RGB-D Image Processing Algorithm for Target Recognition and Pose Estimation of Visual Servo System

This paper studies the control performance of visual servoing system under the planar camera and RGB-D cameras, the contribution of this paper is through rapid identification of target RGB-D images and precise measurement of depth direction to strengthen the performance indicators of visual servoing...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Sensors (Basel, Switzerland) Ročník 20; číslo 2; s. 430
Hlavní autori: Li, Shipeng, Li, Di, Zhang, Chunhua, Wan, Jiafu, Xie, Mingyou
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland MDPI AG 12.01.2020
MDPI
Predmet:
Accuracy
Algorithms
Cameras
depth measurement
Methods
pose estimation
rgb-d sensor
Robots
Sensors
Systems stability
Target recognition
visual servoing
depth measurement
visual servoing
RGB-D sensor
pose estimation
target recognition
ISSN:1424-8220, 1424-8220
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper studies the control performance of visual servoing system under the planar camera and RGB-D cameras, the contribution of this paper is through rapid identification of target RGB-D images and precise measurement of depth direction to strengthen the performance indicators of visual servoing system such as real time and accuracy, etc. Firstly, color images acquired by the RGB-D camera are segmented based on optimized normalized cuts. Next, the gray scale is restored according to the histogram feature of the target image. Then, the obtained 2D graphics depth information and the enhanced gray image information are distort merged to complete the target pose estimation based on the Hausdorff distance, and the current image pose is matched with the target image pose. The end angle and the speed of the robot are calculated to complete a control cycle and the process is iterated until the servo task is completed. Finally, the performance index of this control system based on proposed algorithm is tested about accuracy, real-time under position-based visual servoing system. The results demonstrate and validate that the RGB-D image processing algorithm proposed in this paper has the performance in the above aspects of the visual servoing system.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s20020430