Abstract
In this paper, we present a new stereo vision-based system and its efficient hardware implementation for real-time underwater environments exploration throughout 3D sparse reconstruction based on a number of feature points. The proposed underwater 3D shape reconstruction algorithm details are presented. The main concepts and advantages are discussed and comparison with existing systems is performed. In order to achieve real-time video constraints, a hardware implementation of the algorithm is performed using Xilinx System Generator. The pipelined stereo vision system has been implemented using Field Programmable Gate Arrays (FPGA) technology. Both timing constraints and mathematical operations precision have been evaluated in order to validate the proposed hardware implementation of our system. Experimental results show that the proposed system presents high accuracy and execution time performances.
Highlights
Exploitation and preservation of groundwater resources are very important with many challenges related to economic development, social constraints and mainly environment protection
(2) Intersecting the ray vector "r2 "corresponding to the laser projection on image plane (∏2 ) to the a set of stereo images of2 pattern test placed on2 both cameras common field of view, image laser beam position (Zlaser ) with respect to camera segmentation that highlights the laser projections, outliers elimination based on region‐constraints, laser spot extraction along the laser beam direction, and the underwater 3D shape reconstruction algorithm based on distance measurements between the optical center and each laser projection
This paper presents a methodology for implementing real-time DSP applications on a reconfigurable logic platform using
Summary
Exploitation and preservation of groundwater resources are very important with many challenges related to economic development, social constraints and mainly environment protection In this context, hydro-geologists are, for example, highly attracted by the interest of confined underwater environments. The computational complexity and large amount of data make real-time processing of stereo vision challenging because of the inherent instruction cycle delay within conventional computers [1] In this case, custom architecture implementation on FPGA (Field Programmable Gate Arrays) is one of the most recommended solutions. We propose a 3D shape reconstruction algorithm for underwater confined environment (karst) exploration using stereoscopic images and its pipelined hardware architecture design. Conclusions and future works are presented in the last section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
