Automatic Crack Segmentation for UAV-Assisted Bridge Inspection

Ayele, Yonas Zewdu; Aliyari, Mostafa; Griffiths, David; Droguett, Enrique López

doi:10.3390/en13236250

Cited by 77 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They used a custom-built hexacopter with a payload capacity of 110 g and a 20 min flight time. Yunas Zewdu Ayele (2020) [45] proposed a methodology for a UAV-based bridge inspection to assess bridge damage using novel technologies. Their methodology for bridge inspection involves collecting data and training a model which enables modifying drone flights to obtain optimum efficiency.…”

Section: Aeryon Skyrangermentioning

confidence: 99%

Impact of UAV Hardware Options on Bridge Inspection Mission Capabilities

Ameli

Aremanda

Friess

et al. 2022

Drones

View full text Add to dashboard Cite

Uncrewed Aerial Vehicles (UAV) constitute a rapidly evolving technology field that is becoming more accessible and capable of supplementing, expanding, and even replacing some traditionally manual bridge inspections. Given the classification of the bridge inspection types as initial, routine, in-depth, damage, special, and fracture critical members, specific UAV mission requirements can be developed, and their suitability for UAV application examined. Results of a review of 23 applications of UAVs in bridge inspections indicate that mission sensor and payload needs dictate the UAV configuration and size, resulting in quadcopter configurations being most suitable for visual camera inspections (43% of visual inspections use quadcopters), and hexa- and octocopter configurations being more suitable for higher payload hyperspectral, multispectral, and Light Detection and Ranging (LiDAR) inspections (13%). In addition, the number of motors and size of the aircraft are the primary drivers in the cost of the vehicle. 75% of vehicles rely on GPS for navigation, and none of them are capable of contact inspections. Factors that limit the use of UAVs in bridge inspections include the UAV endurance, the capability of navigation in GPS deprived environments, the stability in confined spaces in close proximity to structural elements, and the cost. Current research trends in UAV technologies address some of these limitations, such as obstacle detection and avoidance methods, autonomous flight path planning and optimization, and UAV hardware optimization for specific mission requirements.

show abstract

Section: Aeryon Skyrangermentioning

confidence: 99%

Impact of UAV Hardware Options on Bridge Inspection Mission Capabilities

Ameli

Aremanda

Friess

et al. 2022

Drones

View full text Add to dashboard Cite

show abstract

“…More details about establishing these UAV-based bridge inspection datasets are presented in the following sections. A DJI Matrice 100 with a Zenmuse Z3 aerial zoom camera and 7× zoom capacity was used to carry out the UAV-based bridge inspection; for more information, see [20]. As a result, images with 3000 × 4000 resolution were obtained; these high-resolution images allow for the capture of cropped images with high qualities (see images in Figure 3).…”

Section: Step 12-establishing Uav-based Bridge Inspection Datasetsmentioning

confidence: 99%

“…A wide variety of image processing methods and techniques are used in crack detection, including morphological approaches, digital image correlation, wavelet transform, median filtering, threshold methods, random structured forests, the photogrammetric technique, the recognition technique, and edge detectors such as the Canny, Sobel, Gabor, and Prewitt [9][10][11][12][13][14][15][16]. Recently, convolutional neural networks (CNNs) have gained a lot of attention and are widely used in the crack detection task [15,[17][18][19][20]. For instance, Shengyuan Li and Xuefeng Zhao designed a CNN architecture of binary-class output for crack detection by modifying the AlexNet architecture [17].…”

