More Like this

1. Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection

   https://doi.org/10.3390/s20164403  

   Billah, Umme Hafsa; La, Hung Manh; Tavakkoli, Alireza (August 2020, Sensors)

   null (Ed.)

   An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation, while addressing the effect of gradient vanishing problem. A feature silencing module is incorporated in the proposed framework, capable of eliminating non-discriminative feature maps from the network to improve performance. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network’s robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than the state-of-the-art crack detection architectures. 

   more » « less
2. Deep Learning-Based Crack Detection Using Mask R-CNN Technique

   Tan, Chenjun; Uddin, Nasim; Mohammed, Yahya M. (August 2019, 9 th International Conference on Structural Health Monitoring of Intelligent Infrastructure)

   Cracks of civil infrastructures, including bridges, dams, roads, and skyscrapers, potentially reduce local stiffness and cause material discontinuities, so as to lose their designed functions and threaten public safety. This inevitable process signifier urgent maintenance issues. Early detection can take preventive measures to prevent damage and possible failure. With the increasing size of image data, machine/deep learning based method have become an important branch in detecting cracks from images. This study is to build an automatic crack detector using the state-of-the-art technique referred to as Mask Regional Convolution Neural Network (R-CNN), which is kind of deep learning. Mask R-CNN technique is a recently proposed algorithm not only for object detection and object localization but also for object instance segmentation of natural images. It is found that the built crack detector is able to perform highly effective and efficient automatic segmentation of a wide range of images of cracks. In addition, this proposed automatic detector could work on videos as well; indicating that this detector based on Mask R-CNN provides a robust and feasible ability on detecting cracks exist and their shapes in real time on-site. 

   more » « less
3. Automated Transverse Crack Mapping System with Optical Sensors and Big Data Analytics

   https://doi.org/10.3390/s20071838  

   Won, Kwanghee; Sim, Chungwook (April 2020, Sensors)

   null (Ed.)

   Transverse cracks on bridge decks provide the path for chloride penetration and are the major reason for deck deterioration. For such reasons, collecting information related to the crack widths and spacing of transverse cracks are important. In this study, we focused on developing a data pipeline for automated crack detection using non-contact optical sensors. We developed a data acquisition system that is able to acquire data in a fast and simple way without obstructing traffic. Understanding that GPS is not always available and odometer sensor data can only provide relative positions along the direction of traffic, we focused on providing an alternative localization strategy only using optical sensors. In addition, to improve existing crack detection methods which mostly rely on the low-intensity and localized line-segment characteristics of cracks, we considered the direction and shape of the cracks to make our machine learning approach smarter. The proposed system may serve as a useful inspection tool for big data analytics because the system is easy to deploy and provides multiple properties of cracks. Progression of crack deterioration, if any, both in spatial and temporal scale, can be checked and compared if the system is deployed multiple times. 

   more » « less
4. Pruning deep convolutional neural networks for efficient edge computing in condition assessment of infrastructures

   https://doi.org/10.1111/mice.12449  

   Wu, Rih‐Teng; Singla, Ankush; Jahanshahi, Mohammad_R; Bertino, Elisa; Ko, Bong_Jun; Verma, Dinesh (May 2019, Computer-Aided Civil and Infrastructure Engineering)

   Abstract Health monitoring of civil infrastructures is a key application of Internet of things (IoT), while edge computing is an important component of IoT. In this context, swarms of autonomous inspection robots, which can replace current manual inspections, are examples of edge devices. Incorporation of pretrained deep learning algorithms into these robots for autonomous damage detection is a challenging problem since these devices are typically limited in computing and memory resources. This study introduces a solution based on network pruning using Taylor expansion to utilize pretrained deep convolutional neural networks for efficient edge computing and incorporation into inspection robots. Results from comprehensive experiments on two pretrained networks (i.e., VGG16 and ResNet18) and two types of prevalent surface defects (i.e., crack and corrosion) are presented and discussed in detail with respect to performance, memory demands, and the inference time for damage detection. It is shown that the proposed approach significantly enhances resource efficiency without decreasing damage detection performance. 

   more » « less
5. Mapping Electric Transmission Line Infrastructure from Aerial Imagery with Deep Learning

   https://doi.org/10.1109/IGARSS39084.2020.9323851  

   Hu, Wei; Alexander, Ben; Cathcart, Wendell; Hu, Atsushi; Nair, Varun; Zuo, Lin; Malof, Jordan; Collins, Leslie; Bradbury, Kyle (September 2020, IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium)

   null (Ed.)

   Access to electricity positively correlates with many beneficial socioeconomic outcomes in the developing world including improvements in education, health, and poverty. Efficient planning for electricity access requires information on the location of existing electric transmission and distribution infrastructure; however, the data on existing infrastructure is often unavailable or expensive. We propose a deep learning based method to automatically detect electric transmission infrastructure from aerial imagery and quantify those results with traditional object detection performance metrics. In addition, we explore two challenges to applying these techniques at scale: (1) how models trained on particular geographies generalize to other locations and (2) how the spatial resolution of imagery impacts infrastructure detection accuracy. Our approach results in object detection performance with an F1 score of 0.53 (0.47 precision and 0.60 recall). Using training data that includes more diverse geographies improves performance across the 4 geographies that we examined. Image resolution significantly impacts object detection performance and decreases precipitously as the image resolution decreases. 

   more » « less