Bhattacharya, G, Puhan, NB and Mandal, B ORCID: https://orcid.org/0000-0001-8417-1410 (2022) Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition. Signal Processing: Image Communication, 108. 116818 - 116818.

[img] Text
CSDNetManuscript.pdf - Accepted Version
Restricted to Repository staff only until 18 July 2024.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (19MB)

Abstract

Image/video based defect recognition is a crucial task in automating visual inspection of concrete structures. Although some progress has been made to automatically recognize defects in concrete structural images, significant challenges still exist. In this work, we propose a deep convolutional neural network architecture that embeds novel spatial-channel interaction based concurrent attention (SCA) for multi-target, multi-class defect recognition. SCA module stems from novel kernel salient feature (KSF) encoder that captures higher-order features with robust discriminative representation of concrete defects. KSF encoder incorporates kernelized convolution followed by dynamic routing operation to be used as the primary building block. The proposed CSDNet architecture is able to apportion higher weightage in defective regions while suppressing large background area (healthy region), thereby improving recognition performance of overlapping defects in concrete structures. Experimental results and ablation study on four large benchmark datasets show consistent superiority of our proposed network as compared to current state-of-the-art methodologies. This end-to-end trainable architecture can be augmented with unmanned aerial vehicles (UAVs) to monitor health of massive infrastructures to leverage high concrete defect recognition performance.

Item Type: Article
Additional Information: The final version of this accepted manuscript can be accessed directly from the publisher. Refer to any relevant terms and conditions.
Uncontrolled Keywords: Kernel salient feature encoder; Spatial-channel attention; Concrete structural defect; Convolutional neural network; Multi-target multi-class classification
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Depositing User: Symplectic
Date Deposited: 11 Aug 2022 11:22
Last Modified: 11 Aug 2022 11:22
URI: https://eprints.keele.ac.uk/id/eprint/11249

Actions (login required)

View Item View Item