Accurate and efficient corrosion detection is a difficult but important issue with immediate relevance to maintenance of Naval ships. The current process requires an inspector to physically access the space and perform a very manual visual inspection of the space. Considering the schedules of both the inspector and the ship, coordinating the inspection of hundreds of tanks and voids is not always a straightforward process. There is a significant amount of research into automatic detection of corrosion via computer vision algorithms, but performing pixel level segmentation introduces added difficulty. There are two key reasons for this: the lack of annotated data and the inherent difficulty in the type of problem. In this work, we utilized a combination of annotated data from a different domain and a small hand labeled dataset of panoramic images from our target domain: the inside of empty ship tanks and voids. We trained two High-Resolution Network (HRNet) models for our corrosion detector; the first with a dataset outside our target domain, the second with our hand annotated panoramic tank images. By ensembling our two models, the F1-score increased by about 120% and IOU score by about 176% with respect to the single baseline corrosion detector. The data collection process via LiDAR scanning allows the inspection process to be performed remotely. Additionally, the setup of the detector leads to a natural expansion of the corrosion dataset as panoramas from LiDAR scans are continually fed through the detector and the detections are validated. This allows for the corrosion models to be later retrained for potential improvement in accuracy and robustness.
KEYWORDS: Clouds, 3D image processing, Image processing, LIDAR, Data processing, Associative arrays, 3D acquisition, Scanners, Optical character recognition, Machine vision
The presence of noise, displacement of points, and empty spots in a raw Light Detection and Ranging (LiDAR) point cloud are common phenomena caused by reflective surfaces or objects. Typical approaches to solve this problem are either avoid or cover the reflective areas or to manually remove the erroneous data in post processing. This can help clean the point cloud structure but will cause sparsity issues. To combat this, in this paper, we introduce a two-step process to perform point cloud restoration. Instead of removing noise, this approach can restore the points to the closest surface which they may belong to. Next, to fill out empty spots, we introduce a technique called point cloud inpainting, which involves interpolating points in 2D then mapping it back to 3D for flat surfaces. The point cloud then becomes more photorealistic and easier to use for other computer vision tasks.
Multi-agent reinforcement learning (MARL) has transformed research and development in robotics especially for navigation purposes. Using deep learning, multi-agent coordination, reinforcement learning can solve critical tasks such as finding shortest paths or avoiding obstacles with exceptional speed. However, given a LiDAR point cloud structure, performing such tasks directly using MARL, can be computationally expensive and cumbersome due to massive nature of 3D point clouds. In this work, we leverage 2D (MARL), path planning and obstacle avoidance to obtain a low latency navigation in 3D though a correspondence 2D floor plan. We change the environment dynamically with adversarial threats such as fire or leakage -- the RL agents can quickly find a new path given the learned environment. The method shows strong performances in both throughput and latency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.