A lightweight RT-DETR model for corn seedling and weed detection with adaptive feature fusion
- 1 August 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (16) , 165230
Abstract
Due to the large size of the existing corn seedling and weed detection models, they are difficult to deploy on resource-constrained platforms such as miniature weeding robots. Therefore, it is necessary to achieve a balance between detection accuracy and computational efficiency for the detection models. This paper proposed a lightweight detection model, RT-DETR-DSA, based on the RT-DETR-r18 model. Firstly, a dual-path convolution-attention block was designed to construct the backbone network, which improved the model’s computational efficiency by parallelizing the convolution and attention mechanisms. Secondly, based on the cross-scale feature interaction layer of the original model, this paper proposed the adaptive feature fusion block to complement and enhance the high and low-level features to improve the model’s detection accuracy. Finally, to further reduce the model’s computational load, a sliding-window self-attention block was introduced into the neck network, which divided the feature map into multiple non-overlapping windows and calculated the attention within each window separately. Experimental results showed that the proposed RT-DETR-DSA model was constructed with only 13.0M parameters, corresponding to a 35.6% reduction compared with the original RT-DETR-r18 model; its computational load was measured as only 34.9G, achieving a 40.6% reduction over the original model; the mAP@0.5 of the improved model was 1.2 percentage points higher than that of the original model; and its FPS (frames per second) reached 85.4. The RT-DETR-DSA model proposed in this paper improved computational efficiency while maintaining high detection accuracy in corn seedling and weed detection, and provided a potential technical solution for the visual perception system of miniature weeding robots.Keywords
Funding Information
- Key Technology Research and Development Program of Shandong Province (2025TSGCCZZB0802)
- China Scholarship Council (202401040020)
This publication has 30 references indexed in Scilit:
- A lightweight deep learning and whale optimization framework for sustainable precision agricultureDiscover Computing, 2026
- Intelligent optimization of Reference Evapotranspiration (ETo) for precision irrigationJournal of Computational Science, 2023
- IMPACT OF MACHINE learning ON Management, healthcare AND AGRICULTUREMaterials Today: Proceedings, 2023
- D-NMS: A dynamic NMS network for general object detectionNeurocomputing, 2022
- Key technologies of machine vision for weeding robots: A review and benchmarkComputers and Electronics in Agriculture, 2022
- An extensive review on the consequences of chemical pesticides on human health and environmentJournal of Cleaner Production, 2021
- CNN feature based graph convolutional network for weed and crop recognition in smart farmingComputers and Electronics in Agriculture, 2020
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018
- Limitations of Existing Weed Control Practices Necessitate Development of Alternative Techniques Based on Biological Approaches2018
- Understanding maize–weed competition: resource competition, light quality and the whole plantField Crops Research, 2001