EUVIMEDEUVIMED entdecken
Crossref

RT-CWDT: a lightweight real-time transformer for crop and weed detection with adaptive feature sampling

Qi Yan, Ning Jin, Si Li, Huaji Zhu, Yisheng Miao, Huarui Wu

Measurement Science and Technology · 30.10.2026 · 37 (43) · 435405

DOI: 10.1088/1361-6501/aeb714 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 29.10.2026. Verfasst von Qi Yan und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Liaoning Provincial Science and Technology Plan Joint Plan, earmarked fund for CARS-Major Vegetables.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate crop–weed discrimination is essential for site-specific weed management and reduced herbicide use in precision agriculture. In real field environments, irregular plant morphology, small targets, mutual leaf occlusion, and cluttered soil backgrounds degrade detection accuracy, while on-board deployment further requires real-time inference on resource-constrained devices. This study proposes RT-CWDT, a lightweight real-time crop–weed detector that improves the feature representation of RT-DETR-R18 in the backbone, in the enhancement of the high-level feature, and in the encoder. The selective gated residual block restricts the spatial convolution of the backbone to a quarter of the channels and recalibrates the result with a gated module. The dual-attention hybrid-kernel module applies attention-guided large kernels to part of the channels of the high-level feature and preserves lightweight local feature modeling on the remaining ones. The adaptive sampling encoder combines deformable sampling with a reordering attention, enabling high-level features to align with the irregular geometry of plants rather than a fixed token grid. On the Weed-Crop dataset, RT-CWDT reaches 76.7% precision, 73.0% recall, 75.9% mAP50, and 38.8% mAP50:95, outperforming RT-DETR-R18 by 3.5 percentage points in mAP50 while reducing parameters by 21.1% and GFLOPs by 18.1%. RT-CWDT also outperforms RT-DETR-R18 on the CropAndWeed and ImageWeeds datasets, which differ in species, label scheme, and viewpoint, and it keeps its advantage under both single-factor and compound simulated imaging degradations. Using TensorRT INT8 on an NVIDIA Jetson Orin NX, RT-CWDT runs at 51.9 FPS against 42.0 FPS for RT-DETR-R18. RT-CWDT therefore improves detection accuracy while maintaining a lightweight architecture and real-time inference, which suits the detection of crops and weeds on a resource-constrained embedded device.

Förderung

  • National Key Research and Development Program of China
  • Liaoning Provincial Science and Technology Plan Joint Plan
  • earmarked fund for CARS-Major Vegetables

Zitieren

APA

Yan, Q., Jin, N., Li, S., Zhu, H., Miao, Y., & Wu, H. (2026). RT-CWDT: a lightweight real-time transformer for crop and weed detection with adaptive feature sampling. Measurement Science and Technology, 37(43), 435405. https://doi.org/10.1088/1361-6501/aeb714

Vancouver

Yan Q, Jin N, Li S, Zhu H, Miao Y, Wu H. RT-CWDT: a lightweight real-time transformer for crop and weed detection with adaptive feature sampling. Measurement Science and Technology. 2026;37(43):435405. doi:10.1088/1361-6501/aeb714

BibTeX
@article{Yan2026,
  author = {Yan, Qi and Jin, Ning and Li, Si and Zhu, Huaji and Miao, Yisheng and Wu, Huarui},
  title = {RT-CWDT: a lightweight real-time transformer for crop and weed detection with adaptive feature sampling},
  journal = {Measurement Science and Technology},
  year = {2026},
  volume = {37},
  number = {43},
  pages = {435405},
  doi = {10.1088/1361-6501/aeb714}
}
Kostenlos starten →