data or expensive similarity measures. In the last years a lot of NN search algorithms have been developed to overcome those...
متن کاملAn optimized version of the Approximating and Eliminating Search Algorithm (AESA) for Nearest Neighbour classification
The Approximating and Eliminating Search Algorithm (AESA) and related AESA-based techniques are among the fastest methods for (k-)Nearest Neighbour(s) searching in general metric spaces. These techniques can be optimized for the (easier) (k-)Nearest Neighbour(s) classification problem. In particular, an optimized version of the AESA is proposed here which is shown to be significantly faster tha...
متن کامل