The conventional operation and maintenance of 5G computer rooms is characterized by a low level of automation, which can result in untimely replacement of hard disks and potential data loss. In order to achieve efficient and timely replacement of hard disks in 5G computer rooms, this paper proposes a novel methodology for attitude recognition of such disks using an RGB-D depth camera and quintic polynomial interpolation algorithm. This method obtains two-dimensional position information of the hard disk through RGB images, and then combines depth images to obtain the coordinate system of the three-dimensional hard disk. The precise identification of the area to grasp a hard disk is achieved through the design of the grasping process, RGB-D image preprocessing, attitude estimation, and grasping trajectory planning. Additionally, by combining hard disk attitude estimation, the robot arm can be effectively controlled to complete the grasping process of the hard disk. The experiments carried out on the visual recognition method proposed in the article have shown that it achieves high accuracy in recognizing the grasping area of a hard disk. Moreover, the robot arm grasping system based on this method has been used to replace hard disks in 5G computer rooms automatically.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Hard Disk Posture Recognition and Grasping Based on Depth Vision


    Weitere Titelangaben:

    Lect.Notes Computer


    Beteiligte:
    Yang, Huayong (Herausgeber:in) / Liu, Honghai (Herausgeber:in) / Zou, Jun (Herausgeber:in) / Yin, Zhouping (Herausgeber:in) / Liu, Lianqing (Herausgeber:in) / Yang, Geng (Herausgeber:in) / Ouyang, Xiaoping (Herausgeber:in) / Wang, Zhiyong (Herausgeber:in) / Li, Chenyu (Autor:in) / Zhang, Cong (Autor:in)

    Kongress:

    International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023



    Erscheinungsdatum :

    21.10.2023


    Format / Umfang :

    12 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Hard Disk Posture Recognition and Grasping Based on Depth Vision

    Li, Chenyu / Zhang, Cong / Shi, Lun et al. | TIBKAT | 2023


    Determination of Object Location for Robotic Grasping Using Depth Vision Sensor

    Chikurtev, Denis / Yovchev, Kaloyan / Chikurteva, Ava et al. | TIBKAT | 2020


    Stereo-Vision-Guided Object Grasping

    Nguyen, M.-C. / Graefe, V. / International Symposium on Automotive Technology and Automation | British Library Conference Proceedings | 1999


    Stereo-vision-guided object grasping

    Nguyen,M.C. / Graefe,V. / Univ.d.Bundeswehr Muenchen,DE | Kraftfahrwesen | 1999


    A 3D Human Posture Approach for Activity Recognition Based on Depth Camera

    MANZI, Alessandro / CAVALLO, Filippo / DARIO, Paolo | BASE | 2016

    Freier Zugriff