Idioma:

Guava Detection and Pose Estimation Using a Low-Cost RGB-D Sensor in the Field

Lin, Guichao ; Tang, Yunchao ; Zou, Xiangjun ; Xiong, Juntao ; Li, Jinhui

Sensors (Basel, Switzerland), 2019-01, Vol.19 (2), p.428 [Periódico revisado por pares]

Switzerland: MDPI AG

Texto completo disponível

Citações Citado por

Enviar para

Título:
Guava Detection and Pose Estimation Using a Low-Cost RGB-D Sensor in the Field
Autor: Lin, Guichao ; Tang, Yunchao ; Zou, Xiangjun ; Xiong, Juntao ; Li, Jinhui
Assuntos: Algorithms ; Apples ; Architectural engineering ; Artificial neural networks ; branch reconstruction ; Clustering ; Collision avoidance ; Fruits ; fully convolutional network ; Guava ; guava detection ; Harvest ; Harvesting ; Image retrieval ; International conferences ; Low cost ; Methods ; Pattern recognition ; Pose estimation ; RGB-D sensor ; Robots ; Semantics ; Sensors ; Three dimensional models
É parte de: Sensors (Basel, Switzerland), 2019-01, Vol.19 (2), p.428
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: Fruit detection in real outdoor conditions is necessary for automatic guava harvesting, and the branch-dependent pose of fruits is also crucial to guide a robot to approach and detach the target fruit without colliding with its mother branch. To conduct automatic, collision-free picking, this study investigates a fruit detection and pose estimation method by using a low-cost red⁻green⁻blue⁻depth (RGB-D) sensor. A state-of-the-art fully convolutional network is first deployed to segment the RGB image to output a fruit and branch binary map. Based on the fruit binary map and RGB-D depth image, Euclidean clustering is then applied to group the point cloud into a set of individual fruits. Next, a multiple three-dimensional (3D) line-segments detection method is developed to reconstruct the segmented branches. Finally, the 3D pose of the fruit is estimated using its center position and nearest branch information. A dataset was acquired in an outdoor orchard to evaluate the performance of the proposed method. Quantitative experiments showed that the precision and recall of guava fruit detection were 0.983 and 0.948, respectively; the 3D pose error was 23.43° ± 14.18°; and the execution time per fruit was 0.565 s. The results demonstrate that the developed method can be applied to a guava-harvesting robot.
Editor: Switzerland: MDPI AG
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Guava Detection and Pose Estimation Using a Low-Cost RGB-D Sensor in the Field

Lin, Guichao ; Tang, Yunchao ; Zou, Xiangjun ; Xiong, Juntao ; Li, Jinhui

Switzerland: MDPI AG

Buscando em bases de dados remotas. Favor aguardar.