Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis
The severity of rice blast and its impacts on rice yield are closely related to the inoculum quantity of <i>Magnaporthe oryzae</i>, and automatic detection of the pathogen spores in microscopic images can provide a rapid and effective way to quantify pathogen inoculum. Traditional spore...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/14/2/290 |
| _version_ | 1827344430845132800 |
|---|---|
| author | Huiru Zhou Qiang Lai Qiong Huang Dingzhou Cai Dong Huang Boming Wu |
| author_facet | Huiru Zhou Qiang Lai Qiong Huang Dingzhou Cai Dong Huang Boming Wu |
| author_sort | Huiru Zhou |
| collection | DOAJ |
| description | The severity of rice blast and its impacts on rice yield are closely related to the inoculum quantity of <i>Magnaporthe oryzae</i>, and automatic detection of the pathogen spores in microscopic images can provide a rapid and effective way to quantify pathogen inoculum. Traditional spore detection methods mostly rely on manual feature extraction and shallow machine learning models, and are mostly designed for the indoor counting of a single spore class, which cannot handle the interference of impurity particles in the field. This study achieved automatic detection of rice blast fungus spores in the mixture with other fungal spores and rice pollens commonly encountered under field conditions by using deep learning based object detection techniques. First, 8959 microscopic images of a single spore class and 1450 microscopic images of mixed spore classes, including the rice blast fungus spores and four common impurity particles, were collected and labelled to form the benchmark dataset. Then, Faster R-CNN, Cascade R-CNN and YOLOv3 were used as the main detection frameworks, and multiple convolutional neural networks were used as the backbone networks in training of nine object detection algorithms. The results showed that the detection performance of YOLOv3_DarkNet53 is superior to the other eight algorithms, and achieved 98.0% mean average precision (intersection over union > 0.5) and an average speed of 36.4 frames per second. This study demonstrated the enormous application potential of deep object detection algorithms in automatic detection and quantification of rice blast fungus spores. |
| first_indexed | 2024-03-07T22:47:07Z |
| format | Article |
| id | doaj.art-f601614f942f44faae9b10790a1fda56 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-07T22:47:07Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-f601614f942f44faae9b10790a1fda562024-02-23T15:03:49ZengMDPI AGAgriculture2077-04722024-02-0114229010.3390/agriculture14020290Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative AnalysisHuiru Zhou0Qiang Lai1Qiong Huang2Dingzhou Cai3Dong Huang4Boming Wu5College of Plant Protection, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Plant Protection, China Agricultural University, Beijing 100193, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Plant Protection, China Agricultural University, Beijing 100193, ChinaThe severity of rice blast and its impacts on rice yield are closely related to the inoculum quantity of <i>Magnaporthe oryzae</i>, and automatic detection of the pathogen spores in microscopic images can provide a rapid and effective way to quantify pathogen inoculum. Traditional spore detection methods mostly rely on manual feature extraction and shallow machine learning models, and are mostly designed for the indoor counting of a single spore class, which cannot handle the interference of impurity particles in the field. This study achieved automatic detection of rice blast fungus spores in the mixture with other fungal spores and rice pollens commonly encountered under field conditions by using deep learning based object detection techniques. First, 8959 microscopic images of a single spore class and 1450 microscopic images of mixed spore classes, including the rice blast fungus spores and four common impurity particles, were collected and labelled to form the benchmark dataset. Then, Faster R-CNN, Cascade R-CNN and YOLOv3 were used as the main detection frameworks, and multiple convolutional neural networks were used as the backbone networks in training of nine object detection algorithms. The results showed that the detection performance of YOLOv3_DarkNet53 is superior to the other eight algorithms, and achieved 98.0% mean average precision (intersection over union > 0.5) and an average speed of 36.4 frames per second. This study demonstrated the enormous application potential of deep object detection algorithms in automatic detection and quantification of rice blast fungus spores.https://www.mdpi.com/2077-0472/14/2/290rice blastfungal spore detectionobject detectiondeep learningdisease monitoring |
| spellingShingle | Huiru Zhou Qiang Lai Qiong Huang Dingzhou Cai Dong Huang Boming Wu Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis Agriculture rice blast fungal spore detection object detection deep learning disease monitoring |
| title | Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis |
| title_full | Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis |
| title_fullStr | Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis |
| title_full_unstemmed | Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis |
| title_short | Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis |
| title_sort | automatic detection of rice blast fungus spores by deep learning based object detection models benchmarks and quantitative analysis |
| topic | rice blast fungal spore detection object detection deep learning disease monitoring |
| url | https://www.mdpi.com/2077-0472/14/2/290 |
| work_keys_str_mv | AT huiruzhou automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis AT qianglai automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis AT qionghuang automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis AT dingzhoucai automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis AT donghuang automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis AT bomingwu automaticdetectionofriceblastfungussporesbydeeplearningbasedobjectdetectionmodelsbenchmarksandquantitativeanalysis |