A methodology for detection and localization of fruits in apples orchards from aerial images.
Abstract. Computer vision methods based on convolutional neural networks (CNNs) have presented promising results on image-based fruit detection at ground-level for different crops. However, the integration of the detections found in different images, allowing accurate fruit counting and yield prediction, have received less attention. This work presents a methodology for automated fruit counting employing aerial-images. It includes algorithms based on multiple view geometry to perform fruits tracking, not just avoiding double counting but also locating the fruits in the 3-D space. Preliminary assessments show correlations above 0.8 between fruit counting and true yield for apples. The annotated dataset employed on CNN training is publicly available.
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Anais e Proceedings de eventos biblioteca |
| Language: | Ingles English |
| Published: |
2021-11-26
|
| Subjects: | Redes neurais, Contagem automática de frutas, Detecção de maçãs, Convolutional neural networks, Fruit detection, Maçã, Neural networks, Apples, |
| Online Access: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1136667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract. Computer vision methods based on convolutional neural networks (CNNs) have presented promising results on image-based fruit detection at ground-level for different crops. However, the integration of the detections found in different images, allowing accurate fruit counting and yield prediction, have received less attention. This work presents a methodology for automated fruit counting employing aerial-images. It includes algorithms based on multiple view geometry to perform fruits tracking, not just avoiding double counting but also locating the fruits in the 3-D space. Preliminary assessments show correlations above 0.8 between fruit counting and true yield for apples. The annotated dataset employed on CNN training is publicly available. |
|---|