Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet

With the progress of social life, the aging of building facilities has become an inevitable phenomenon. The efficiency of manual crack detection is limited, so it is necessary to explore intelligent detection technology. This article proposes a novel crack detection method TF-MobileNet. We took into...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiantao Yu, Songrong Qian, Cheng Chen
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/19/9004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283618699575296
author Jiantao Yu
Songrong Qian
Cheng Chen
author_facet Jiantao Yu
Songrong Qian
Cheng Chen
author_sort Jiantao Yu
collection DOAJ
description With the progress of social life, the aging of building facilities has become an inevitable phenomenon. The efficiency of manual crack detection is limited, so it is necessary to explore intelligent detection technology. This article proposes a novel crack detection method TF-MobileNet. We took into account the effect of lightweight and crack feature extraction, so we developed a novel crack feature extraction backbone network, which combined Transformer and MobileNetV3. Then we improved the feature fusion network by using the multi-headed attention mechanism of the Bottleneck Transformer, which enables the feature fusion effect to be improved. Then, we integrated SENet and SimAM attention mechanisms into the networks used for feature extraction and feature fusion, thereby further improving the crack detection performance. Finally, we deployed our model in edge devices (NVIDIA Jeston Nano). The findings indicate that our proposed model has achieved 90.8% mAP on the dataset and worked well on the edge device side, which meet the requirements of automatic crack detection. Our model enables real-time monitoring of pavement using edge devices. This approach allows for timely maintenance and repair of the pavement. In the future, we can train the model to recognize more pavement distress features, addressing road safety issues effectively.
format Article
id doaj-art-ee2a3b4b43ab4104938fa583b8bc69d5
institution OA Journals
issn 2076-3417
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ee2a3b4b43ab4104938fa583b8bc69d52025-08-20T01:47:44ZengMDPI AGApplied Sciences2076-34172024-10-011419900410.3390/app14199004Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNetJiantao Yu0Songrong Qian1Cheng Chen2School of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaState Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaWith the progress of social life, the aging of building facilities has become an inevitable phenomenon. The efficiency of manual crack detection is limited, so it is necessary to explore intelligent detection technology. This article proposes a novel crack detection method TF-MobileNet. We took into account the effect of lightweight and crack feature extraction, so we developed a novel crack feature extraction backbone network, which combined Transformer and MobileNetV3. Then we improved the feature fusion network by using the multi-headed attention mechanism of the Bottleneck Transformer, which enables the feature fusion effect to be improved. Then, we integrated SENet and SimAM attention mechanisms into the networks used for feature extraction and feature fusion, thereby further improving the crack detection performance. Finally, we deployed our model in edge devices (NVIDIA Jeston Nano). The findings indicate that our proposed model has achieved 90.8% mAP on the dataset and worked well on the edge device side, which meet the requirements of automatic crack detection. Our model enables real-time monitoring of pavement using edge devices. This approach allows for timely maintenance and repair of the pavement. In the future, we can train the model to recognize more pavement distress features, addressing road safety issues effectively.https://www.mdpi.com/2076-3417/14/19/9004TF-MobileNetautomatic crack detectionlightweightingattention mechanismedge deployment
spellingShingle Jiantao Yu
Songrong Qian
Cheng Chen
Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
Applied Sciences
TF-MobileNet
automatic crack detection
lightweighting
attention mechanism
edge deployment
title Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
title_full Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
title_fullStr Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
title_full_unstemmed Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
title_short Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet
title_sort lightweight crack automatic detection algorithm based on tf mobilenet
topic TF-MobileNet
automatic crack detection
lightweighting
attention mechanism
edge deployment
url https://www.mdpi.com/2076-3417/14/19/9004
work_keys_str_mv AT jiantaoyu lightweightcrackautomaticdetectionalgorithmbasedontfmobilenet
AT songrongqian lightweightcrackautomaticdetectionalgorithmbasedontfmobilenet
AT chengchen lightweightcrackautomaticdetectionalgorithmbasedontfmobilenet