| In recent years,with the development of artificial intelligence,the research of three-dimensional reconstruction has become more and more popular.Based on the three-dimensional reconstruction algorithm of structured light and time of flight(TOF),this paper proposes a system and algorithm to fuse the two output depth maps.The main work of this paper includes the following aspects:(1)Introduced the common methods in depth perception field,introduced the concepts of structured light method and time flight method in detail,and the method of system construction.Several methods of phase unwrapping for structured light are introduced in detail.The phase-shifting method and multi-frequency heterodyne algorithm are emphasized.(2)Extracting the depth of the object to be measured based on structured light and TOF algorithm,aiming at the shadow of the object to be measured due to the angle between projection equipment and camera equipment in structured light,which results in errors in three-dimensional reconstruction.This paper proposes an effective algorithm to eliminate errors.The core of the algorithm is to use edge detection technology to extract the contour information of the object to be measured,to extract the noise area by setting the threshold size,and to replace the mean value with the depth information of the unaffected area.Experiments show that the algorithm is feasible and effective.(3)a new method to fuse the depth of TOF camera and the depth output of the structured light camera is introduced.The basic idea is to replace the output depth of structured light at low frequencies with the rough depth of TOF camera output.The depth of TOF output is fused with the output depth of structured light at high frequencies by the proposed multi-frequency heterodyne algorithm.Experiments show that our method can produce high resolution depth information.Finally,the paper summarizes the work of this paper and prospects some meaningful problems. |
PDF Full Text Request