Loading [a11y]/accessibility-menu.js
Sensor Placement Optimization using Random Sample Consensus for Best Views Estimation | IEEE Conference Publication | IEEE Xplore

Sensor Placement Optimization using Random Sample Consensus for Best Views Estimation


Abstract:

The estimation of a 3D sensor constellation for maximizing the observable surface area percentage of a given set of target objects is a challenging and combinatorial expl...Show More

Abstract:

The estimation of a 3D sensor constellation for maximizing the observable surface area percentage of a given set of target objects is a challenging and combinatorial explosive problem that has a wide range of applications for perception tasks that may require gathering sensor information from multiple views due to environment occlusions. To tackle this problem, the Gazebo simulator was configured for accurately modeling 8 types of depth cameras with different hardware characteristics, such as image resolution, field of view, range of measurements and acquisition rate. Later on, several populations of depth sensors were deployed within 4 different testing environments targeting object recognition and bin picking applications with increasing level of occlusions and geometry complexity. The sensor populations were either uniformly or randomly inserted on a set of regions of interest in which useful sensor data could be retrieved and in which the real sensors could be installed or moved by a robotic arm. The proposed approach of using fusion of 3D point clouds from multiple sensors using color segmentation and voxel grid merging for fast surface area coverage computation, coupled with a random sample consensus algorithm for best views estimation, managed to quickly estimate useful sensor constellations for maximizing the observable surface area of a set of target objects, making it suitable to be used for deciding the type and spatial disposition of sensors and also guide movable 3D cameras for avoiding environment occlusions.
Date of Conference: 26-27 April 2023
Date Added to IEEE Xplore: 25 May 2023
ISBN Information:

ISSN Information:

Conference Location: Tomar, Portugal

I. Introduction

Object recognition within environments with large and dynamic occlusions is a challenging task that can be tackled by either deploying an extensive and expensive sensor constellation or by actively moving a set of sensors within the environment in order to maximize the observable surface area of the target objects. This is a variant of the View Planning Problem (VPP) [1] , which has a wide range of applications within the active perception domain, such as the estimation of the next best view for 3D scanning [2] , object recognition with occlusions, exploration of unknown environments, deployment of sensor networks to monitor targets, among many others.

References

References is not available for this document.