Abstract:Aiming at the problem of low magnification defect rating of continuous casting billets, a system solution based on deep learning framework was established. Based on the defect target detection algorithm of YOLO V4, the detection and recognition of defects of detection class are carried out. The standard Average Precision (AP) index is used as the evaluation index. The AP of “central pipe”, “central porosity”, “nonmetallic inclusion”, “subsurface blowhole” and “central segregation” reached 82.19%, 97.63%, 54.27%, 66.20% and 29.29% respectively. The defect instance segmentation algorithm based on MASK RCNN was used to detect and identify segmented defects. Taking the standard AP(0.5-0.95) as the evaluation index, the AP(0.5-0.95) for detecting and segmentation of four types of defects, namely, “central crack”, “corner crack”, “middle crack” and “subcutaneous crack”, reached 0.78. In particular, From the perspective of production and application, AP(0.5) reaches 0.96, which can better meet the needs of defect detection.
CHEN T, CHENG M M, TAN P, et al. Sketch2Photo: Internet image montage[J]. ACM Trans Graph, 2009, 28(5):1.
[6]
Wang L, Hua G, Sukthankar R, et al. Video object discovery and Co-segmentation with extremely weak supervision[J]. European Conference on Computer Vision, 2014: 640.
[7]
Ren Z, Gao S, Chia L T, et al. Region-based saliency detection and its application in object recognition[J]. IEEE Trans Circuits Syst Video Technol, 2014, 24(5):769.
[8]
Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans Pattern Anal Mach Intell, 1998, 20(11):1254.
[9]
Treisman A M, Gelade G. A feature-integration theory of attention[J]. Cogn Psychol, 1980,12(1):97.
[10]
Walther D,Koch C. 2006 Special Issue: Modeling attention to salient proto-objects[J]. Neural Networks, 2006, 19(9):1395.
[11]
Gao D, Vasconcelos N. Bottom-up saliency is a discriminant process[J]. IEEE Int Conf Comput Vis, 2007: 1.
[12]
LIU T, YUAN Z J, SUN J, et al. Learning to detect a salient object[J]. IEEE Trans Pattern Anal Mach Intell, 2011, 33(2):353.
[13]
JIANG H, WANG J, YUAN Z, et al. Salient object detection: A discriminative regional feature integration approach[J]. IEEE Conf Comput Vis Pattern Recognit, 2013: 2083.
[14]
Lu S, Mahadevan V, Vasconcelos N. Learning optimal seeds for diffusion-based salient object detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2014:2790.
KUEN J, WANG Z, WANG G. Recurrent attentional networks for saliency detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2016: 3668.
[17]
WANG L, LU H, ZHANG P, et al. Saliency detection with recurrent fully convolutional networks[J]. European Conference on Computer Vision, 2016:825.
[18]
Viola P, Jones M. Robust real-time object detection[J]. Int J Comput Vis, 2001(4):34.
[19]
Messom C, Barczak A. Fast and efficient rotated haar-like features using rotated integral images[J]. Proc 2006 Australas Conf Robot Autom, 2006:1.
[20]
Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997,55(1):119.
[21]
Dalal N, Triggs B. Histograms of oriented gradients for human detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2005:886.
[22]
Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Trans Pattern Anal Mach Intell, 2010(9):162.
[23]
Zhou X, Wang D, Krähenbühl P.Objects as points[J]. arXiv,2019: 12.
[24]
Bochkovskiy A, Wang C Y, Liao M. YOLOv4: Optimal speed and accuracy of object detection[J]. arXiv, 2020:10934.