Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

Amhaz, Rabih; Chambon, Sylvie; Idier, Jérôme; Baltazart, Vincent

doi:10.1109/tits.2015.2477675

Cited by 354 publications

(215 citation statements)

References 32 publications

(61 reference statements)

Supporting

Mentioning

213

Contrasting

Order By: Relevance

“…Selection of crack endpoints at step 1 Endpoints serve as seed points for initializing the search for shortest paths at step 2. According to [1], the choice of endpoints obeys two conditions: endpoints are the darkest pixels within P×P image subsets (with P = 8) and the grey level of each is lower than the following threshold:…”

Section: Improved Mps Methodology (Mps-v1)mentioning

confidence: 99%

“…This section briefly recalls the five steps of the MPS method in [1]. Assuming cracks match to darker pixels within pavement image, MPS is based on the selection of minimum paths and then, emphasizes the connectivity between crack pixels.…”

Section: General Synoptic Of Mpsmentioning

confidence: 99%

“…Fig. 1) consists in refining the crack skeleton and estimating the crack width along the crack skeleton (see [1,27] for details).…”

Section: General Synoptic Of Mpsmentioning

confidence: 99%

“…It has been shown in [1] that the crack skeleton reach a DICE similarity coefficient of about 50% and the post-processing stage further improves the segmentation performance by 30% to 40%. The latter rates may greatly vary from one image to one another depending on the complexity of the crack pattern.…”

Section: General Synoptic Of Mpsmentioning

confidence: 99%

“…The benchmarking of some existing techniques is provided in [1,[4][5][6][7]. One of the latest technique, namely the Minimal Path Selection (MPS) technique has shown to outperform the other methods at the pixel scale on simulated and field pavement images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Ongoing tests and improvements of the MPS algorithm for the automatic crack detection within grey level pavement images

Baltazart¹,

Nicolle²,

Yang

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-The MPS approach (Minimal Path Selection) has shown in [1] to provide robust and accurate segmentation of cracks within pavement images compared to other algorithms. As a counterpart, MPS suffers from a large computing time. In this paper, we present three different ongoing improvements to reduce the computing time and to improve the overall segmentation performance. Most of the work focuses on the first three steps of the algorithm which achieve the segmentation of the crack skeleton. This is at first the improvement of the MPS methodology under Matlab coding, then, the C language MPS version and finally, the first attempt to parallelize MPS under the GPU platform. The results on pavement images illustrate the achieved improvements in terms of better segmentation and faster computational time.

show abstract

Section: Improved Mps Methodology (Mps-v1)mentioning

confidence: 99%

Section: General Synoptic Of Mpsmentioning

confidence: 99%

“…Fig. 1) consists in refining the crack skeleton and estimating the crack width along the crack skeleton (see [1,27] for details).…”

Section: General Synoptic Of Mpsmentioning

confidence: 99%

Section: General Synoptic Of Mpsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ongoing tests and improvements of the MPS algorithm for the automatic crack detection within grey level pavement images

Baltazart¹,

Nicolle²,

Yang

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

Analysis of distributed database access path prediction based on recurrent neural network in internet of things

2019

Concurrency and Computation

View full text Add to dashboard Cite

For avoiding the phenomenon of congestion, delay, and jitter in thedatabase access path, it is necessary to study the prediction method of database access path. Predicted database access path has high delay and jitter when using existing database access path prediction method to predict the path. Therefore, a prediction method of database access path is proposed based on the recurrent neural network. A decision matrix is constructed and normalized based on the analytic hierarchy process. The evaluation value of the alternative transit data center is calculated by the arithmetic weighted average operator, and the transit data center is selected according to the evaluation result. The matter-element analysis model is used to establish the mapping relationship between the user experience quality and the network service quality parameters. Moreover, the user experience quality evaluation level objective function of the database access path prediction method is constructed. Through the objective function to obtain the optimal database access path, the database access path prediction is completed. The experimental results show that the delay of the database access path predicted by the proposed method is much lower than other methods. The jitter is less than 30 ms and the jitter is small, which verifies the effectiveness of the path prediction method. KEYWORDSaccess path, alternative transit data center, database, decision matrix, prediction method, recurrent neural network INTRODUCTIONLarge-scale databases copy user data to multiple databases to improve user service quality. 1 A large amount of data needs to be transmitted between these distributed databases. Measurement studies have shown that the traffic between databases already accounts for nearly half of the database export bandwidth. 2,3 To meet the peak bandwidth requirement of the application, the access path of the database needs to be predicted. The existing database access path prediction method predicts the optimal path with high delay and large jitter. It is necessary to analyze and study the database access path prediction method. 4Wang et al proposed a database access path prediction method based on the number limit and data transmission delay. 5 This method uses the distributed shortest path tree algorithm to collect the relevant information and sensing data of sensor nodes in the k + 1 hop communication range. The virtual force theory is used to calculate the virtual force of the sensor node and the resultant force of all virtual forces. Based on the current dwell time of the grid center and the next dwell grid center based on the number of stays, the size and direction of the resultant force are calculated; then, according to the location of the sensor node, the remaining energy and other information to find a better path to complete the database access path prediction. The delay of the path predicted by this method is higher.Luo and Liu proposed a database access path prediction method based on traffic gravitational field. 6 This method combines the...

show abstract

Deep learning‐based multi‐class damage detection for autonomous post‐disaster reconnaissance

Mondal

Jahanshahi

et al. 2020

Struct Control Health Monit

View full text Add to dashboard Cite

Timely assessment of damages induced to buildings due to an earthquake is critical for ensuring life safety, mitigating financial losses, and expediting the rehabilitation process as well as enhancing the structural resilience where resilience is measured by an infrastructure's capacity to restore full functionality post extreme events. Since manual inspection is expensive, time consuming and risky, low‐cost unmanned aerial vehicles or robots can be leveraged as a viable alternative for quick reconnaissance. Visual data captured by the sensors mounted on the robots can be analyzed, and the damages can be detected and classified autonomously. The present study proposes the use of deep learning‐based approaches to this end. Region‐based convolutional neural network (Faster RCNN) is exploited to detect four different damage types, namely, surface crack, spalling (which includes façade spalling and concrete spalling), and severe damage with exposed rebars and severely buckled rebars. The performance of the proposed approach is evaluated on manually annotated image data collected from reinforced concrete buildings damaged under several past earthquakes such as Nepal (2015), Taiwan (2016), Ecuador (2016), Erzincan (1992), Duzce (1999), Bingol (2003), Peru (2007), Wenchuan (2008), and Haiti (2010). Several experiments are presented in the paper to illustrate the capabilities, as well as the limitations, of the proposed approach for earthquake reconnaissance. It was observed that Inception‐ResNet‐v2 significantly outperforms the other networks considered in this study. The research outcome is a stepping stone forward to facilitate the autonomous assessment of buildings where this can be potentially useful for insurance companies, government agencies, and property owners.

show abstract

Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

Abstract: International audienc

Cited by 354 publications

References 32 publications

Ongoing tests and improvements of the MPS algorithm for the automatic crack detection within grey level pavement images

Ongoing tests and improvements of the MPS algorithm for the automatic crack detection within grey level pavement images

Analysis of distributed database access path prediction based on recurrent neural network in internet of things

Deep learning‐based multi‐class damage detection for autonomous post‐disaster reconnaissance

Contact Info

Product

Resources

About