A comparison of an RGB-D cameras performance and a stereo camera in relation to object recognition and spatial position determination

Abstract

Results of using an RGB-D camera (Kinect sensor) and a stereo camera, separately, in order to determine the 3D real position of characteristic points of a predetermined object in a scene are presented. KAZE algorithm was used to make the recognition, that algorithm exploits the nonlinear scale space through nonlinear diffusion filtering; 3D coordinates of the centroid of a predetermined object were calculated employing the camera calibration information and the depth parameter provided by a Kinect sensor and a stereo camera. Other comparisons have been made using different types of cameras similar to those used in this work, however, a conclusion of the best performance depends on the specific application, for example, it has been shown that for 3D surface reconstruction, the Intel RealSense D415 camera has higher precision than the Kinect. Experimental results of this work show it is possible to get the required coordinates with both cameras in order to locate a robot, although a balance in the distance where the sensor is placed must be guaranteed: no fewer than 0.8 m from the object to guarantee the real depth information, it is due to Kinect operating range; 0.5 m to stereo camera, but it must not be 1 m away to have a suitable rate of object recognition, however, without loss of generality it can be concluded that the Kinect presents greater precision in the distance measurements with respect to the stereo camera.

Design and Control of Autonomous Rover for Foliage Navigation

“…By relating Equation ( 8) and ( 12), the relation between the acceleration in terms of mass and torque can be formulated as shown in Equation (13).…”

Evaluating Augmented Reality Communication: How Can We Teach Procedural Skill in AR?

“…Volumetric view and cameras. During the design discussions, we found that the accuracy from state-of-the-art consumer RGBD cameras [13,31] is not sufficient for very small and translucent objects during parts of medical procedures. Thus, we use large 1920x1080 screens in addition to 3D scene reconstruction in our system.…”

Position Identification Method of Isolation Switch for Prosumer Substation Based on Intelligent Image Recognition Technology

“…Corresponding changes occur at the same time to determine whether the opening and closing are in place, that is, the "double confirmation" of the switch position needs to be realized. At present, the research methods for the identification of the opening and closing positions of the isolation switch mainly include pressure sensor technology, micro switch technology, optical sensing technology, attitude sensor and intelligent image recognition technology (Rodriguez, 2021). Among them, image recognition technology mainly refers to the use of computer vision, pattern recognition and other technologies to extract features from the information in the image area to meet the information and visual needs of users in different scenarios (Zheng et al, 2016).…”