LiteTom-RTDETR: A Lightweight Real-Time Tomato Detection System for Plant Factories

Authors:
Open Access
Publisher website
Google Scholar
Abstract
The accuracy and speed of tomato detection were increased to facilitate fully automated harvesting by improving the Real-Time Detection Transformer (RTDETR) to develop a new lightweight tomato detection model called LiteTom-RTDETR. This model employed RepViT as a lightweight backbone network instead of the original RTDETR backbone, considerably reducing both the number of parameters in and computational complexity of the model. Furthermore, a context guide fusion module was designed to enhance multiscale feature extraction efficiency, and an adaptive sliding weight mechanism was integrated into the loss function to mitigate class-imbalance issues. The proposed LiteTom-RTDETR model was shown to balance high tomato identification accuracy (88.2%) with an excellent real-time inference speed (52.2 frames per second) and computational efficiency (36.3 GFLOPs). Notably, the average detection accuracy of LiteTom-RTDETR was 0.6% higher, its detection speed was 15.5% faster, and its computational load and model size were 36.2% and 31.6% smaller, respectively, than those of the original RTDETR model. Therefore, the proposed model provides a practical approach for realizing visual recognition tasks in resource-constrained mobile automated tomato harvesting equipment.
Funding Information
  • Shaanxi Provincial Key R&D Program (2023-YBGY-385, 2024NC-YBXM-203, 2022JM-131, 24JC024, SLGRCQD2101)
  • Key Research Program Project of Shaanxi Provincial Department of Science and Technology (2023-YBGY-385, 2024NC-YBXM-203, 2022JM-131, 24JC024, SLGRCQD2101)
  • Shaanxi Provincial Department of Science and Technology General Project (2023-YBGY-385, 2024NC-YBXM-203, 2022JM-131, 24JC024, SLGRCQD2101)
  • Special Program for Local Service and Industrialization Cultivation Project of Shaanxi Provincial Department of Education (2023-YBGY-385, 2024NC-YBXM-203, 2022JM-131, 24JC024, SLGRCQD2101)
  • Shaanxi University of Technology (2023-YBGY-385, 2024NC-YBXM-203, 2022JM-131, 24JC024, SLGRCQD2101)

This publication has 25 references indexed in Scilit: