GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection
Fruits require different planting techniques at different growth stages. Traditionally, the maturity stage of fruit is judged visually, which is time-consuming and labor-intensive. Fruits differ in size and color, and sometimes leaves or branches occult some of fruits, limiting automatic detection o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-01-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023011?viewType=HTML |
| _version_ | 1811237757376266240 |
|---|---|
| author | Mei-Ling Huang Yi-Shan Wu |
| author_facet | Mei-Ling Huang Yi-Shan Wu |
| author_sort | Mei-Ling Huang |
| collection | DOAJ |
| description | Fruits require different planting techniques at different growth stages. Traditionally, the maturity stage of fruit is judged visually, which is time-consuming and labor-intensive. Fruits differ in size and color, and sometimes leaves or branches occult some of fruits, limiting automatic detection of growth stages in a real environment. Based on YOLOV4-Tiny, this study proposes a GCS-YOLOV4-Tiny model by (1) adding squeeze and excitation (SE) and the spatial pyramid pooling (SPP) modules to improve the accuracy of the model and (2) using the group convolution to reduce the size of the model and finally achieve faster detection speed. The proposed GCS-YOLOV4-Tiny model was executed on three public fruit datasets. Results have shown that GCS-YOLOV4-Tiny has favorable performance on mAP, Recall, F1-Score and Average IoU on Mango YOLO and Rpi-Tomato datasets. In addition, with the smallest model size of 20.70 MB, the mAP, Recall, F1-score, Precision and Average IoU of GCS-YOLOV4-Tiny achieve 93.42 ± 0.44, 91.00 ± 1.87, 90.80 ± 2.59, 90.80 ± 2.77 and 76.94 ± 1.35%, respectively, on F. margarita dataset. The detection results outperform the state-of-the-art YOLOV4-Tiny model with a 17.45% increase in mAP and a 13.80% increase in F1-score. The proposed model provides an effective and efficient performance to detect different growth stages of fruits and can be extended for different fruits and crops for object or disease detections. |
| first_indexed | 2024-04-12T12:29:51Z |
| format | Article |
| id | doaj.art-81e9472f89224816b541d2c1c5db1d2f |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-12T12:29:51Z |
| publishDate | 2023-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-81e9472f89224816b541d2c1c5db1d2f2022-12-22T03:33:04ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-0124126810.3934/mbe.2023011GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detectionMei-Ling Huang 0Yi-Shan Wu1Department of Industrial Engineering & Management, National Chin-Yi University of Technology, Taichung, TaiwanDepartment of Industrial Engineering & Management, National Chin-Yi University of Technology, Taichung, TaiwanFruits require different planting techniques at different growth stages. Traditionally, the maturity stage of fruit is judged visually, which is time-consuming and labor-intensive. Fruits differ in size and color, and sometimes leaves or branches occult some of fruits, limiting automatic detection of growth stages in a real environment. Based on YOLOV4-Tiny, this study proposes a GCS-YOLOV4-Tiny model by (1) adding squeeze and excitation (SE) and the spatial pyramid pooling (SPP) modules to improve the accuracy of the model and (2) using the group convolution to reduce the size of the model and finally achieve faster detection speed. The proposed GCS-YOLOV4-Tiny model was executed on three public fruit datasets. Results have shown that GCS-YOLOV4-Tiny has favorable performance on mAP, Recall, F1-Score and Average IoU on Mango YOLO and Rpi-Tomato datasets. In addition, with the smallest model size of 20.70 MB, the mAP, Recall, F1-score, Precision and Average IoU of GCS-YOLOV4-Tiny achieve 93.42 ± 0.44, 91.00 ± 1.87, 90.80 ± 2.59, 90.80 ± 2.77 and 76.94 ± 1.35%, respectively, on F. margarita dataset. The detection results outperform the state-of-the-art YOLOV4-Tiny model with a 17.45% increase in mAP and a 13.80% increase in F1-score. The proposed model provides an effective and efficient performance to detect different growth stages of fruits and can be extended for different fruits and crops for object or disease detections.https://www.aimspress.com/article/doi/10.3934/mbe.2023011?viewType=HTMLobject detectionyolov4-tinysesppgroup convolution |
| spellingShingle | Mei-Ling Huang Yi-Shan Wu GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection Mathematical Biosciences and Engineering object detection yolov4-tiny se spp group convolution |
| title | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection |
| title_full | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection |
| title_fullStr | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection |
| title_full_unstemmed | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection |
| title_short | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection |
| title_sort | gcs yolov4 tiny a lightweight group convolution network for multi stage fruit detection |
| topic | object detection yolov4-tiny se spp group convolution |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023011?viewType=HTML |
| work_keys_str_mv | AT meilinghuang gcsyolov4tinyalightweightgroupconvolutionnetworkformultistagefruitdetection AT yishanwu gcsyolov4tinyalightweightgroupconvolutionnetworkformultistagefruitdetection |