Multiscale Attention Networks for Pavement Defect Detection

计算机科学 卷积(计算机科学) 编码器 像素 卷积神经网络 特征(语言学) 人工智能 比例(比率) 模式识别(心理学) 水准点(测量) 特征提取 数据挖掘 人工神经网络 大地测量学 量子力学 物理 语言学 哲学 地理 操作系统
作者
Junde Chen,Yuxin Wen,Yaser A. Nanehkaran,Defu Zhang,Adnan Zeb
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:72: 1-12 被引量:25
标识
DOI:10.1109/tim.2023.3298391
摘要

Pavement defects such as cracks, net cracks, and pit slots can cause potential traffic safety problems. The timely detection and identification play a key role in reducing the harm of various pavement defects. Particularly, the recent development in deep learning-based CNNs has shown competitive performance in image detection and classification. To detect pavement defects automatically and improve effects, a multi-scale mobile attention-based network, which we termed MANet, is proposed to perform the detection of pavement defects. The architecture of the encoder-decoder is used in MANet, where the encoder adopts the MobileNet as the backbone network to extract pavement defect features. Instead of the original 3×3 convolution, the multi-scale convolution kernels are utilized in depth-wise separable convolution layers of the network. Further, the hybrid attention mechanism is separately incorporated into the encoder and decoder modules to infer the significance of spatial points and inter-channel relationship features for the input intermediate feature maps. The proposed approach achieves state-of-the-art performance on two publicly-available benchmark datasets, i.e., the Crack500 (500 crack images with 2,000×1,500 pixels) and CFD (118 crack images with 480×320 pixels) datasets. The mean intersection over union ( MIoU ) of the proposed approach on these two datasets reaches 0.7219 and 0.7788, respectively. Ablation experiments show that the multi-scale convolution and hybrid attention modules can effectively help the model extract high-level feature representations and generate more accurate pavement crack segmentation results. We further test the model on locally collected pavement crack images (131 images with 1024×768 pixels) and it achieves a satisfactory result. The proposed approach realizes the MIoU of 0.6514 on the local dataset and outperforms other compared baseline methods. Experimental findings demonstrate the validity and feasibility of the proposed approach and it provides a viable solution for pavement crack detection in practical application scenarios. Our code is available at https://github.com/xtu502/pavement-defects.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
xieyuanxing完成签到,获得积分10
1秒前
3秒前
3秒前
白鹭立雪完成签到,获得积分10
4秒前
书生完成签到,获得积分10
5秒前
刘佳敏完成签到 ,获得积分10
5秒前
mhy完成签到 ,获得积分10
5秒前
6秒前
Chiuchiu完成签到,获得积分10
8秒前
3366ll完成签到 ,获得积分10
8秒前
铎铎铎完成签到 ,获得积分10
8秒前
迷人的天抒应助清修采纳,获得10
9秒前
划水完成签到,获得积分10
9秒前
英吉利25发布了新的文献求助10
10秒前
11完成签到 ,获得积分10
10秒前
静默向上发布了新的文献求助10
12秒前
韭菜盒子完成签到,获得积分20
12秒前
12秒前
831143完成签到 ,获得积分0
12秒前
wwww完成签到 ,获得积分10
15秒前
15秒前
16秒前
my完成签到 ,获得积分10
18秒前
ll完成签到 ,获得积分10
19秒前
大豆终结者完成签到,获得积分10
19秒前
djbj2022发布了新的文献求助10
20秒前
忽忽完成签到,获得积分10
20秒前
22秒前
24秒前
26秒前
wanci应助韭黄采纳,获得10
26秒前
Silieze完成签到,获得积分10
26秒前
郑zhenglanyou完成签到,获得积分10
27秒前
sherwing2009发布了新的文献求助10
29秒前
小美猪完成签到,获得积分10
30秒前
xiaomeng完成签到,获得积分10
30秒前
英吉利25发布了新的文献求助10
30秒前
研友_ZzrWKZ完成签到 ,获得积分10
30秒前
典雅的语海完成签到,获得积分10
31秒前
静默向上完成签到,获得积分10
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968578
求助须知:如何正确求助?哪些是违规求助? 3513393
关于积分的说明 11167478
捐赠科研通 3248836
什么是DOI,文献DOI怎么找? 1794499
邀请新用户注册赠送积分活动 875131
科研通“疑难数据库(出版商)”最低求助积分说明 804664