BV-Net: Bin-based Vector-predicted Network for tubular solder joint detection. (October 2021)

• Record Type: Journal Article
• Authors: Zhou, Chenlin; Shen, Xiaofei; Wang, Peng; Wei, Wei; Sun, Jia; Luo, Yongkang; Li, Yiming
• Is Part Of: Measurement. Volume 183(2021)
• Publication Date: 2021-10
• Subjects: Object detection -- Defect detection -- Quality inspection -- Tubular solder joint detection -- Deep learning; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.109821
• Languages: English
• ISSNs: 0263-2241

Abstract

Abstract: Tubular solder joint detection is an important and challengeable issue in industry, due to the small objects, rarely collected datasets and real-time and high precision requirements. Traditional methods on defect detection cannot solve tubular solder joint detection due to lacking of angle estimation. In this paper, we propose a tubular solder joint detection method named Bin-based Vector-predicted Network (BV-Net), which combines the framework of state-of-the-art deep-learning-based object detector (YOLOv4) with specific characteristics and requirements of tubular solder joint detection. BV-Net could effectively estimate both the center point and the direction of tubular solder joints. Firstly, To regress the center point, we propose a Circle-based Distance-Intersection over Union (CirDIoU) loss, which gets better learning performance for the center point of tubular solder joint than Distance-Intersection over Union (DIOU) loss. Secondly, to estimate the direction, we introduce a bin-based angle regression method, which transforms a regression task into a classification and regression task, improving the precision of direction estimation greatly. Thirdly, we establish a tubular solder joint dataset and design a new evaluation index: mAP ( δ d, δ θ ) for tubular solder joint detection, combining the relative deviation of center point positioning δ d and the relative deviation of angle regression δ θ . Finally, comparison experiments on the dataset are carried out. BV-Net achieved 85.5% mAP (0.5%, 3%) with 34.4 FPS, meeting the requirements of industrial system. In direction estimation, bin-based angle regression method promotes 4.3% mAP (-, 3%), compared with the baseline. In center point positioning, BV-Net outperforms YOLOv4 by an improvement of 0.4% mAP (0.5%, -). The experimental results verified the effectiveness of our method. Highlights: A deep-learning-based method for tubular solder joint detection is developed. A circle-based loss is proposed to center point positioning. A angle regression method is introduced to defect detection field for angle estimation.