AerialCrackDetection_Keras is a project about object detection from aerial imagery using pavament crack data. The project uses the open source software library Keras and Tensorflow, with a ZF or VGG16 or ZF or VGG16 or GoogleNet or ResNet50 or ResNet101 neuronal networks. AerialCrackDetection_Keras is based on Faster RCNN.
PS: The project is only the original version, the improved version is not open.
@inproceedings{
Author = {Bo Wang},
Title = {AerialCrackDataset: Towards Object Detection with Dataset},
Laboratory = {Key Laboratory of Optoelectronic Imaging Technology and System,
Ministry of Education, School of Optoelectronics,
Beijing Institute of Technology},
Year = {2017}
}
cd $FRCN_ROOT
mkdir model
cd model
# put the Pre-trained ImageNet models here
cd $FRCN_ROOT
./train.py [--path] [--network]
# --path is the dataset location you want to train
# --net in {ZF, VGG16, GoogleNet, ResNet50, ResNet101} is the network arch to use
cd $FRCN_ROOT
./test.py [--path] [--network]
# --path is the dataset location you want to test
# --net in {ZF, VGG16, GoogleNet, ResNet50, ResNet101} is the network arch to use