Deep Semantic 3D Visual Metric Reconstruction Using Wall-Climbing Robot

This project introduces an inspection method using a deep neural network to detect the crack and spalling defects on concrete structures performed by a wall-climbing robot. First, we create a pixel-level semantic dataset which includes 820 labeled images. Second, we propose an inspection method to obtain 3D metric measurement by using an RGB-D camera-based visual simultaneous localization and mapping (SLAM), which is able to generate pose coupled key-frames with depth information. Therefore, the semantic inspection results can be registered in the concrete structure 3D model for condition assessment and monitoring. Third, we present our new generation wall-climbing robot to perform the inspection task on both horizontal and vertical surfaces