Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network
Achieving rapid and accurate localization of winter jujubes in trees is an indispensable step for the development of automated harvesting equipment. Unlike larger fruits such as apples, winter jujube is smaller with a higher density and serious occlusion, which obliges higher requirements for the id...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/19/4833 |
| _version_ | 1797477171065782272 |
|---|---|
| author | Zhouzhou Zheng Yaohua Hu Yichen Qiao Xing Hu Yuxiang Huang |
| author_facet | Zhouzhou Zheng Yaohua Hu Yichen Qiao Xing Hu Yuxiang Huang |
| author_sort | Zhouzhou Zheng |
| collection | DOAJ |
| description | Achieving rapid and accurate localization of winter jujubes in trees is an indispensable step for the development of automated harvesting equipment. Unlike larger fruits such as apples, winter jujube is smaller with a higher density and serious occlusion, which obliges higher requirements for the identification and positioning. To address the issues, an accurate winter jujube localization method using improved YOLOX-Nano network was proposed. First, a winter jujube dataset containing a variety of complex scenes, such as backlit, occluded, and different fields of view, was established to train our model. Then, to improve its feature learning ability, an attention feature enhancement module was designed to strengthen useful features and weaken irrelevant features. Moreover, DIoU loss was used to optimize training and obtain a more robust model. A 3D positioning error experiment and a comparative experiment were conducted to validate the effectiveness of our method. The comparative experiment results showed that our method outperforms the state-of-the-art object detection networks and the lightweight networks. Specifically, the precision, recall, and AP of our method reached 93.08%, 87.83%, and 95.56%, respectively. The positioning error experiment results showed that the average positioning errors of the X, Y, Z coordinate axis were 5.8 mm, 5.4 mm, and 3.8 mm, respectively. The model size is only 4.47 MB and can meet the requirements of winter jujube picking for detection accuracy, positioning errors, and the deployment of embedded systems. |
| first_indexed | 2024-03-09T21:13:50Z |
| format | Article |
| id | doaj.art-44a87afd334e45cd9dd69face9437e12 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:13:50Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-44a87afd334e45cd9dd69face9437e122023-11-23T21:39:29ZengMDPI AGRemote Sensing2072-42922022-09-011419483310.3390/rs14194833Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano NetworkZhouzhou Zheng0Yaohua Hu1Yichen Qiao2Xing Hu3Yuxiang Huang4College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaCollege of Optical, Mechanical and Electrical Engineering, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaAchieving rapid and accurate localization of winter jujubes in trees is an indispensable step for the development of automated harvesting equipment. Unlike larger fruits such as apples, winter jujube is smaller with a higher density and serious occlusion, which obliges higher requirements for the identification and positioning. To address the issues, an accurate winter jujube localization method using improved YOLOX-Nano network was proposed. First, a winter jujube dataset containing a variety of complex scenes, such as backlit, occluded, and different fields of view, was established to train our model. Then, to improve its feature learning ability, an attention feature enhancement module was designed to strengthen useful features and weaken irrelevant features. Moreover, DIoU loss was used to optimize training and obtain a more robust model. A 3D positioning error experiment and a comparative experiment were conducted to validate the effectiveness of our method. The comparative experiment results showed that our method outperforms the state-of-the-art object detection networks and the lightweight networks. Specifically, the precision, recall, and AP of our method reached 93.08%, 87.83%, and 95.56%, respectively. The positioning error experiment results showed that the average positioning errors of the X, Y, Z coordinate axis were 5.8 mm, 5.4 mm, and 3.8 mm, respectively. The model size is only 4.47 MB and can meet the requirements of winter jujube picking for detection accuracy, positioning errors, and the deployment of embedded systems.https://www.mdpi.com/2072-4292/14/19/4833winter jujubesYOLOX-Nanoattention feature enhancement3D positioningDIoU loss |
| spellingShingle | Zhouzhou Zheng Yaohua Hu Yichen Qiao Xing Hu Yuxiang Huang Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network Remote Sensing winter jujubes YOLOX-Nano attention feature enhancement 3D positioning DIoU loss |
| title | Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network |
| title_full | Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network |
| title_fullStr | Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network |
| title_full_unstemmed | Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network |
| title_short | Real-Time Detection of Winter Jujubes Based on Improved YOLOX-Nano Network |
| title_sort | real time detection of winter jujubes based on improved yolox nano network |
| topic | winter jujubes YOLOX-Nano attention feature enhancement 3D positioning DIoU loss |
| url | https://www.mdpi.com/2072-4292/14/19/4833 |
| work_keys_str_mv | AT zhouzhouzheng realtimedetectionofwinterjujubesbasedonimprovedyoloxnanonetwork AT yaohuahu realtimedetectionofwinterjujubesbasedonimprovedyoloxnanonetwork AT yichenqiao realtimedetectionofwinterjujubesbasedonimprovedyoloxnanonetwork AT xinghu realtimedetectionofwinterjujubesbasedonimprovedyoloxnanonetwork AT yuxianghuang realtimedetectionofwinterjujubesbasedonimprovedyoloxnanonetwork |