Abstract
We propose a detection-based tracking system for automatically processing maritime ship inspection videos and predicting suspicious areas where cracks may exist. This system consists of two stages. Stage one uses a state-of-the-art object detection model, i.e., RetinaNet, which is customized with certain modifications and the optimal anchor setting for detecting cracks in the ship inspection images/videos. Stage two is an enhanced tracking system including two key components. The first component is a state-of-the-art tracker, namely, Channel and Spatial Reliability Tracker (CSRT), with improvements to handle model drift in a simple manner. The second component is a tailored data association algorithm which creates tracking trajectories for the cracks being tracked. This algorithm is based on not only the intersection over union (IoU) of the detections and tracking updates but also their respective areas when associating detections to the existing trackers. Consequently, the tracking results compensate for the detection jitters which could lead to both tracking jitter and creation of redundant trackers. Our study shows that the proposed detection-based tracking system has achieved a reasonable performance on automatically analyzing ship inspection videos. It has proven the feasibility of applying deep neural network based computer vision technologies to automating remote ship inspection. The proposed system is being matured and will be integrated into a digital infrastructure which will facilitate the whole ship inspection process.
Highlights
The rapid development and effectiveness of convolutional neural networks (CNN)have greatly contributed to enormously emerging computer vision applications and tools.As the performance and maturity level of computer vision technologies are continuously improving, we can utilize them to enhance or assist human tasks under certain circumstances in order to reduce safety risks, increase work efficiency, and cut costs.One growing trend of applying computer vision technologies is remote visual inspection (RVI) [1,2], where a human inspector inspects a video instead of being physically present on the site
We present a detection-based object tracking system which automates the process of detecting cracks in the ship inspection videos and assists human inspectors to focus their attention on a subset of the video frames for analysis and decision-making
We focus on investigating the feasibility of the CNN-based detection model which is trained on the real crack images captured by our ship inspectors
Summary
As the performance and maturity level of computer vision technologies are continuously improving, we can utilize them to enhance or assist human tasks under certain circumstances in order to reduce safety risks, increase work efficiency, and cut costs. One growing trend of applying computer vision technologies is remote visual inspection (RVI) [1,2], where a human inspector inspects a video instead of being physically present on the site. This is very beneficial when the assets to be inspected are difficult to access or in dangerous environments. To reduce the inspection cost and increase personnel safety, leading ship classification societies
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.
