Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision
The approach of dynamic tracking and counting for obscured citrus based on machine vision is a key element to realizing orchard yield measurement and smart orchard production management. In this study, focusing on citrus images and dynamic videos in a modern planting mode, we proposed the citrus det...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/14/3/1136 |
_version_ | 1797319044620091392 |
---|---|
author | Yuliang Feng Wei Ma Yu Tan Hao Yan Jianping Qian Zhiwei Tian Ang Gao |
author_facet | Yuliang Feng Wei Ma Yu Tan Hao Yan Jianping Qian Zhiwei Tian Ang Gao |
author_sort | Yuliang Feng |
collection | DOAJ |
description | The approach of dynamic tracking and counting for obscured citrus based on machine vision is a key element to realizing orchard yield measurement and smart orchard production management. In this study, focusing on citrus images and dynamic videos in a modern planting mode, we proposed the citrus detection and dynamic counting method based on the lightweight target detection network YOLOv7-tiny, Kalman filter tracking, and the Hungarian algorithm. The YOLOv7-tiny model was used to detect the citrus in the video, and the Kalman filter algorithm was used for the predictive tracking of the detected fruits. In order to realize optimal matching, the Hungarian algorithm was improved in terms of Euclidean distance and overlap matching and the two stages life filter was added; finally, the drawing lines counting strategy was proposed. ln this study, the detection performance, tracking performance, and counting effect of the algorithms are tested respectively; the results showed that the average detection accuracy of the YOLOv7-tiny model reached 97.23%, the detection accuracy in orchard dynamic detection reached 95.12%, the multi-target tracking accuracy and the precision of the improved dynamic counting algorithm reached 67.14% and 74.65% respectively, which were higher than those of the pre-improvement algorithm, and the average counting accuracy of the improved algorithm reached 81.02%. The method was proposed to effectively help fruit farmers grasp the number of citruses and provide a technical reference for the study of yield measurement in modernized citrus orchards and a scientific decision-making basis for the intelligent management of orchards. |
first_indexed | 2024-03-08T04:01:05Z |
format | Article |
id | doaj.art-eb939dd185d34be686536bcd7107d935 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-08T04:01:05Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-eb939dd185d34be686536bcd7107d9352024-02-09T15:07:55ZengMDPI AGApplied Sciences2076-34172024-01-01143113610.3390/app14031136Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine VisionYuliang Feng0Wei Ma1Yu Tan2Hao Yan3Jianping Qian4Zhiwei Tian5Ang Gao6College of Engineering, China Agricultural University, Beijing 100083, ChinaInstitute of Urban Agriculture, Chinese Academy of Agriculture Sciences, Chengdu 610213, ChinaCollege of Engineering, China Agricultural University, Beijing 100083, ChinaCollege of Engineering, China Agricultural University, Beijing 100083, ChinaInstitute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaInstitute of Urban Agriculture, Chinese Academy of Agriculture Sciences, Chengdu 610213, ChinaCollege of Mechanical and Electrical Engineering, Shandong Agricultural University, Taian 271018, ChinaThe approach of dynamic tracking and counting for obscured citrus based on machine vision is a key element to realizing orchard yield measurement and smart orchard production management. In this study, focusing on citrus images and dynamic videos in a modern planting mode, we proposed the citrus detection and dynamic counting method based on the lightweight target detection network YOLOv7-tiny, Kalman filter tracking, and the Hungarian algorithm. The YOLOv7-tiny model was used to detect the citrus in the video, and the Kalman filter algorithm was used for the predictive tracking of the detected fruits. In order to realize optimal matching, the Hungarian algorithm was improved in terms of Euclidean distance and overlap matching and the two stages life filter was added; finally, the drawing lines counting strategy was proposed. ln this study, the detection performance, tracking performance, and counting effect of the algorithms are tested respectively; the results showed that the average detection accuracy of the YOLOv7-tiny model reached 97.23%, the detection accuracy in orchard dynamic detection reached 95.12%, the multi-target tracking accuracy and the precision of the improved dynamic counting algorithm reached 67.14% and 74.65% respectively, which were higher than those of the pre-improvement algorithm, and the average counting accuracy of the improved algorithm reached 81.02%. The method was proposed to effectively help fruit farmers grasp the number of citruses and provide a technical reference for the study of yield measurement in modernized citrus orchards and a scientific decision-making basis for the intelligent management of orchards.https://www.mdpi.com/2076-3417/14/3/1136smart orchardautomatic detectiontarget trackingdynamic counting |
spellingShingle | Yuliang Feng Wei Ma Yu Tan Hao Yan Jianping Qian Zhiwei Tian Ang Gao Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision Applied Sciences smart orchard automatic detection target tracking dynamic counting |
title | Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision |
title_full | Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision |
title_fullStr | Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision |
title_full_unstemmed | Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision |
title_short | Approach of Dynamic Tracking and Counting for Obscured Citrus in Smart Orchard Based on Machine Vision |
title_sort | approach of dynamic tracking and counting for obscured citrus in smart orchard based on machine vision |
topic | smart orchard automatic detection target tracking dynamic counting |
url | https://www.mdpi.com/2076-3417/14/3/1136 |
work_keys_str_mv | AT yuliangfeng approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT weima approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT yutan approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT haoyan approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT jianpingqian approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT zhiweitian approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision AT anggao approachofdynamictrackingandcountingforobscuredcitrusinsmartorchardbasedonmachinevision |