TY - JOUR
T1 - Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection
AU - Tanveer, Muhammad
AU - Kim, Byunghyun
AU - Hong, Jonghwa
AU - Sim, Sung Han
AU - Cho, Soojin
N1 - Publisher Copyright:
© 2022 by the authors.
PY - 2022/12
Y1 - 2022/12
N2 - Innovative concrete structure maintenance now requires automated computer vision inspection. Modern edge computing devices (ECDs), such as smartphones, can serve as sensing and computational platforms and can be integrated with deep learning models to detect on-site damage. Due to the fact that ECDs have limited processing power, model sizes should be reduced to improve efficiency. This study compared and analyzed the performance of five semantic segmentation models that can be used for damage detection. These models are categorized as lightweight (ENet, CGNet, ESNet) and heavyweight (DDRNet-Slim23, DeepLabV3+ (ResNet-50)), based on the number of model parameters. All five models were trained and tested on the concrete structure dataset considering four types of damage: cracks, efflorescence, rebar exposure, and spalling. Overall, based on the performance evaluation and computational cost, CGNet outperformed the other models and was considered effective for the on-site damage detection application of ECDs.
AB - Innovative concrete structure maintenance now requires automated computer vision inspection. Modern edge computing devices (ECDs), such as smartphones, can serve as sensing and computational platforms and can be integrated with deep learning models to detect on-site damage. Due to the fact that ECDs have limited processing power, model sizes should be reduced to improve efficiency. This study compared and analyzed the performance of five semantic segmentation models that can be used for damage detection. These models are categorized as lightweight (ENet, CGNet, ESNet) and heavyweight (DDRNet-Slim23, DeepLabV3+ (ResNet-50)), based on the number of model parameters. All five models were trained and tested on the concrete structure dataset considering four types of damage: cracks, efflorescence, rebar exposure, and spalling. Overall, based on the performance evaluation and computational cost, CGNet outperformed the other models and was considered effective for the on-site damage detection application of ECDs.
KW - computer vision
KW - damage detection
KW - deep learning
KW - edge computing device
KW - lightweight models
UR - http://www.scopus.com/inward/record.url?scp=85144858094&partnerID=8YFLogxK
U2 - 10.3390/app122412786
DO - 10.3390/app122412786
M3 - Article
AN - SCOPUS:85144858094
SN - 2076-3417
VL - 12
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 24
M1 - 12786
ER -