%0 Journal Article
%T Vision based Pixel-level Bridge Structural Damage Detection Using a Link ASPP Network
%A Wenlong Deng
%A Yongli Mou
%A Takahiro Kashiwa
%A Sergio Escalera
%A Kohei Nagai
%A Kotaro Nakayama
%A Yutaka Matsuo
%A Helmut Prendinger
%J Automation in Construction
%D 2020
%V 110
%F Wenlong Deng2020
%O HuPBA; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3314), last updated on Tue, 25 Oct 2022 12:18:16 +0200
%X Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface structural damage detection, such as delamination and rebar exposure. It is well known that the quality of a deep learning model is highly dependent on the quality of the training dataset. Bridge damage detection, our application domain, has the following main challenges: (i) labeling the damages requires knowledgeable civil engineering professionals, which makes it difficult to collect a large annotated dataset; (ii) the damage area could be very small, whereas the background area is large, which creates an unbalanced training environment; (iii) due to the difficulty to exactly determine the extension of the damage, there is often a variation among different labelers who perform pixel-wise labeling. In this paper, we propose a novel model for bridge structural damage detection to address the first two challenges. This paper follows the idea of an atrous spatial pyramid pooling (ASPP) module that is designed as a novel network for bridge damage detection. Further, we introduce the weight balanced Intersection over Union (IoU) loss function to achieve accurate segmentation on a highly unbalanced small dataset. The experimental results show that (i) the IoU loss function improves the overall performance of damage detection, as compared to cross entropy loss or focal loss, and (ii) the proposed model has a better ability to detect a minority class than other light segmentation networks.
%K Semantic image segmentation
%K Deep learning
%U https://doi.org/10.1016/j.autcon.2019.102973
%P 102973