AX dataset reported in this paper is available from the lead contact upon request. • The DOTA dataset has been published in a publicly accessible repository. The access address is listed in the key resources table . Datasets are publicly accessible. • All code associated with this paper can be freely accessed and downloaded via https://github.com/ShawnWang04/LEHP-DETR . • Any additional information required to reanalyze the data reported in this paper is available from the lead contact upon request. Acknowledgments Thanks to the National Natural Science Foundation of China (No. 32360437) and the Innovation Fund for Higher Education of Gansu Province (No. 2021A-056), and the National Industri
Open resource ↗ShawnWang04/LEHP-DETR · lines:594-657Unverified paper record
LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection.
iScience · 9 Dec 2024 · 10.1016/j.isci.2024.111558
Abstract
Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of computer vision and deep learning techniques offers a new way to solve this problem. In this study, based on RT-DETR, we introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR. Experimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model. Compared to the base model, LEHP-DETR reduces the number of parameters by 67.3%, the model size by 66.3%, and the FLOPs by 37.6%. the average detection accuracy mAP50 and mAP50:95 increased by 2.6% and 3.5%, respectively.
Plant phenotyping relevance
アマ種子ではなくフラックスの莢という植物器官を画像から検出するモデルを新規設計し、比較実験で性能を検証しており、器官表現型の取得・抽出法が中心である。
titleLEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection.
abstractwe introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR.
abstractExperimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model.
Code and data availability
The paper's authors publicly release the LEHP-DETR analysis code (the improved RT-DETR model used for flax capsule detection) on GitHub. The paper-specific FLAX dataset is only available upon request from the lead contact, so it does not qualify as a public asset. DOTA is a cited third-party dataset, not paper-specific
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.