A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2
Disease and pest detection of grape foliage is essential for grape yield and quality. RGB image (RGBI), multispectral image (MSI), and thermal infrared image (TIRI) are widely used in the health detection of plants. In this study, we collected three types of grape foliage images with six common clas...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/24/5102 |
| _version_ | 1797500995509420032 |
|---|---|
| author | Rui Yang Xiangyu Lu Jing Huang Jun Zhou Jie Jiao Yufei Liu Fei Liu Baofeng Su Peiwen Gu |
| author_facet | Rui Yang Xiangyu Lu Jing Huang Jun Zhou Jie Jiao Yufei Liu Fei Liu Baofeng Su Peiwen Gu |
| author_sort | Rui Yang |
| collection | DOAJ |
| description | Disease and pest detection of grape foliage is essential for grape yield and quality. RGB image (RGBI), multispectral image (MSI), and thermal infrared image (TIRI) are widely used in the health detection of plants. In this study, we collected three types of grape foliage images with six common classes (anthracnose, downy mildew, leafhopper, mites, viral disease, and healthy) in the field. ShuffleNet V2 was used to build up detection models. According to the accuracy of RGBI, MSI, TIRI, and multi-source data concatenation (MDC) models, and a multi-source data fusion (MDF) decision-making method was proposed for improving the detection performance for grape foliage, aiming to enhance the decision-making for RGBI of grape foliage by fusing the MSI and TIRI. The results showed that 40% of the incorrect detection outputs were rectified using the MDF decision-making method. The overall accuracy of MDF model was 96.05%, which had improvements of 2.64%, 13.65%, and 27.79%, compared with the RGBI, MSI, and TIRI models using label smoothing, respectively. In addition, the MDF model was based on the lightweight network with 3.785 M total parameters and 0.362 G multiply-accumulate operations, which could be highly portable and easy to be applied. |
| first_indexed | 2024-03-10T03:11:54Z |
| format | Article |
| id | doaj.art-b8c9c98d6e584616807ef47e2fa313f5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:11:54Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b8c9c98d6e584616807ef47e2fa313f52023-11-23T10:24:50ZengMDPI AGRemote Sensing2072-42922021-12-011324510210.3390/rs13245102A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2Rui Yang0Xiangyu Lu1Jing Huang2Jun Zhou3Jie Jiao4Yufei Liu5Fei Liu6Baofeng Su7Peiwen Gu8College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, ChinaSchool of Agriculture, Ningxia University, Yinchuan 750021, ChinaDisease and pest detection of grape foliage is essential for grape yield and quality. RGB image (RGBI), multispectral image (MSI), and thermal infrared image (TIRI) are widely used in the health detection of plants. In this study, we collected three types of grape foliage images with six common classes (anthracnose, downy mildew, leafhopper, mites, viral disease, and healthy) in the field. ShuffleNet V2 was used to build up detection models. According to the accuracy of RGBI, MSI, TIRI, and multi-source data concatenation (MDC) models, and a multi-source data fusion (MDF) decision-making method was proposed for improving the detection performance for grape foliage, aiming to enhance the decision-making for RGBI of grape foliage by fusing the MSI and TIRI. The results showed that 40% of the incorrect detection outputs were rectified using the MDF decision-making method. The overall accuracy of MDF model was 96.05%, which had improvements of 2.64%, 13.65%, and 27.79%, compared with the RGBI, MSI, and TIRI models using label smoothing, respectively. In addition, the MDF model was based on the lightweight network with 3.785 M total parameters and 0.362 G multiply-accumulate operations, which could be highly portable and easy to be applied.https://www.mdpi.com/2072-4292/13/24/5102grape foliagedisease and pestdetectionmulti-source data fusionShuffleNet V2 |
| spellingShingle | Rui Yang Xiangyu Lu Jing Huang Jun Zhou Jie Jiao Yufei Liu Fei Liu Baofeng Su Peiwen Gu A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 Remote Sensing grape foliage disease and pest detection multi-source data fusion ShuffleNet V2 |
| title | A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 |
| title_full | A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 |
| title_fullStr | A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 |
| title_full_unstemmed | A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 |
| title_short | A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2 |
| title_sort | multi source data fusion decision making method for disease and pest detection of grape foliage based on shufflenet v2 |
| topic | grape foliage disease and pest detection multi-source data fusion ShuffleNet V2 |
| url | https://www.mdpi.com/2072-4292/13/24/5102 |
| work_keys_str_mv | AT ruiyang amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT xiangyulu amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT jinghuang amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT junzhou amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT jiejiao amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT yufeiliu amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT feiliu amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT baofengsu amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT peiwengu amultisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT ruiyang multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT xiangyulu multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT jinghuang multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT junzhou multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT jiejiao multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT yufeiliu multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT feiliu multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT baofengsu multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 AT peiwengu multisourcedatafusiondecisionmakingmethodfordiseaseandpestdetectionofgrapefoliagebasedonshufflenetv2 |