Green Apple Detection Method Based on Multidimensional Feature Extraction Network Model and Transformer Module

• Published in: Journal of food protection 2025-01, Vol.88 (1), p.100397, Article 100397
• Main Authors: Ji, Wei, Zhai, Kelong, Xu, Bo, Wu, Jiawen
• Format: Article
• Language: English
• Subjects: DETR; Near color system; ResNet18; Sample analysis; Target detection; Transformer
• ISSN: 0362-028X; 1944-9097; 1944-9097
• DOI: 10.1016/j.jfp.2024.100397

•Integrated an expanded pyramid module to enhance multiscale fruit feature capture.•Upgraded ResNet18 with DCNv2 for improved spatial perception of green apples.•Introduced multiscale deformable attention in Transformer, boosting accuracy and speed.•Proposed method was validated through rigorous experiments and real-world deployment. To enhance the fast and accurate detection of pollution-free green apples for food safety, this paper uses the DETR network as a framework to propose a new method for pollution-free green apple detection based on a multidimensional feature extraction network and Transformer module. Firstly, an improved DETR network main feature extraction module adopts the ResNet18 network and replaces some residual layers with deformable convolutions (DCNv2), enabling the model to better adapt to pollution-free fruit changes at different scales and angles, while eliminating the impact of microbial contamination on fruit testing; Subsequently, the extended spatial pyramid pooling model (DSPP) and multiscale residual aggregation module (FRAM) are integrated, which help reduce feature noise and minimize the loss of underlying features during the feature extraction process. The fusion of the two modules enhances the model’s ability to detect objects of different scales, thereby improving the accuracy of near-color fruit detection. At the same time, in order to solve the problems of slow convergence speed and large calculation amount of the basic network model, the convergence speed of the overall network model is improved by replacing the attention mechanism of Transformer. Experimental results show that compared with the original DETR model, the proposed algorithm has improved in AP, AP50, and AP75 indicators, especially in the AP50 indicator, which has the most obvious improvement reaching a detection accuracy of 97.12%. In the meantime, the trained network model is deployed on the picking robot. Compared with the original DETR network model, its average detection accuracy is as high as 96.58%, and the detection speed is increased by about 51%. Mixed sample detection tests were carried out before and after the model deployment, and the detection rate of the proposed method for nonpolluted fruits reached more than 0.95. enabling the picking robot to efficiently complete the task of picking green apples. The test results show that the algorithm proposed in this article exhibits great potential in the task of detecting pollution-free near-color fr