Section: Introductionmentioning

confidence: 99%

UAV-Based Bridge Inspection via Transfer Learning

2021

Self Cite

View full text Add to dashboard Cite

As bridge inspection becomes more advanced and more ubiquitous, artificial intelligence (AI) techniques, such as machine and deep learning, could offer suitable solutions to the nation’s problems of overdue bridge inspections. AI coupling with various data that can be captured by unmanned aerial vehicles (UAVs) enables fully automated bridge inspections. The key to the success of automated bridge inspection is a model capable of detecting failures from UAV data like images and films. In this context, this paper investigates the performances of state-of-the-art convolutional neural networks (CNNs) through transfer learning for crack detection in UAV-based bridge inspection. The performance of different CNN models is evaluated via UAV-based inspection of Skodsberg Bridge, located in eastern Norway. The low-level features are extracted in the last layers of the CNN models and these layers are trained using 19,023 crack and non-crack images. There is always a trade-off between the number of trainable parameters that CNN models need to learn for each specific task and the number of non-trainable parameters that come from transfer learning. Therefore, selecting the optimized amount of transfer learning is a challenging task and, as there is not enough research in this area, it will be studied in this paper. Moreover, UAV-based bridge inception images require specific attention to establish a suitable dataset as the input of CNN models that are trained on homogenous images. However, in the real implementation of CNN models in UAV-based bridge inspection images, there are always heterogeneities and noises, such as natural and artificial effects like different luminosities, spatial positions, and colors of the elements in an image. In this study, the effects of such heterogeneities on the performance of CNN models via transfer learning are examined. The results demonstrate that with a simplified image cropping technique and with minimum effort to preprocess images, CNN models can identify crack elements from non-crack elements with 81% accuracy. Moreover, the results show that heterogeneities inherent in UAV-based bridge inspection data significantly affect the performance of CNN models with an average 32.6% decrease of accuracy of the CNN models. It is also found that deeper CNN models do not provide higher accuracy compared to the shallower CNN models when the number of images for adoption to a specific task, in this case crack detection, is not large enough; in this study, 19,023 images and shallower models outperform the deeper models.

show abstract

“…These methods are effective for blurring of focus, but their effects have not been confirmed for "blurring" caused by camera movement. There have been recent studies on bridge inspections using a camera mounted on a mobile robot [10] or UAV [11][12][13]. In order to obtain the information necessary for bridge inspection from the images acquired by UAVs or mobile robots, it is necessary to perform advanced processing on the images, which is difficult to perform on a general-purpose PC.…”

Section: Introductionmentioning

confidence: 99%

Estimation and Sharpening of Blur in Degraded Images Captured by a Camera on a Moving Object

Hayashi

Tsubouchi

2022

Sensors

View full text Add to dashboard Cite

In this research, we aim to propose an image sharpening method to make it easy to identify concrete cracks from blurred images captured by a moving camera. This study is expected to help realize social infrastructure maintenance using a wide range of robotic technologies, and to solve the future labor shortage and shortage of engineers. In this paper, a method to estimate parameters of motion blur for Point Spread Function (PSF) is mainly discussed, where we assume that there are two main degradation factors caused by the camera, out-of-focus blur and motion blur. A major contribution of this paper is that the parameters can properly be estimated from a sub-image of the object under inspection if the sub-image contains uniform speckled texture. Here, the cepstrum of the sub-image is fully utilized. Then, a filter convoluted PSF which consists of convolution with PSF (motion blur) and PSF (out-of focus blur) can be utilized for deconvolution of the blurred image for sharpening with significant effect. PSF (out-of-focus blur) is a constant function unique to each camera and lens, and can be confirmed before or after shooting. PSF (motion blur), on the other hand, needs to be estimated on a case-by-case basis since the amount and direction of camera movement varies depending on the time of shooting. Previous research papers have sometimes encountered difficulties in estimating the parameters of motion blur because of the emphasis on generality. In this paper, the main object is made of concrete, and on the surface of it there are speckled textures. We hypothesized that we can narrow down the candidates of parameters of motion blur by using these speckled patterns. To verify this hypothesis, we conducted experiments to confirm and examine the following two points using a general-purpose camera used in actual bridge inspections: 1. Influence on the cepstrum when the isolated point-like texture unique to concrete structures is used as a feature point. 2. Selection method of multiple images to narrow down the candidate minima of the cepstrum. It is novel that the parameters of motion blur can be well estimated by using the unique speckled pattern on the surface of the object.

show abstract

Automatic Crack Segmentation for UAV-Assisted Bridge Inspection

Cited by 77 publications

References 33 publications

Impact of UAV Hardware Options on Bridge Inspection Mission Capabilities

Impact of UAV Hardware Options on Bridge Inspection Mission Capabilities

UAV-Based Bridge Inspection via Transfer Learning

Estimation and Sharpening of Blur in Degraded Images Captured by a Camera on a Moving Object

Contact Info

Product

Resources

About