Crack Detection Using Enhanced Hierarchical Convolutional Neural Networks
This work addresses crack detection for infrastructure inspection using UAVs, offering an incremental improvement over traditional HCNNs.
The paper tackles the problem of crack detection from UAV-collected images by proposing an enhanced hierarchical convolutional neural network (HCNN) that reduces obscuration in down-sampling and uses feature preserving blocks to minimize information loss, achieving improved detection results as demonstrated on various crack datasets.
Unmanned aerial vehicles (UAV) are expected to replace human in hazardous tasks of surface inspection due to their flexibility in operating space and capability of collecting high quality visual data. In this study, we propose enhanced hierarchical convolutional neural networks (HCNN) to detect cracks from image data collected by UAVs. Unlike traditional HCNN, here a set of branch networks is utilised to reduce the obscuration in the down-sampling process. Moreover, the feature preserving blocks combine the current and previous terms from the convolutional blocks to provide input to the loss functions. As a result, the weights of resized images can be reduced to minimise the information loss. Experiments on images of different crack datasets have been carried out to demonstrate the effectiveness of proposed HCNN.