Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement
In-field in situ droplet deposition digitization is beneficial for obtaining feedback on spraying performance and precise spray control, the cost-effectiveness of the measurement system is crucial to its scalable application. However, the limitations of camera performance in low-cost imaging systems...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/14/1/106 |
| _version_ | 1797340220109094912 |
|---|---|
| author | Jian Liu Shihui Yu Xuemei Liu Guohang Lu Zhenbo Xin Jin Yuan |
| author_facet | Jian Liu Shihui Yu Xuemei Liu Guohang Lu Zhenbo Xin Jin Yuan |
| author_sort | Jian Liu |
| collection | DOAJ |
| description | In-field in situ droplet deposition digitization is beneficial for obtaining feedback on spraying performance and precise spray control, the cost-effectiveness of the measurement system is crucial to its scalable application. However, the limitations of camera performance in low-cost imaging systems, coupled with dense spray droplets and a complex imaging environment, result in blurred and low-resolution images of the deposited droplets, which creates challenges in obtaining accurate measurements. This paper proposes a Droplet Super-Resolution Semantic Segmentation (DSRSS) model and a Multi-Adhesion Concave Segmentation (MACS) algorithm to address the accurate segmentation problem in low-quality droplet deposition images, and achieve a precise and efficient multi-parameter measurement of droplet deposition. Firstly, a droplet deposition image dataset (DDID) is constructed by capturing high-definition droplet images and using image reconstruction methods. Then, a lightweight DSRSS model combined with anti-blurring and super-resolution semantic segmentation is proposed to achieve semantic segmentation of deposited droplets and super-resolution reconstruction of segmentation masks. The weighted IoU (WIoU) loss function is used to improve the segmented independence of droplets, and a comprehensive evaluation criterion containing six sub-items is used for parameter optimization. Finally, the MACS algorithm continues to segment the remained adhesive droplets processed by the DSRSS model and corrects the bias of the individual droplet regions by regression. The experiments show that when the two weight parameters α and β in WIoU are 0.775 and 0.225, respectively, the droplet segmentation independence rate of DSRSS on the DDID reaches 0.998, and the IoU reaches 0.973. The MACS algorithm reduces the droplet adhesion rate in images with a coverage rate of more than 30% by 15.7%, and the correction function reduces the coverage error of model segmentation by 3.54%. The parameters of the DSRSS model are less than 1 M, making it possible to run it on embedded platforms. The proposed approach improves the accuracy of spray measurement using low-quality droplet deposition image and will help to scale-up of fast spray measurements in the field. |
| first_indexed | 2024-03-08T09:59:51Z |
| format | Article |
| id | doaj.art-709ed87093244460b887ea0bba07c5bc |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-08T09:59:51Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-709ed87093244460b887ea0bba07c5bc2024-01-29T13:40:18ZengMDPI AGAgriculture2077-04722024-01-0114110610.3390/agriculture14010106Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying MeasurementJian Liu0Shihui Yu1Xuemei Liu2Guohang Lu3Zhenbo Xin4Jin Yuan5College of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaIn-field in situ droplet deposition digitization is beneficial for obtaining feedback on spraying performance and precise spray control, the cost-effectiveness of the measurement system is crucial to its scalable application. However, the limitations of camera performance in low-cost imaging systems, coupled with dense spray droplets and a complex imaging environment, result in blurred and low-resolution images of the deposited droplets, which creates challenges in obtaining accurate measurements. This paper proposes a Droplet Super-Resolution Semantic Segmentation (DSRSS) model and a Multi-Adhesion Concave Segmentation (MACS) algorithm to address the accurate segmentation problem in low-quality droplet deposition images, and achieve a precise and efficient multi-parameter measurement of droplet deposition. Firstly, a droplet deposition image dataset (DDID) is constructed by capturing high-definition droplet images and using image reconstruction methods. Then, a lightweight DSRSS model combined with anti-blurring and super-resolution semantic segmentation is proposed to achieve semantic segmentation of deposited droplets and super-resolution reconstruction of segmentation masks. The weighted IoU (WIoU) loss function is used to improve the segmented independence of droplets, and a comprehensive evaluation criterion containing six sub-items is used for parameter optimization. Finally, the MACS algorithm continues to segment the remained adhesive droplets processed by the DSRSS model and corrects the bias of the individual droplet regions by regression. The experiments show that when the two weight parameters α and β in WIoU are 0.775 and 0.225, respectively, the droplet segmentation independence rate of DSRSS on the DDID reaches 0.998, and the IoU reaches 0.973. The MACS algorithm reduces the droplet adhesion rate in images with a coverage rate of more than 30% by 15.7%, and the correction function reduces the coverage error of model segmentation by 3.54%. The parameters of the DSRSS model are less than 1 M, making it possible to run it on embedded platforms. The proposed approach improves the accuracy of spray measurement using low-quality droplet deposition image and will help to scale-up of fast spray measurements in the field.https://www.mdpi.com/2077-0472/14/1/106droplet deposition measurementimage processingsuper-resolutionsemantic segmentation |
| spellingShingle | Jian Liu Shihui Yu Xuemei Liu Guohang Lu Zhenbo Xin Jin Yuan Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement Agriculture droplet deposition measurement image processing super-resolution semantic segmentation |
| title | Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement |
| title_full | Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement |
| title_fullStr | Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement |
| title_full_unstemmed | Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement |
| title_short | Super-Resolution Semantic Segmentation of Droplet Deposition Image for Low-Cost Spraying Measurement |
| title_sort | super resolution semantic segmentation of droplet deposition image for low cost spraying measurement |
| topic | droplet deposition measurement image processing super-resolution semantic segmentation |
| url | https://www.mdpi.com/2077-0472/14/1/106 |
| work_keys_str_mv | AT jianliu superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement AT shihuiyu superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement AT xuemeiliu superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement AT guohanglu superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement AT zhenboxin superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement AT jinyuan superresolutionsemanticsegmentationofdropletdepositionimageforlowcostsprayingmeasurement |