██╗ ██╗ ██████╗ ██╗ █████╗ ██████╗████████╗
╚██╗ ██╔╝██╔═══██╗██║ ██╔══██╗██╔════╝╚══██╔══╝
╚████╔╝ ██║ ██║██║ ███████║██║ ██║
╚██╔╝ ██║ ██║██║ ██╔══██║██║ ██║
██║ ╚██████╔╝███████╗██║ ██║╚██████╗ ██║
╚═╝ ╚═════╝ ╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚═╝
YOLACT has not been updating for some time, but nevertheless our team used YOLACT for instance segmentation on detecting cracks! Our drone attaches to the wall and moves in any direction, with camera just 30cm away from the wall. with the specs. of the camera we use, crack width can be calculated using the mask detected from YOLACT.
The GUI is just simply based on google Photos API, with images get from time that can be set on GUI. after setting time from and to the time to look, images are downloaded from google Photos. And then crack width is calculated, with output saved on 'output'folder.
If you use YOLACT or this code base in your work, please cite
@inproceedings{yolact-iccv2019,
author = {Daniel Bolya and Chong Zhou and Fanyi Xiao and Yong Jae Lee},
title = {YOLACT: {Real-time} Instance Segmentation},
booktitle = {ICCV},
year = {2019},
}
For YOLACT++, please cite
@article{yolact-plus-tpami2020,
author = {Daniel Bolya and Chong Zhou and Fanyi Xiao and Yong Jae Lee},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
title = {YOLACT++: Better Real-time Instance Segmentation},
year = {2020},
}