期刊
FRONTIERS IN PLANT SCIENCE
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fpls.2021.705021
关键词
fruit detection; computer vision; recognition and localization; multi-feature classification; edge detection; vision sensing
资金
- National Key Research and Development Program of China [2020YFD1000104]
- Key Field R&D Program Project of Guangdong Province, China [2019B020223002]
- China Agriculture Research System of MOF [CARS-31-10]
- Laboratory of Lingnan Modern Agriculture Project [NT2021009]
The study successfully achieved multi-target recognition and positioning in orchards using a modified deep learning algorithm, providing a solution for the precise identification of banana fruits, inflorescence axes, and flower buds, with high speed and accuracy under both front-lighting and backlighting conditions. Experimental results demonstrated that the method can meet the real-time operational requirements for the banana bud-cutting robot.
Multi-target recognition and positioning using robots in orchards is a challenging task in modern precision agriculture owing to the presence of complex noise disturbance, including wind disturbance, changing illumination, and branch and leaf shading. To obtain the target information for a bud-cutting robotic operation, we employed a modified deep learning algorithm for the fast and precise recognition of banana fruits, inflorescence axes, and flower buds. Thus, the cutting point on the inflorescence axis was identified using an edge detection algorithm and geometric calculation. We proposed a modified YOLOv3 model based on clustering optimization and clarified the influence of front-lighting and backlighting on the model. Image segmentation and denoising were performed to obtain the edge images of the flower buds and inflorescence axes. The spatial geometry model was constructed on this basis. The center of symmetry and centroid were calculated for the edges of the flower buds. The equation for the position of the inflorescence axis was established, and the cutting point was determined. Experimental results showed that the modified YOLOv3 model based on clustering optimization showed excellent performance with good balance between speed and precision both under front-lighting and backlighting conditions. The total pixel positioning error between the calculated and manually determined optimal cutting point in the flower bud was 4 and 5 pixels under the front-lighting and backlighting conditions, respectively. The percentage of images that met the positioning requirements was 93 and 90%, respectively. The results indicate that the new method can satisfy the real-time operating requirements for the banana bud-cutting robot.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据