Grapevine buds detection and localization in 3D space based on Structure from Motion and 2D image classification
| Autor: | Humberto Miatello, Diego Sebastián Pérez, Facundo Bromberg, Carlos Ariel Díaz |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0106 biological sciences
DBSCAN General Computer Science Computer science Point cloud 02 engineering and technology 01 natural sciences k-nearest neighbors algorithm 0202 electrical engineering electronic engineering information engineering Structure from motion Contextual image classification Pixel business.industry GRAPEVINE BUD DETECTION General Engineering Pattern recognition COMPUTER VISION PRECISION VITICULTURE Ciencias de la Computación Ciencias de la Computación e Información RGB color model 020201 artificial intelligence & image processing Artificial intelligence business Classifier (UML) CIENCIAS NATURALES Y EXACTAS 010606 plant biology & botany |
| Zdroj: | Computers in Industry. 99:303-312 |
| ISSN: | 0166-3615 |
| DOI: | 10.1016/j.compind.2018.03.033 |
| Popis: | In viticulture, there are several applications where 3D bud detection and localization in vineyards is a necessary task susceptible to automation: measurement of sunlight exposure, autonomous pruning, bud counting, type-of-bud classification, bud geometric characterization, internode length, and bud development stage. This paper presents a workflow to achieve quality 3D localizations of grapevine buds based on well-known computer vision and machine learning algorithms when provided with images captured in natural field conditions (i.e., natural sunlight and the addition of no artificial elements), during the winter season and using a mobile phone RGB camera. Our pipeline combines the Oriented FAST and Rotated BRIEF (ORB) for keypoint detection, a Fast Local Descriptor for Dense Matching (DAISY) for describing the keypoint, and the Fast Approximate Nearest Neighbor (FLANN) technique for matching keypoints, with the Structure from Motion multi-view scheme for generating consistent 3D point clouds. Next, it uses a 2D scanning window classifier based on Bag of Features and Support Vectors Machine for classification of 3D points in the cloud. Finally, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for 3D bud localization is applied. Our approach resulted in a maximum precision of 1.0 (i.e., no false detections), a maximum recall of 0.45 (i.e. 45% of the buds detected), and a localization error within the range of 259–554 pixels (corresponding to approximately 3 bud diameters, or 1.5 cm) when evaluated over the whole range of user-given parameters of workflow components. Fil: Díaz, Carlos Ariel. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina Fil: Pérez, Diego Sebastián. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina Fil: Miatello, Humberto. New Lab; Estados Unidos Fil: Bromberg, Facundo. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect