Abstract
Automated tire visual inspection plays an extraordinary important role in ensuring tire quality and driving safety. Due to the anisotropic complex multi texture and defect diversity characteristic of tire radiographic image, tire intelligent visual inspection has become one of the technical bottlenecks of intelligent manufacturing. In this work, a novel tire defect detection model using Concise Semantic Segmentation Network (Concise-SSN) is investigated for automated tire visual inspection. We perform an end-to-end pixel-wise tire defect detection by combining the power of an optimized semantic segmentation network and a compact convolutional neural network for classification. It can achieve the end-to-end pixel-wise full class defect detection and classification. The experimental results show superior performance on defect segmentation and classification tasks compared to state-of-the-art models with smaller model size and faster computation. Comparative experiments indicated that our Concise-SSN achieves the mPA score of 85.13%, the mIoU score of 77.34% on our test set. The accuracy of defect classification is 96.5% on average. Finally, we show faster computation (0.132 seconds per image) with competitive results on our dataset, which can meet the needs of online tire detection.
Highlights
According to World Health Organization, about 1.3 million people die and 50 million disabled from road accidents each year, among them 40% are caused by tire failures [1]
OVERVIEW Inspired by the SegNet, in this work we propose a concise encoder-decoder architecture for tire radiographic image feature learning
We investigate the performance of our proposed Concise-SSN Network with the state-of-the-art segmentation networks and deep convolution neural network (DCNN)
Summary
According to World Health Organization, about 1.3 million people die and 50 million disabled from road accidents each year, among them 40% are caused by tire failures [1]. The problem space is different from road and indoor scene understanding such that we probe into designing a more compact and effective network structure by removing layers that have little influence on tire radiographic image feature learning to perform the efficiency and accuracy of real-time detection. This multi texture background and high resolution of input images brings challenges to the design of a unified robust and automatic tire visual inspection algorithm To alleviate this problem, we first propose a texture segmentation method based on Gabor filter and fuzzy c-means clustering to segment different regions of tire radiographic images. Segmented image blocks are input to the proposed tire visual inspection model for further detection This trick would significantly reduce the complexity and computation of the problem space in this application.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
