Growing-Stage Trunk Detection and Trunk-Type Classification for Visual Navigation in Standard Camellia oleifera Orchard Scenes
Advances in Engineering Technology Research · 14.07.2026 · 17 (1) · 558
DOI: 10.56028/aetr.17.1.558.2026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Engineering Technology Research, online erschienen am 14.07.2026. Verfasst von Bingqian Hua und 4 weiteren Autor:innen.
Abstract (Originalsprache)
In vision-based navigation for standardized Camellia oleifera orchards, the root points of young Camellia oleifera trees are difficult to extract directly and robustly, and the use of the root-point substitution method often introduces deviations in navigation reference points. To address this issue, this study was conducted in the Daguo Camellia oleifera Technology Demonstration Park, Wangcheng District, Changsha, Hunan Province, with a focus on trunk architecture detection and navigation-point offset correction for young trees. First, a visual recognition dataset of young Camellia oleifera trees was constructed for standardized inter-row orchard scenes, and trunks were directly annotated into two categories: the single-trunk type and the no-distinct-main-trunk or short-bifurcated-main-trunk type. Second, the two trunk architecture types were detected using an object detection method, and the midpoint of the lower edge of each bounding box was taken as the initial navigation reference point in the root-point substitution method. Subsequently, the offset characteristics between the initial navigation reference point and the actual safe navigation point were analyzed for different trunk architecture types, and the navigation point was corrected accordingly. Experimental results showed that the proposed method can effectively identify the two trunk architecture types of young trees in standardized Camellia oleifera orchards and can further correct the navigation reference point according to trunk architecture type, thereby reducing the risk of collision caused by reference-point deviation during navigation. The results provide methodological support for navigation-point extraction, navigation-line generation, and safe-passage control in vision-based navigation for standardized Camellia oleifera orchards.
Zitieren
APA
Hua, B., Li, H., Zhu, F., Weng, T., & Wen, T. (2026). Growing-Stage Trunk Detection and Trunk-Type Classification for Visual Navigation in Standard Camellia oleifera Orchard Scenes. Advances in Engineering Technology Research, 17(1), 558. https://doi.org/10.56028/aetr.17.1.558.2026
Vancouver
Hua B, Li H, Zhu F, Weng T, Wen T. Growing-Stage Trunk Detection and Trunk-Type Classification for Visual Navigation in Standard Camellia oleifera Orchard Scenes. Advances in Engineering Technology Research. 2026;17(1):558. doi:10.56028/aetr.17.1.558.2026
BibTeX
@article{Hua2026,
author = {Hua, Bingqian and Li, Hong and Zhu, Fulei and Weng, Tianhao and Wen, Tao},
title = {Growing-Stage Trunk Detection and Trunk-Type Classification for Visual Navigation in Standard Camellia oleifera Orchard Scenes},
journal = {Advances in Engineering Technology Research},
year = {2026},
volume = {17},
number = {1},
pages = {558},
doi = {10.56028/aetr.17.1.558.2026}
}
EUVIMED