Automatic pavement crack detection based on single stage salient-instance segmentation and concatenated feature pyramid network

Author(s):  
Gang Li ◽  
Dongchao Lan ◽  
Xuan Zheng ◽  
Xue Li ◽  
Jian Zhou
Author(s):  
Yongtao Yu ◽  
Haiyan Guan ◽  
Dilong Li ◽  
Yongjun Zhang ◽  
Shenghua Jin ◽  
...  

Author(s):  
Ирина Канаева ◽  
Irina Kanaeva ◽  
Юлия Иванова ◽  
Yuliya Ivanova

Robust automatic pavement crack detection is critical to automated road condition evaluation. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. This study makes literature review of road damage detection issues. The paper considers the existing datasets for detection and segmentation distress of road and asphalt pavement. A CNN for pavement cracks instance segmentation has been developed with the use of images from the driver's seat view. A method for generating a synthetic dataset is also presented, and effectiveness of its applicability to the current problem is evaluated. The relevance of the study is emphasized by research on pixel-level automatic damage detection remains a challenging problem, due to heterogeneous pixel intensity, complex crack topology, poor illumination condition, and noisy texture background.


2020 ◽  
Vol 21 (4) ◽  
pp. 1525-1535 ◽  
Author(s):  
Fan Yang ◽  
Lei Zhang ◽  
Sijia Yu ◽  
Danil Prokhorov ◽  
Xue Mei ◽  
...  

2020 ◽  
Vol 13 (6) ◽  
pp. 1-9
Author(s):  
CHEN Xiao-Dong ◽  
◽  
AI Da-Hang ◽  
ZHANG Jia-Chen ◽  
CAI Huai-Yu ◽  
...  

2021 ◽  
Vol 11 (3) ◽  
pp. 968
Author(s):  
Yingchun Sun ◽  
Wang Gao ◽  
Shuguo Pan ◽  
Tao Zhao ◽  
Yahui Peng

Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method.


2021 ◽  
Author(s):  
Nima Safaei ◽  
Omar Smadi ◽  
Babak Safaei ◽  
Arezoo Masoud

<p>Cracks considerably reduce the life span of pavement surfaces. Currently, there is a need for the development of robust automated distress evaluation systems that comprise a low-cost crack detection method for performing fast and cost-effective roadway health monitoring practices. Most of the current methods are costly and have labor-intensive learning processes, so they are not suitable for small local-level projects with limited resources or are only usable for specific pavement types.</p> <p>This paper proposes a new method that uses an improved version of the weighted neighborhood pixels segmentation algorithm to detect cracks in 2-D pavement images. This method uses the Gaussian cumulative density function as the adaptive threshold to overcome the drawback of fixed thresholds in noisy environments. The proposed algorithm was tested on 300 images containing a wide range of noise representative of different noise conditions. This method proved to be time and cost-efficient as it took less than 3.15 seconds per 320 × 480 pixels image for a Xeon (R) 3.70 GHz CPU processor to determine the detection results. This makes the model a perfect choice for county-level pavement maintenance projects requiring cost-effective pavement crack detection systems. The validation results were promising for the detection of low to severe-level cracks (Accuracy = 97.3%, Precision = 79.21%, Recall= 89.18% and F<sub>1</sub> score = 83.9%).</p>


2019 ◽  
Vol 1 (1) ◽  
Author(s):  
Hongwei Lei ◽  
Jianlian Cheng ◽  
Qi Xu

This article introduces the application of image recognition technology in cement pavement crack detection and put forward to method for determining threshold about grayscale stretching. the algorithm is designed about binarization which has a self-adaptive characteristic. After the image is preprocessed, we apply 2D Wavelet and Laplace operator to process the image. According to the characteristic of pixel of gray image, an algorithm designed on binarization for Binary image. The feasibility of this method can be verified the image processed by comparing with the results of three algorithms: Otsu method, iteration method and fixed threshold method.


Sign in / Sign up

Export Citation Format

Share Document