Vision-based Robot Localization Research Articles

Vision-based robot localization based on the efficient matching of planar features

Real-time accurate localization is a key component of any autonomous mobile robot. Visual localization algorithms usually rely on feature matching between the current view and a map using point descriptors. Many descriptors such as SIFT or SURF are designed to recognize features seen from different viewpoints, but in robotics context, robot movement can be modeled to bring useful information for the matching problem. Here we detail a feature-matching solution using a local 3D model of the features that exploits the motion model of the robot. We compare our method against the SIFT descriptor in a simple matching experiment. The method is then combined with prediction models to achieve autonomous navigation of a mobile robot. Experiments showed that localization remains possible despite severe viewpoint change.

A Shadow Removal Method for a Mobile Robot Localization Using External Surveillance Cameras

Abstract Shadow detection and removal is important to deal with vision based mobile robot localization. The shadow cast by objects within environment which a mobile robot moves can lead to inaccurate object feature extraction and an erroneous scene analysis. To remove the shadow of an object, the difference image between the original and background image is usually used. However, as the shadow area caused by the light source comes out, it should be removed to obtain the accurate object image. In this paper, we used the surveillance cameras installed at the room ceiling for vision based robot localization. Time-consuming algorithm is difficult applied for the mobile robot localization. Therefore, we proposed a fast shadow removal algorithm based the HSV color space. Generally, the shadow removal method by the HSV color space is speedy but not enough to find shadow property compared with other methods. Shadow mask and HSV color space are used together to detect the shadow region. Experimental results show that the proposed method is simple to understand, can detect and remove shadow effectively for a mobile robot localization.

Monte Carlo Filtering Using Kernel Embedding of Distributions

Recent advances of kernel methods have yielded a framework for representing probabilities using a reproducing kernel Hilbert space, called kernel embedding of distributions. In this paper, we propose a Monte Carlo filtering algorithm based on kernel embeddings. The proposed method is applied to state-space models where sampling from the transition model is possible, while the observation model is to be learned from training samples without assuming a parametric model. As a theoretical basis of the proposed method, we prove consistency of the Monte Carlo method combined with kernel embeddings. Experimental results on synthetic models and real vision-based robot localization confirm the effectiveness of the proposed approach.

OUTDOOR VIEW RECOGNITION BASED ON LANDMARK GROUPING AND LOGISTIC REGRESSION

Vision-based robot localization outdoors has remained more elusive than its indoors counterpart. Drastic illumination changes and the scarceness of suitable landmarks are the main difficulties. This paper attempts to surmount them by deviating from the main trend of using local features. Instead, a global descriptor called landmark-view is defined, which aggregates the most visually-salient landmarks present in each scene. Thus, landmark co-occurrence and spatial and saliency relationships between them are added to the single landmark characterization, based on saliency and color distribution. A suitable framework to compare landmark-views is developed, and it is shown how this remarkably enhances the recognition performance, compared against single landmark recognition. A view-matching model is constructed using logistic regression. Experimentation using 45 views, acquired outdoors, containing 273 landmarks, yielded good recognition results. The overall percentage of correct view classification obtained was 80.6%, indicating the adequacy of the approach.

옴니 카메라의 전방향 영상을 이용한 이동 로봇의 위치 인식 시스템

Vision-based robot localization is challenging due to the vast amount of visual information available, requiring extensive storage and processing time. To deal with these challenges, we propose the use of features extracted from omni-directional panoramic images and present a method for localization of a mobile robot equipped with an omni-directional camera. The core of the proposed scheme may be summarized as follows : First, we utilize an omni-directional camera which can capture instantaneous <TEX>$360^{\circ}$</TEX> panoramic images around a robot. Second, Nodes around the robot are extracted by the correlation coefficients of Circular Horizontal Line between the landmark and the current captured image. Third, the robot position is determined from the locations by the proposed correlation-based landmark image matching. To accelerate computations, we have assigned the node candidates using color information and the correlation values are calculated based on Fast Fourier Transforms. Experiments show that the proposed method is effective in global localization of mobile robots and robust to lighting variations.

Monocular Vision-Based Robot Localization and Target Tracking

This paper presents a vision-based technology for localizing targets in 3D environment. It is achieved by the combination of different types of sensors including optical wheel encoders, an electrical compass, and visual observations with a single camera. Based on the robot motion model and image sequences, extended Kalman filter is applied to estimate target locations and the robot pose simultaneously. The proposed localization system is applicable in practice because it is not necessary to have the initializing setting regarding starting the system from artificial landmarks of known size. The technique is especially suitable for navigation and target tracing for an indoor robot and has a high potential extension to surveillance and monitoring for Unmanned Aerial Vehicles with aerial odometry sensors. The experimental results present “cm” level accuracy of the localization of the targets in indoor environment under a high-speed robot movement.

Active Appearance-Based Robot Localization Using Stereo Vision

A vision-based robot localization system must be robust: able to keep track of the position of the robot at any time even if illumination conditions change and, in the extreme case of a failure, able to efficiently recover the correct position of the robot. With this objective in mind, we enhance the existing appearance-based robot localization framework in two directions by exploiting the use of a stereo camera mounted on a pan-and-tilt device. First, we move from the classical passive appearance-based localization framework to an active one where the robot sometimes executes actions with the only purpose of gaining information about its location in the environment. Along this line, we introduce an entropy-based criterion for action selection that can be efficiently evaluated in our probabilistic localization system. The execution of the actions selected using this criterion allows the robot to quickly find out its position in case it gets lost. Secondly, we introduce the use of depth maps obtained with the stereo cameras. The information provided by depth maps is less sensitive to changes of illumination than that provided by plain images. The main drawback of depth maps is that they include missing values: points for which it is not possible to reliably determine depth information. The presence of missing values makes Principal Component Analysis (the standard method used to compress images in the appearance-based framework) unfeasible. We describe a novel Expectation-Maximization algorithm to determine the principal components of a data set including missing values and we apply it to depth maps. The experiments we present show that the combination of the active localization with the use of depth maps gives an efficient and robust appearance-based robot localization system.

Real-time vision-based robot localization

An algorithm for robot localization using visual landmarks is described. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a preloaded map, and the location of the robot from those correspondences. The primary advantages of this algorithm are its use of a single geometric tolerance to describe observation error, its ability to recognize ambiguous sets of correspondences, its ability to compute bounds on the error in localization, and its fast execution. The current version of the algorithm has been implemented and tested on a mobile robot system. In several hundred trials the algorithm has not failed, and computes location accurate to within a centimeter in less than half a second. >