Open PhD and Master Positions @
Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies
full-text on https://doi.org/10.1061/(ASCE)CF.1943-5509.0001652
Dr. Yuhan Jiang 2020/11/04
Highlights:
The developed application (running in background) automatically captures screenshots and processes them
The manual participation was crafting few labels
The point cloud was generated from Autodesk ReCap Pro
The pixelwise segmentation was powered by U-net
The U-net model training only used few orthographic (front, back, left, and right) view images
The data augmentation included rotation, resize, perspective, and flip
The “contours” function was powered by OpenCV
Testing Result
Captured image Pixelwise segmentation
Training Data Set
Image Label
Window Detection Using U-net and 3D Mesh Model (Window Detection Ver.1)