Development of an automatic monitoring system for rice light-trap pests based on machine vision
Monitoring pest populations in paddy fields is important to effectively implement integrated pest management. Light traps are widely used to monitor field pests all over the world. Most conventional light traps still involve manual identification of target pests from lots of trapped insects, which i...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-10-01
|
| Series: | Journal of Integrative Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095311920631689 |
| _version_ | 1819065674565156864 |
|---|---|
| author | Qing YAO Jin FENG Jian TANG Wei-gen XU Xu-hua ZHU Bao-jun YANG Jun LÜ Yi-ze XIE Bo YAO Shu-zhen WU Nai-yang KUAI Li-jun WANG |
| author_facet | Qing YAO Jin FENG Jian TANG Wei-gen XU Xu-hua ZHU Bao-jun YANG Jun LÜ Yi-ze XIE Bo YAO Shu-zhen WU Nai-yang KUAI Li-jun WANG |
| author_sort | Qing YAO |
| collection | DOAJ |
| description | Monitoring pest populations in paddy fields is important to effectively implement integrated pest management. Light traps are widely used to monitor field pests all over the world. Most conventional light traps still involve manual identification of target pests from lots of trapped insects, which is time-consuming, labor-intensive and error-prone, especially in pest peak periods. In this paper, we developed an automatic monitoring system for rice light-trap pests based on machine vision. This system is composed of an intelligent light trap, a computer or mobile phone client platform and a cloud server. The light trap firstly traps, kills and disperses insects, then collects images of trapped insects and sends each image to the cloud server. Five target pests in images are automatically identified and counted by pest identification models loaded in the server. To avoid light-trap insects piling up, a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects. There was a close correlation (r=0.92) between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap. Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system. |
| first_indexed | 2024-12-21T15:50:13Z |
| format | Article |
| id | doaj.art-e77aaa30ea484f69a4373a1bc3e8e352 |
| institution | Directory Open Access Journal |
| issn | 2095-3119 |
| language | English |
| last_indexed | 2024-12-21T15:50:13Z |
| publishDate | 2020-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Integrative Agriculture |
| spelling | doaj.art-e77aaa30ea484f69a4373a1bc3e8e3522022-12-21T18:58:15ZengElsevierJournal of Integrative Agriculture2095-31192020-10-01191025002513Development of an automatic monitoring system for rice light-trap pests based on machine visionQing YAO0Jin FENG1Jian TANG2Wei-gen XU3Xu-hua ZHU4Bao-jun YANG5Jun LÜ6Yi-ze XIE7Bo YAO8Shu-zhen WU9Nai-yang KUAI10Li-jun WANG11School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.China; Correspondence YAO QingSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.ChinaState Key Laboratory of Rice Biology, China National Rice Research Institute, Hangzhou 310006, P.R.China; Correspondence TANG JianPlant Protection, Quarantine and Pesticide Management Station of Zhejiang, Hangzhou 310020, P.R.ChinaZhejiang Top Cloud-agri Technology Co., Ltd., Hangzhou 310015, P.R.ChinaState Key Laboratory of Rice Biology, China National Rice Research Institute, Hangzhou 310006, P.R.ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.ChinaAgricultural Technology Extension Center of Shangyu, Shaoxing 312300, P.R.ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.ChinaAgricultural Technology Extension Center of Keerqin, Keerqin 137713, P.R.ChinaMonitoring pest populations in paddy fields is important to effectively implement integrated pest management. Light traps are widely used to monitor field pests all over the world. Most conventional light traps still involve manual identification of target pests from lots of trapped insects, which is time-consuming, labor-intensive and error-prone, especially in pest peak periods. In this paper, we developed an automatic monitoring system for rice light-trap pests based on machine vision. This system is composed of an intelligent light trap, a computer or mobile phone client platform and a cloud server. The light trap firstly traps, kills and disperses insects, then collects images of trapped insects and sends each image to the cloud server. Five target pests in images are automatically identified and counted by pest identification models loaded in the server. To avoid light-trap insects piling up, a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects. There was a close correlation (r=0.92) between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap. Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.http://www.sciencedirect.com/science/article/pii/S2095311920631689automatic monitoring systemlight traprice pestmachine visionimage processingconvolutional neural network |
| spellingShingle | Qing YAO Jin FENG Jian TANG Wei-gen XU Xu-hua ZHU Bao-jun YANG Jun LÜ Yi-ze XIE Bo YAO Shu-zhen WU Nai-yang KUAI Li-jun WANG Development of an automatic monitoring system for rice light-trap pests based on machine vision Journal of Integrative Agriculture automatic monitoring system light trap rice pest machine vision image processing convolutional neural network |
| title | Development of an automatic monitoring system for rice light-trap pests based on machine vision |
| title_full | Development of an automatic monitoring system for rice light-trap pests based on machine vision |
| title_fullStr | Development of an automatic monitoring system for rice light-trap pests based on machine vision |
| title_full_unstemmed | Development of an automatic monitoring system for rice light-trap pests based on machine vision |
| title_short | Development of an automatic monitoring system for rice light-trap pests based on machine vision |
| title_sort | development of an automatic monitoring system for rice light trap pests based on machine vision |
| topic | automatic monitoring system light trap rice pest machine vision image processing convolutional neural network |
| url | http://www.sciencedirect.com/science/article/pii/S2095311920631689 |
| work_keys_str_mv | AT qingyao developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT jinfeng developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT jiantang developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT weigenxu developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT xuhuazhu developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT baojunyang developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT junlu developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT yizexie developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT boyao developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT shuzhenwu developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT naiyangkuai developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision AT lijunwang developmentofanautomaticmonitoringsystemforricelighttrappestsbasedonmachinevision |