Cargando…

Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering

It is necessary to detect multi-type farmland obstacles in real time and accurately for unmanned agricultural vehicles. An improved YOLOv5s algorithm based on the K-Means clustering algorithm and CIoU Loss function was proposed to improve detection precision and speed up real-time detection. The K-M...

Descripción completa

Detalles Bibliográficos
Autores principales: Xue, Jinlin, Cheng, Feng, Li, Yuqing, Song, Yue, Mao, Tingting
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8915062/
https://www.ncbi.nlm.nih.gov/pubmed/35270935
http://dx.doi.org/10.3390/s22051790
_version_ 1784667919471345664
author Xue, Jinlin
Cheng, Feng
Li, Yuqing
Song, Yue
Mao, Tingting
author_facet Xue, Jinlin
Cheng, Feng
Li, Yuqing
Song, Yue
Mao, Tingting
author_sort Xue, Jinlin
collection PubMed
description It is necessary to detect multi-type farmland obstacles in real time and accurately for unmanned agricultural vehicles. An improved YOLOv5s algorithm based on the K-Means clustering algorithm and CIoU Loss function was proposed to improve detection precision and speed up real-time detection. The K-Means clustering algorithm was used in order to generate anchor box scales to accelerate the convergence speed of model training. The CIoU Loss function, combining the three geometric measures of overlap area, center distance and aspect ratio, was adopted to reduce the occurrence of missed and false detection and improve detection precision. The experimental results showed that the inference time of a single image was reduced by 75% with the improved YOLOv5s algorithm; compared with that of the Faster R-CNN algorithm, real-time performance was effectively improved. Furthermore, the mAP value of the improved algorithm was increased by 5.80% compared with that of the original YOLOv5s, which indicates that using the CIoU Loss function had an obvious effect on reducing the missed detection and false detection of the original YOLOv5s. Moreover, the detection of small target obstacles of the improved algorithm was better than that of the Faster R-CNN.
format Online
Article
Text
id pubmed-8915062
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89150622022-03-12 Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering Xue, Jinlin Cheng, Feng Li, Yuqing Song, Yue Mao, Tingting Sensors (Basel) Article It is necessary to detect multi-type farmland obstacles in real time and accurately for unmanned agricultural vehicles. An improved YOLOv5s algorithm based on the K-Means clustering algorithm and CIoU Loss function was proposed to improve detection precision and speed up real-time detection. The K-Means clustering algorithm was used in order to generate anchor box scales to accelerate the convergence speed of model training. The CIoU Loss function, combining the three geometric measures of overlap area, center distance and aspect ratio, was adopted to reduce the occurrence of missed and false detection and improve detection precision. The experimental results showed that the inference time of a single image was reduced by 75% with the improved YOLOv5s algorithm; compared with that of the Faster R-CNN algorithm, real-time performance was effectively improved. Furthermore, the mAP value of the improved algorithm was increased by 5.80% compared with that of the original YOLOv5s, which indicates that using the CIoU Loss function had an obvious effect on reducing the missed detection and false detection of the original YOLOv5s. Moreover, the detection of small target obstacles of the improved algorithm was better than that of the Faster R-CNN. MDPI 2022-02-24 /pmc/articles/PMC8915062/ /pubmed/35270935 http://dx.doi.org/10.3390/s22051790 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xue, Jinlin
Cheng, Feng
Li, Yuqing
Song, Yue
Mao, Tingting
Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title_full Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title_fullStr Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title_full_unstemmed Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title_short Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering
title_sort detection of farmland obstacles based on an improved yolov5s algorithm by using ciou and anchor box scale clustering
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8915062/
https://www.ncbi.nlm.nih.gov/pubmed/35270935
http://dx.doi.org/10.3390/s22051790
work_keys_str_mv AT xuejinlin detectionoffarmlandobstaclesbasedonanimprovedyolov5salgorithmbyusingciouandanchorboxscaleclustering
AT chengfeng detectionoffarmlandobstaclesbasedonanimprovedyolov5salgorithmbyusingciouandanchorboxscaleclustering
AT liyuqing detectionoffarmlandobstaclesbasedonanimprovedyolov5salgorithmbyusingciouandanchorboxscaleclustering
AT songyue detectionoffarmlandobstaclesbasedonanimprovedyolov5salgorithmbyusingciouandanchorboxscaleclustering
AT maotingting detectionoffarmlandobstaclesbasedonanimprovedyolov5salgorithmbyusingciouandanchorboxscaleclustering