Unsupervised Saliency Detection of Rail Surface Defects Using Stereoscopic Images
Unsupervised Saliency Detection of Rail Surface Defects Using Stereoscopic Images
复制标题
使用立体图像对钢轨表面缺陷进行无监督显着性检测
DOI：
10.1109/tii.2020.3004397
复制
发表时间：
2021-03-01
影响因子：
12.3
通讯作者：
Meng, Qinggang
中科院分区：
文献类型：
--
作者：
Niu, Menghui;Song, Kechen;Meng, Qinggang
视觉信息因其高效性和稳定性而越来越被认为是检测轨面缺陷的有用方法。然而，它不能充分地检测复杂背景信息中的完整缺陷。添加表面轮廓可以通过包括缺陷的3-D信息来有效地改善这一点。然而，在高速检测中，传统的三维轮廓获取困难且与图像采集分离，不能有效满足上述要求。因此，本文提出了一种基于双目线扫描系统的非监督立体显著性检测方法。该方法可以同时获得高精度的图像以及轮廓信息，同时也避免了结构光重建方法的解码失真。在我们的方法中，提出了一种全局低秩非负重建算法与背景约束。与低秩恢复模型不同，该算法具有更全面的低秩和背景聚类特性。此外，该方法还提出了基于轨道表面几何特性的离群点检测方法。最后，将图像显著性检测结果和深度异常检测结果与协同融合相关联，建立了包含钢轨表面缺陷的数据集（RSDDS-113）进行实验验证。实验结果表明，该方法的平均绝对误差为0.09，ROC曲线下面积为0.94，优于15种最先进的算法。
Visual information is increasingly recognized as a useful method to detect rail surface defects due to its high efficiency and stability. However, it cannot sufficiently detect a complete defect in the complex background information. The addition of surface profiles can effectively improve this by including a 3-D information of defects. However, in high-speed detection, the traditional 3-D profile acquisition is difficult and separate from the image acquisition, which cannot satisfy the above-mentioned requirements effectively. Therefore, an unsupervised stereoscopic saliency detection method based on a binocular line-scanning system is proposed in this article. This method can simultaneously obtain a highly precise image as well as profile information while also avoids the decoding distortion of the structured light reconstruction method. In our method, a global low-rank nonnegative reconstruction algorithm with a background constraint is proposed. Unlike the low-rank recovery model, the algorithm has a more comprehensive low rank and background clustering properties. Furthermore, outlier detection based on the geometric properties of the rail surface is also proposed in this method. Finally, the image saliency results and depth outlier detection results are associated with the collaborative fusion, and a dataset (RSDDS-113) containing the rail surface defects is established for the experimental verification. The experimental results demonstrate that our method can obtain a mean absolute error of 0.09 and area under the ROC curve of 0.94, better than 15 state-of-the-art algorithms.