Crack_Database：此存储库可将crack的数据集用于语义分割

# DIMEC-Crack_Database # Semantic Segmentation Model for Crack Images from Concrete Bridges for Mobile Devices # ## Enrique Lopez Droguett, Juan Tapia, Claudio Yanez and Ruben Boroschek. # Computer vision algorithms are powerful techniques that can be used for remotely monitoring and inspecting civil structures. Detecting and segmenting cracks in images of concrete bridges can provide useful information related to the health of the structure. There are several states of the art methods based on Deep Learning that have been used for segmentation tasks. However, most of them require a large number of parameters which limits their use in mobile device applications. A DenseNet architecture was proposed with only 13 layers with one feature extractor stage and two datapaths. Implementations of state of the art semantic segmentation methods are also tested. The implemented method achieved better results than standard algorithms with only a fraction of the parameters making them suitable for developing mobile device applications for bridge structure monitoring. As an additional contribution, two novel databases for semantic segmentation of cracks are presented. These databases were used to test all algorithms in this work and will be available upon request. Additional experiments using a public database were also performed for comparison. The best results were achieved using a DenseNet-13 architecture achieving an Intersection Over Union of 94.51% for crack semantic segmentation and only 350,000 parameters. #  # This datasets are available only for research purpoose. ## For request the password, please send an email to juan.tapia.f@usach.cl