Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO
Currently, some intelligent devices are available to assist in the detection of imperfect wheat grains. However, the background of grain surface images acquired by intelligent devices is dense and complicated with overlapping particles, causing noise interferences in the detection of imperfect wheat...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Food Publishing Company
2024-12-01
|
| Series: | Shipin Kexue |
| Subjects: | |
| Online Access: | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-030.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539864681152512 |
|---|---|
| author | FAN Jiawei, WU Lan, YAN Jingjing |
| author_facet | FAN Jiawei, WU Lan, YAN Jingjing |
| author_sort | FAN Jiawei, WU Lan, YAN Jingjing |
| collection | DOAJ |
| description | Currently, some intelligent devices are available to assist in the detection of imperfect wheat grains. However, the background of grain surface images acquired by intelligent devices is dense and complicated with overlapping particles, causing noise interferences in the detection of imperfect wheat grains. To address the high missed detection rate of imperfect grains in target detection algorithms and to enhance the model detection speed, this study optimized the lightweight network model YOLOV4-Tiny. First, a small target detection layer was added to enhance the utilization of high semantic information. Then, the SENet attention mechanism optimized with exponential thinking was embedded to facilitated the design of an Enhanced Feature Extraction Network (Increase-FPN) in order to enhance the model’s ability to extract features of imperfect grains amidst complex backgrounds so that the detection accuracy could be improved and false negative rates reduced. At last, depthwise separable convolution was employed as the feature extraction method for the residual network of the backbone component to reduce the calculation of model parameters, optimize model deployment, and solve the issue of poor real-time performance. Experimental results demonstrated that the improved IDS-YOLO algorithm achieved a balance between detection speed and accuracy, with an average increase of 6.2% in mean average precision (mAP) when compared with other benchmark algorithms. The frames per second (FPS) value was 88.03, meeting the real-time detection requirements, and the parameter size of the improved model was only 5.51 MB. |
| format | Article |
| id | doaj-art-fa09e67bfb654bac94dba8b52113cda0 |
| institution | Kabale University |
| issn | 1002-6630 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | China Food Publishing Company |
| record_format | Article |
| series | Shipin Kexue |
| spelling | doaj-art-fa09e67bfb654bac94dba8b52113cda02025-02-05T09:07:53ZengChina Food Publishing CompanyShipin Kexue1002-66302024-12-01452326827710.7506/spkx1002-6630-20240519-115Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLOFAN Jiawei, WU Lan, YAN Jingjing0(1. College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China;2. College of Electromechanical Engineering, Henan University of Technology, Zhengzhou 450001, China)Currently, some intelligent devices are available to assist in the detection of imperfect wheat grains. However, the background of grain surface images acquired by intelligent devices is dense and complicated with overlapping particles, causing noise interferences in the detection of imperfect wheat grains. To address the high missed detection rate of imperfect grains in target detection algorithms and to enhance the model detection speed, this study optimized the lightweight network model YOLOV4-Tiny. First, a small target detection layer was added to enhance the utilization of high semantic information. Then, the SENet attention mechanism optimized with exponential thinking was embedded to facilitated the design of an Enhanced Feature Extraction Network (Increase-FPN) in order to enhance the model’s ability to extract features of imperfect grains amidst complex backgrounds so that the detection accuracy could be improved and false negative rates reduced. At last, depthwise separable convolution was employed as the feature extraction method for the residual network of the backbone component to reduce the calculation of model parameters, optimize model deployment, and solve the issue of poor real-time performance. Experimental results demonstrated that the improved IDS-YOLO algorithm achieved a balance between detection speed and accuracy, with an average increase of 6.2% in mean average precision (mAP) when compared with other benchmark algorithms. The frames per second (FPS) value was 88.03, meeting the real-time detection requirements, and the parameter size of the improved model was only 5.51 MB.https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-030.pdfreal-time detection; imperfect wheat grains; small target detection; grain storage quality; deep learning |
| spellingShingle | FAN Jiawei, WU Lan, YAN Jingjing Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO Shipin Kexue real-time detection; imperfect wheat grains; small target detection; grain storage quality; deep learning |
| title | Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO |
| title_full | Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO |
| title_fullStr | Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO |
| title_full_unstemmed | Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO |
| title_short | Real-time Detection of Imperfect Wheat Grains on Wheat Pile Surface Based on IDS-YOLO |
| title_sort | real time detection of imperfect wheat grains on wheat pile surface based on ids yolo |
| topic | real-time detection; imperfect wheat grains; small target detection; grain storage quality; deep learning |
| url | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-030.pdf |
| work_keys_str_mv | AT fanjiaweiwulanyanjingjing realtimedetectionofimperfectwheatgrainsonwheatpilesurfacebasedonidsyolo |