An approach for density monitoring of brown planthopper population in simulated paddy fields
| Autor: | Sarin Watcharabutsarakham, Wantana Sriratanasak, Ithipan Methasate, Wasin Sinthupinyo, Nattachai Watcharapinchai |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
0106 biological sciences
Background subtraction education.field_of_study Contextual image classification biology Computer science business.industry Population ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing 04 agricultural and veterinary sciences Color space biology.organism_classification 01 natural sciences Support vector machine 040103 agronomy & agriculture 0401 agriculture forestry and fisheries Paddy field Computer vision Brown planthopper Artificial intelligence education business 010606 plant biology & botany |
| Zdroj: | 2016 13th International Joint Conference on Computer Science and Software Engineering (JCSSE). |
| DOI: | 10.1109/jcsse.2016.7748922 |
| Popis: | This paper presents an image process for monitoring brown planthopper (BPH) in rice fields. Our system consists of a mobile application and online services. The smart phone is used to capture images of BPH which was adhered on the rice stem. We applied an image classification for counting and identify stages of BPH. In the first step, the region of BPH is located by the SVM-based background subtraction. For each area was described with GLCM features, that varies both angles and color spaces. In the second step, the BPH life stages are identified as nymphal form, macropterous form and brachepterous form. By local features, the classifier was modeled with support vector machines. As a result, this approach achieves an 83% accuracy of BPH stage classification on a paddy field environment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|