TY  - EJOU
AU  - Liu, Qianshuo 
AU  - Zhao, Jun 

TI  - MA-Res U-Net: Design of Soybean Navigation System with Improved U-Net Model
T2  - Phyton-International Journal of Experimental Botany

PY  - 2024
VL  - 93
IS  - 10
SN  - 1851-5657

AB  - Traditional machine vision algorithms have difficulty handling the interference of light and shadow changes, broken rows, and weeds in the complex growth circumstances of soybean fields, which leads to erroneous navigation route segmentation. There are additional shortcomings in the feature extractFion capabilities of the conventional U-Net network. Our suggestion is to utilize an improved U-Net-based method to tackle these difficulties. First, we use ResNet’s powerful feature extraction capabilities to replace the original U-Net encoder. To enhance the concentration on characteristics unique to soybeans, we integrate a multi-scale high-performance attention mechanism. Furthermore, to do multi-scale feature extraction and capture a wider variety of contextual information, we employ atrous spatial pyramid pooling. The segmented image generated by our upgraded U-Net model is then analyzed using the CenterNet method to extract key spots. The RANSAC algorithm then uses these important spots to delineate the soybean seedling belt line. Finally, the navigation line is determined using the angle tangency theory. The experimental findings illustrate the superiority of our method. Our improved model significantly outperforms the original U-Net regarding mean Pixel Accuracy (mPA) and mean Intersection over Union (mIOU) indices, showing a more accurate segmentation of soybean routes. Furthermore, our soybean route navigation system’s outstanding accuracy is demonstrated by the deviation angle, which is only 3° between the actual deviation and the navigation line. This technology makes a substantial contribution to the sustainable growth of agriculture and shows potential for real-world applications.
KW  - Soybean route; image segmentation; sustainable development; deep learning; navigation system

DO  - 10.32604/phyton.2024.056054