Improvement of canny algorithm based on pavement edge detection

Zhao, Hongduo; Qin, Guofeng; Wang, Xingjian

doi:10.1109/cisp.2010.5646923

Cited by 158 publications

(100 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is partly due to the saliency value enhancement step as described in section 3, which has enhance the saliency of pixels with high conspicuity and suppressed those with low conspicuity. We also compare our method with five alternative pavement crack detection methods in the literature, i.e., threshold based methods (ICM [4] and NDHM [6]), edge based methods (BEMD + Sobel [1] and Canny [2]), and the frequency domain based method (Wavelet [3]). Because cracks are elongated, which are about 1 to 3 pixels wide, if a detected crack pixel is no more than 1 pixel away from the GT, we consider it as a true positive [5].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Pavement crack detection based on saliency and statistical features

Tang

Zhou

et al. 2013

2013 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Traditional pavement crack detection methods can not cope well with the complexity and diversity of noises in large image area. To solve this problem, we propose a novel unsupervised crack detection approach based on saliency and statistical features. The saliency is initially represented by a conspicuity map built from the intensity rarity and local contrast of image regions. Then spatial continuity of candidate crack pixels is measured based on the statistical features extracted in their neighborhood. This is followed by a Bayesian model to automatically update the saliency map. Finally, cracks are extracted after adaptive saliency map binarization. Experiments show that proposed method has generated consistent results as those by human visual inspection. The results have also proved the effectiveness of the proposed method in suppressing noises compared with several alternative methods.

show abstract

Section: Resultsmentioning

confidence: 99%

“…To automate this process, some image-based crack detection and recognition methods have been reported in the past decade. These methods normally use curvilinear features to represent cracks, which can be extracted by Sobel-based algorithm [1], Canny edge detector [2], or Wavelet edge detection [3].…”

Section: Introductionmentioning

confidence: 99%

Pavement crack detection based on saliency and statistical features

Tang

Zhou

et al. 2013

2013 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

show abstract

“…There are many edge detection algorithms for image and video, such as Robert algorithm, wavelet transform, Canny algorithm, etc. [5], [6]. So, we can detect the edges of the image using above algorithm.…”

Section: Introductionmentioning

confidence: 98%

An improved particle filter algorithm for Target Tracking

Yang

et al. 2012

2012 IEEE International Conference on Intelligent Control, Automatic Detection and High-End Equipment

View full text Add to dashboard Cite

In order to track the object effectively in the real complex environment, the paper proposes an algorithm which fuses the color and edge feature to establish the object observation model. Color histogram which is not sensitive to the scale, rotation and deformation is a global description of the target and it is suitable to apply to tracking of the shelter and non-rigid object. However, particle filter tracking algorithm based on color cannot track the object correctly when in the condition of illumination changes and similar color clutters. Edge direction histogram contains some information about the structure of space, it can complement the information of the object when we create the observation model. Experiment results show that, the fusion algorithm can effectively overcome the similar color interference, occlusion, rotation, illumination and other issues, and improves the tracking accuracy, and has highly robust.

show abstract

“…In recent decades, some algorithms for image processing have been widely used to detect road cracks. In early studies, many researchers adopted methods related to threshold [12], edge detection [13,14] and morphology [15] based on photometric and geometric hypotheses to improve the accuracy of road crack detection.…”

Section: Introductionmentioning

confidence: 99%

Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement

et al. 2020

View full text Add to dashboard Cite

Automated pavement crack detection and measurement are important road issues. Agencies have to guarantee the improvement of road safety. Conventional crack detection and measurement algorithms can be extremely time-consuming and low efficiency. Therefore, recently, innovative algorithms have received increased attention from researchers. In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement. Specifically, an ensemble of convolutional neural networks was employed to identify the structure of small cracks with raw images. Secondly, outputs of the individual convolutional neural network model for the ensemble were averaged to produce the final crack probability value of each pixel, which can obtain a predicted probability map. Finally, the predicted morphological features of the cracks were measured by using the skeleton extraction algorithm. To validate the proposed method, some experiments were performed on two public crack databases (CFD and AigleRN) and the results of the different state-of-theart methods were compared. To evaluate the efficiency of crack detection methods, three parameters were considered: precision (Pr), recall (Re) and F1 score (F1). For the two public databases of pavement images, the proposed method obtained the highest values of the three evaluation parameters: for the CFD database, Pr = 0.9552, Re = 0.9521 and F1 = 0.9533 (which reach values up to 0.5175 higher than the values obtained on the same database with the other methods), for the AigleRN database, Pr = 0.9302, Re = 0.9166 and F1 = 0.9238 (which reach values up to 0.7313 higher than the values obtained on the same database with the other methods). The experimental results show that the proposed method outperforms the other methods. For crack measurement, the crack length and width can be measure based on different crack types (complex, common, thin, and intersecting cracks.). The results show that the proposed algorithm can be effectively applied for crack measurement.

show abstract

Improvement of canny algorithm based on pavement edge detection

Cited by 158 publications

References 3 publications

Pavement crack detection based on saliency and statistical features

Pavement crack detection based on saliency and statistical features

An improved particle filter algorithm for Target Tracking

Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement

Contact Info

Product

Resources

About