Abstract
For the surface defects inspection task, operators need to check the defect in local detail images by specifying the location, which only the global 3D model reconstruction can’t satisfy. We explore how to address multi-type (original image, semantic image, and depth image) local detail image synthesis and environment data storage by introducing the advanced neural radiance field (Nerf) method. We use a wall-climbing robot to collect surface RGB-D images, generate the 3D global model and its bounding box, and make the bounding box correspond to the Nerf implicit bound. After this, we proposed the Inspection-Nerf model to make Nerf more suitable for our near view and big surface scene. Our model use hash to encode 3D position and two separate branches to render semantic and color images. And combine the two branches’ sigma values as density to render depth images. Experiments show that our model can render high-quality multi-type images at testing viewpoints. The average peak signal-to-noise ratio (PSNR) equals 33.99, and the average depth error in a limited range (2.5 m) equals 0.027 m. Only labeled 2% images of 2568 collected images, our model can generate semantic masks for all images with 0.957 average recall. It can also compensate for the difficulty of manual labeling through multi-frame fusion. Our model size is 388 MB and can synthesize original and depth images of trajectory viewpoints within about 200 m2 dam surface range and extra defect semantic masks.
Funder
China Yangtze Power Co., Ltd.
Shenyang Institute of Automation
Chinese Academy of Sciences
Subject
Building and Construction,Civil and Structural Engineering,Architecture
Reference33 articles.
1. Development and prospect of defect detection technology for concrete dams;Dam Saf.,2016
2. Utilizing UAV and 3D computer vision for visual inspection of a large gravity dam;Khaloo;Front. Built Environ.,2018
3. Damage detection and finite-element model updating of structural components through point cloud analysis;Ghahremani;J. Aerosp. Eng.,2018
4. Automatic detection of structural deficiencies using 4D Hue-assisted analysis of color point clouds;Khaloo;Dynamics of Civil Structures,2019
5. Angeli, S., Lingua, A.M., Maschio, P., Piantelli, L., Dugone, D., and Giorgis, M. (2018, January 6–8). Dense 3D model generation of a dam surface using UAV for visual inspection. Proceedings of the International Conference on Robotics in Alpe-Adria Danube Region, Patras, Greece.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献