CoPR: Toward Accurate Visual Localization With Continuous Place-Descriptor Regression

Enhanced Monte Carlo Localization with Visual Place Recognition for Robust Robot Localization

This paper proposes extending Monte Carlo Localization methods with visual place recognition information in order to build a robust robot localization system. This system is aimed to work in crowded and non-planar scenarios, where 2D laser rangefinders may not always be enough to match the robot position within the map. Thus, visual place recognition will be used in order to obtain robot positi...

Exclusive Visual Descriptor Quantization

Vector quantization (VQ) using exhaustive nearest neighbor (NN) search is the speed bottleneck in classic bag of visual words (BOV) models. Approximate NN (ANN) search methods still cost great time in VQ, since they check multiple regions in the search space to reduce VQ errors. In this paper, we propose ExVQ, an exclusive NN search method to speed up BOV models. Given a visual descriptor, a po...

Toward Bayesian Classifiers with Accurate Probabilities

Face Alignment by Local Deep Descriptor Regression

We present an algorithm for extracting key-point descriptors using deep convolutional neural networks (CNN). Unlike many existing deep CNNs, our model computes local features around a given point in an image. We also present a face alignment algorithm based on regression using these local descriptors. The proposed method called Local Deep Descriptor Regression (LDDR) is able to localize face la...

Visual Place Recognition with Probabilistic Vertex Voting

We propose a novel scoring concept for visual place recognition based on nearest neighbor descriptor voting and demonstrate how the algorithm naturally emerges from the problem formulation. Based on the observation that the number of votes for matching places can be evaluated using a binomial distribution model, loop closures can be detected with high precision. By casting the problem into a pr...