Deep Learning Based Automatic Crack Detection and Segmentation for Unmanned Aerial Vehicle Inspections

Liu, Kangcheng; Han, Xiaodong; Chen, Ben M.

doi:10.1109/robio49542.2019.8961534

Cited by 31 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noted that the augmentation method used for SYDcrack and CrackForest is by cropping rather than resizing as in Crack500. Since resizing can generally weaken the representation of features with fewer details, DCD and GAPs are used here in the original size from the source provided by [44] with a higher fidelity level.…”

Section: A Comparison With Results From Different Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

et al. 2021

View full text Add to dashboard Cite

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure (AF β ) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of AF β while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.INDEX TERMS deep learning, crack detection, hierarchical convolutional neural network, feature preserving, thresholding.

show abstract

Section: A Comparison With Results From Different Frameworkmentioning

confidence: 99%

“…• GAPs [43]: containing 509 images of pavement cracks with densely granular backgrounds under poor light conditions. DCD and GAPs are both integrated into an unified size of 448 × 448, following [44].…”

Section: ) Datasetsmentioning

confidence: 99%

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…They reported a precision value of 95.17% (F 1score not given). Liu et al proposed a method in (Liu, Han et al, 2019), which they also named CrackNet as in (Zhang et al, 2017). It is based on an FPN and performs with an F 1score of 86.5%.…”

Section: Related Workmentioning

confidence: 99%

A sigmoid‐optimized encoder–decoder network for crack segmentation with copy‐edit‐paste transfer learning

Çelik

König

2022

Computer aided Civil Eng

View full text Add to dashboard Cite

The automatic recognition of cracks is an essential requirement for the cost‐efficient maintenance of concrete structures, such as bridges, buildings, and roads. It should allow the localization and the determination of the crack type and the evaluation of the crack severity by providing information on the shape, orientation, and crack area and width. The first step in this direction is the automatized segmentation of cracks. This paper provides a concrete crack data set (370 images) and proposes two solutions that achieve the best results on two different crack data sets. Our first solution concerns the segmentation architecture. We provide an encoder–decoder‐based network with a particular interconnection of layers between the encoder and decoder parts that outperforms several other methods. In addition, this network is enhanced by squeeze‐and‐excitation blocks equipped with a modified sigmoid activation function. We introduce a stretch coefficient into the sigmoid function and declare it a trainable parameter, allowing more differentiated calibration of the feature map during network training. Our second solution concerns kernel initialization by transfer learning (TL). We propose the Copy‐Edit‐Paste Transfer Learning (CEP TL). By copying, geometric editing, and pasting crack masks onto new concrete background images, we generate thousands of semisynthetic images used to pretrain the network. This CEP TL method increases model performance with significant differences. For data set A (ours), we achieve F1‐scores 76.06 ± 0.06% without CEP TL and 92.32 ± 0.82% with CEP TL. For data set B (DeepCrack data set), we achieve F1‐scores 88.56 ± 0.01% without CEP TL and 90.59 ± 0.80% with CEP TL.

show abstract

“…1. It can also incrementally execute to tackle dynamic changes in the environment, referred to as incremental transform, which is particularly useful for applications that rely on online trajectory generation, e.g., robotic explorations [8]- [11], Micro Aerial Vehicle (MAV) based inspections and transportations [12]- [15]. However, EDT is a computationally expensive algorithm.…”

Section: Introductionmentioning

confidence: 99%

VDB-EDT: An Efficient Euclidean Distance Transform Algorithm Based on VDB Data Structure

Zhu¹,

Wang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a fundamental algorithm, called VDB-EDT, for Euclidean distance transform (EDT) based on the VDB data structure. The algorithm executes on grid maps and generates the corresponding distance field for recording distance information against obstacles, which forms the basis of numerous motion planning algorithms. The contributions of this work mainly lie in three folds. Firstly, we propose a novel algorithm that can facilitate distance transform procedures by optimizing the scheduling priorities of transform functions, which significantly improves the running speed of conventional EDT algorithms. Secondly, we for the first time introduce the memoryefficient VDB data structure, a customed B+ tree, to represent the distance field hierarchically. Benefiting from the special index and caching mechanism, VDB shows a fast (average O(1)) random access speed, and thus is very suitable for the frequent neighborsearching operations in EDT. Moreover, regarding the small scale of existing datasets, we release a large-scale dataset captured from subterranean environments to benchmark EDT algorithms. Extensive experiments on the released dataset and publicly available datasets show that VDB-EDT can reduce memory consumption by about 30%-85%, depending on the sparsity of the environment, while maintaining a competitive running speed with the fastest array-based implementation. The experiments also show that VDB-EDT can significantly outperform the stateof-the-art EDT algorithm in both runtime and memory efficiency, which strongly demonstrates the advantages of our proposed method. The released dataset and source code are available on https://github.com/zhudelong/VDB-EDT.

show abstract

Deep Learning Based Automatic Crack Detection and Segmentation for Unmanned Aerial Vehicle Inspections

Cited by 31 publications

References 22 publications

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

A sigmoid‐optimized encoder–decoder network for crack segmentation with copy‐edit‐paste transfer learning

VDB-EDT: An Efficient Euclidean Distance Transform Algorithm Based on VDB Data Structure

Contact Info

Product

Resources

About