Cotton Stubble Detection Based on Improved YOLOv3

• Published in: Agronomy (Basel) Vol. 13; no. 5; p. 1271
• Main Authors: Yang, Yukun, Li, Jingbin, Nie, Jing, Yang, Shuo, Tang, Jiaqiang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 28.04.2023
• Subjects: Accuracy; Algorithms; Analysis; Cameras; Cotton; Cotton industry; cotton stubble; Crops; Deep learning; Energy consumption; Harvesting; Labeling; Machine learning; machine vision; Navigation; navigation line extraction; Neural networks; Noise reduction; Object recognition; Real time; residual film recovery; Stubble; Support vector machines; Target detection; Technical services; Weeds; China
• ISSN: 2073-4395; 2073-4395
• DOI: 10.3390/agronomy13051271

The stubble after cotton harvesting was used as the detection object to achieve the visual navigation operation for residual film recovery after autumn. An improved (You Only Look Once v3) YOLOv3-based target detection algorithm was proposed to detect cotton stubble. First, field images of residual film recycling were collected. Considering the inconsistency between stubble size and shape, a segmented labeling data set of stubble is proposed. Secondly, the Darknet-53 backbone of the original YOLOv3 network is improved to accommodate tiny targets. Next, the prediction anchor box of the improved detection backbone is clustered using K-means++, and the size of the prediction anchor box suitable for improved YOLOv3 is determined. Finally, for the false detection points after detection, a mean value denoising method is used to remove the false detection points. Feature points are extracted from the denoised stubble, and the candidate points are fitted by the least square method to obtain the navigation line. The optimal model with a mean average precision (mAP) of 0.925 is selected for testing at the test stage. The test results show that the algorithm in this article can detect the stubble of residual film recovery images at different locations, different time periods, and different camera depression angles without misdetection. The detection speed of a single image is 98.6 ms. Based on an improvement over YOLOv3, the improved model has a significantly higher detection rate in different scenarios than YOLOv3. This can provide practical technical support for the visual navigation of residual film recovery.