On Optimal Multi-Sensor Network Configuration for 3D Registration

Journal of Sensor and Actuator Networks

Hadi Aliakbarpour¹  V. B. Surya Prasath¹  Jorge Dias² 

[1] Computational Imaging and Visualization Analysis (CIVA) Lab, Department of Computer Science, University of Missouri-Columbia, Columbia 65211, MO, USA;Institute of Systems and Robotics, University of Coimbra, Faculty of Science and Technology, Coimbra 3000-315, Portugal;

关键词: optimal configuration;    sensor network;    genetic algorithm;    3D;    reconstruction;    registration;    human movements;   

DOI  :  10.3390/jsan4040293

来源: DOAJ

【 摘 要 】

Multi-sensor networks provide complementary information for various taskslike object detection, movement analysis and tracking. One of the important ingredientsfor efficient multi-sensor network actualization is the optimal configuration of sensors.In this work, we consider the problem of optimal configuration of a network of coupledcamera-inertial sensors for 3D data registration and reconstruction to determine humanmovement analysis. For this purpose, we utilize a genetic algorithm (GA) based optimizationwhich involves geometric visibility constraints. Our approach obtains optimal configurationmaximizing visibility in smart sensor networks, and we provide a systematic study usingedge visibility criteria, a GA for optimal placement, and extension from 2D to 3D.Experimental results on both simulated data and real camera-inertial fused data indicate weobtain promising results. The method is scalable and can also be applied to other smartnetwork of sensors. We provide an application in distributed coupled video-inertial sensorbased 3D reconstruction for human movement analysis in real time.

【 授权许可】

Unknown