Abstract
Interest in change detection techniques has considerably increased during recent years in the field of autonomous robotics. This is partly because changes in a robot's working environment are useful for several robotic skills (e.g., spatial cognition, modelling or navigation) and applications (e.g., surveillance or guidance robots). Changes are usually detected by comparing current data provided by the robot's sensors with a previously known map or model of the environment. When the data consists of a large point cloud, dealing with it is a computationally expensive task, mainly due to the amount of points and the redundancy. Using Gaussian Mixture Models (GMM) instead of raw point clouds leads to a more compact feature space that can be used to efficiently process the input data. This allows us to successfully segment the set of 3D points acquired by the sensor and reduce the computational load of the change detection algorithm. However, the segmentation of the environment as a Mixture of Gaussians has some problems that need to be properly addressed. In this paper, a novel change detection algorithm is described in order to improve the robustness and computational cost of previous approaches. The proposal is based on the classic Expectation Maximization (EM) algorithm, for which different selection criteria are evaluated. As demonstrated in the experimental results section, the proposed change detection algorithm achieves the detection of changes in the robot's working environment faster and more accurately than similar approaches.
Highlights
In the last decade, robots and other autonomous systems have been moving away from laboratory setups towards complex real-world environments, which are usually unknown a priori
A comparative study of the different selection criteria was obtained as a result
A change detection and segmentation algorithm based on Mixture of Gaussians has been described for use in autonomous robots
Summary
Robots and other autonomous systems have been moving away from laboratory setups towards complex real-world environments, which are usually unknown a priori. The main drawback of using Gaussian Mixture Models for segmenting changes in the scene is their strong dependence on the number of Gaussians associated to the map When this number is known a priori, the complexity of the problem is reduced and the set of Gaussians is estimated using the classic Expectation and Maximization (EM) algorithm [13]. When the data is acquired in real time by the robot, there is no information about the number of Gaussians, and it should be estimated, which is usually a hard computational task In this vein, the paper proposes an algorithm based on the Split-and-Merge paradigm (SM) [14]. The proposed method focuses on the use of different model selection criteria in order to robustly estimate the number of Gaussians of the mixture, which are evaluated using real and simulated 3D data of indoor environments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
