Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/24/12786 |
| _version_ | 1797461631880396800 |
|---|---|
| author | Muhammad Tanveer Byunghyun Kim Jonghwa Hong Sung-Han Sim Soojin Cho |
| author_facet | Muhammad Tanveer Byunghyun Kim Jonghwa Hong Sung-Han Sim Soojin Cho |
| author_sort | Muhammad Tanveer |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T17:22:11Z |
| format | Article |
| id | doaj.art-7e9437b6c373442db08fe697e1a38afb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:22:11Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7e9437b6c373442db08fe697e1a38afb2023-11-24T13:04:58ZengMDPI AGApplied Sciences2076-34172022-12-0112241278610.3390/app122412786Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage DetectionMuhammad Tanveer0Byunghyun Kim1Jonghwa Hong2Sung-Han Sim3Soojin Cho4Department of Civil Engineering, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of KoreaDepartment of Civil Engineering, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of KoreaSchool of Civil, Architectural Engineering and Landscape Architecture, Sungkyunkwan University, 2066 Seoburo, Jangan-gu, Suwon 16419, Republic of KoreaSchool of Civil, Architectural Engineering and Landscape Architecture, Sungkyunkwan University, 2066 Seoburo, Jangan-gu, Suwon 16419, Republic of KoreaDepartment of Civil Engineering, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of KoreaInnovative 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.https://www.mdpi.com/2076-3417/12/24/12786computer visionedge computing devicedeep learninglightweight modelsdamage detection |
| spellingShingle | Muhammad Tanveer Byunghyun Kim Jonghwa Hong Sung-Han Sim Soojin Cho Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection Applied Sciences computer vision edge computing device deep learning lightweight models damage detection |
| title | Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection |
| title_full | Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection |
| title_fullStr | Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection |
| title_full_unstemmed | Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection |
| title_short | Comparative Study of Lightweight Deep Semantic Segmentation Models for Concrete Damage Detection |
| title_sort | comparative study of lightweight deep semantic segmentation models for concrete damage detection |
| topic | computer vision edge computing device deep learning lightweight models damage detection |
| url | https://www.mdpi.com/2076-3417/12/24/12786 |
| work_keys_str_mv | AT muhammadtanveer comparativestudyoflightweightdeepsemanticsegmentationmodelsforconcretedamagedetection AT byunghyunkim comparativestudyoflightweightdeepsemanticsegmentationmodelsforconcretedamagedetection AT jonghwahong comparativestudyoflightweightdeepsemanticsegmentationmodelsforconcretedamagedetection AT sunghansim comparativestudyoflightweightdeepsemanticsegmentationmodelsforconcretedamagedetection AT soojincho comparativestudyoflightweightdeepsemanticsegmentationmodelsforconcretedamagedetection |