Object Detection Method for Grasping Robot Based on Improved YOLOv5

In the industrial field, the anthropomorphism of grasping robots is the trend of future development, however, the basic vision technology adopted by the grasping robot at this stage has problems such as inaccurate positioning and low recognition efficiency. Based on this practical problem, in order...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qisong Song, Shaobo Li, Qiang Bai, Jing Yang, Xingxing Zhang, Zhiang Li, Zhongjing Duan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	grasping robot object detection improved YOLOv5 network hand-eye calibration method convolutional neural network Mechanical engineering and machinery TJ1-1570
Acceso en línea:	https://doaj.org/article/519ef2f2e47a41938098f579756a55e8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:519ef2f2e47a41938098f579756a55e8
record_format	dspace
spelling	oai:doaj.org-article:519ef2f2e47a41938098f579756a55e82021-11-25T18:22:41ZObject Detection Method for Grasping Robot Based on Improved YOLOv510.3390/mi121112732072-666Xhttps://doaj.org/article/519ef2f2e47a41938098f579756a55e82021-10-01T00:00:00Zhttps://www.mdpi.com/2072-666X/12/11/1273https://doaj.org/toc/2072-666XIn the industrial field, the anthropomorphism of grasping robots is the trend of future development, however, the basic vision technology adopted by the grasping robot at this stage has problems such as inaccurate positioning and low recognition efficiency. Based on this practical problem, in order to achieve more accurate positioning and recognition of objects, an object detection method for grasping robot based on improved YOLOv5 was proposed in this paper. Firstly, the robot object detection platform was designed, and the wooden block image data set is being proposed. Secondly, the Eye-In-Hand calibration method was used to obtain the relative three-dimensional pose of the object. Then the network pruning method was used to optimize the YOLOv5 model from the two dimensions of network depth and network width. Finally, the hyper parameter optimization was carried out. The simulation results show that the improved YOLOv5 network proposed in this paper has better object detection performance. The specific performance is that the recognition precision, recall, mAP value and F1 score are 99.35%, 99.38%, 99.43% and 99.41% respectively. Compared with the original YOLOv5s, YOLOv5m and YOLOv5l models, the mAP of the YOLOv5_ours model has increased by 1.12%, 1.2% and 1.27%, respectively, and the scale of the model has been reduced by 10.71%, 70.93% and 86.84%, respectively. The object detection experiment has verified the feasibility of the method proposed in this paper.Qisong SongShaobo LiQiang BaiJing YangXingxing ZhangZhiang LiZhongjing DuanMDPI AGarticlegrasping robotobject detectionimproved YOLOv5 networkhand-eye calibration methodconvolutional neural networkMechanical engineering and machineryTJ1-1570ENMicromachines, Vol 12, Iss 1273, p 1273 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	grasping robot object detection improved YOLOv5 network hand-eye calibration method convolutional neural network Mechanical engineering and machinery TJ1-1570
spellingShingle	grasping robot object detection improved YOLOv5 network hand-eye calibration method convolutional neural network Mechanical engineering and machinery TJ1-1570 Qisong Song Shaobo Li Qiang Bai Jing Yang Xingxing Zhang Zhiang Li Zhongjing Duan Object Detection Method for Grasping Robot Based on Improved YOLOv5
description	In the industrial field, the anthropomorphism of grasping robots is the trend of future development, however, the basic vision technology adopted by the grasping robot at this stage has problems such as inaccurate positioning and low recognition efficiency. Based on this practical problem, in order to achieve more accurate positioning and recognition of objects, an object detection method for grasping robot based on improved YOLOv5 was proposed in this paper. Firstly, the robot object detection platform was designed, and the wooden block image data set is being proposed. Secondly, the Eye-In-Hand calibration method was used to obtain the relative three-dimensional pose of the object. Then the network pruning method was used to optimize the YOLOv5 model from the two dimensions of network depth and network width. Finally, the hyper parameter optimization was carried out. The simulation results show that the improved YOLOv5 network proposed in this paper has better object detection performance. The specific performance is that the recognition precision, recall, mAP value and F1 score are 99.35%, 99.38%, 99.43% and 99.41% respectively. Compared with the original YOLOv5s, YOLOv5m and YOLOv5l models, the mAP of the YOLOv5_ours model has increased by 1.12%, 1.2% and 1.27%, respectively, and the scale of the model has been reduced by 10.71%, 70.93% and 86.84%, respectively. The object detection experiment has verified the feasibility of the method proposed in this paper.
format	article
author	Qisong Song Shaobo Li Qiang Bai Jing Yang Xingxing Zhang Zhiang Li Zhongjing Duan
author_facet	Qisong Song Shaobo Li Qiang Bai Jing Yang Xingxing Zhang Zhiang Li Zhongjing Duan
author_sort	Qisong Song
title	Object Detection Method for Grasping Robot Based on Improved YOLOv5
title_short	Object Detection Method for Grasping Robot Based on Improved YOLOv5
title_full	Object Detection Method for Grasping Robot Based on Improved YOLOv5
title_fullStr	Object Detection Method for Grasping Robot Based on Improved YOLOv5
title_full_unstemmed	Object Detection Method for Grasping Robot Based on Improved YOLOv5
title_sort	object detection method for grasping robot based on improved yolov5
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/519ef2f2e47a41938098f579756a55e8
work_keys_str_mv	AT qisongsong objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT shaoboli objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT qiangbai objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT jingyang objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT xingxingzhang objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT zhiangli objectdetectionmethodforgraspingrobotbasedonimprovedyolov5 AT zhongjingduan objectdetectionmethodforgraspingrobotbasedonimprovedyolov5
_version_	1718411255517020160

Object Detection Method for Grasping Robot Based on Improved YOLOv5

Ejemplares similares