Simultaneous Localization and Mapping System for Agricultural Yield Estimation Based on Improved VINS-RGBD: A Case Study of a Strawberry Field

• Published in: Agriculture (Basel) Vol. 14; no. 5; p. 784
• Main Authors: Yuan, Quanbo, Wang, Penggang, Luo, Wei, Zhou, Yongxu, Chen, Hongce, Meng, Zhaopeng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2024
• Subjects: Accuracy; Agricultural industry; Agricultural production; Agriculture; Algorithms; Annotations; Artificial intelligence; Camcorders; Cameras; Case studies; China; Crop yield; crop yield estimation; Crop yields; Field tests; Fruits; Image processing; Image reconstruction; Image segmentation; Localization; Mapping; Natural resources; New York; Production planning; Risk management; Robots; Semantic segmentation; Semantics; Sensors; Simultaneous localization and mapping; Storage; Strawberries; Unmanned aerial vehicles; VINS-RGBD; Voxblox; New York; China
• ISSN: 2077-0472; 2077-0472
• DOI: 10.3390/agriculture14050784

Crop yield estimation plays a crucial role in agricultural production planning and risk management. Utilizing simultaneous localization and mapping (SLAM) technology for the three-dimensional reconstruction of crops allows for an intuitive understanding of their growth status and facilitates yield estimation. Therefore, this paper proposes a VINS-RGBD system incorporating a semantic segmentation module to enrich the information representation of a 3D reconstruction map. Additionally, image matching using L_SuperPoint feature points is employed to achieve higher localization accuracy and obtain better map quality. Moreover, Voxblox is proposed for storing and representing the maps, which facilitates the storage of large-scale maps. Furthermore, yield estimation is conducted using conditional filtering and RANSAC spherical fitting. The results show that the proposed system achieves an average relative error of 10.87% in yield estimation. The semantic segmentation accuracy of the system reaches 73.2% mIoU, and it can save an average of 96.91% memory for point cloud map storage. Localization accuracy tests on public datasets demonstrate that, compared to Shi–Tomasi corner points, using L_SuperPoint feature points reduces the average ATE by 1.933 and the average RPE by 0.042. Through field experiments and evaluations in a strawberry field, the proposed system demonstrates reliability in yield estimation, providing guidance and support for agricultural production planning and risk management.