Robust data transmission and recovery of images by compressed sensing for structural health diagnosis

Abstract

SUMMARYDigital cameras are cost-effective vision sensors and able to directly provide two-dimensional information of structural condition in monitoring and assessment applications. For example, digital cameras are essential components of unmanned aerial vehicles (UAVs) and robotic agents for mobile sensing and inspection of pipelines, buildings, transportation infrastructure, etc, especially in post-natural disaster and man-made extreme events assessment. Additionally, while surveillance cameras have been widely used for transportation systems (e.g., traffic monitoring), if appropriately mounted on the large-scale structures such as the bridges, they can continuously monitor the structural condition under operational loads and hazards, complementing the regular visual inspection and assessment conducted by experts. In these or other applications, efficiently and reliably transferring the structural images or videos, which are as such largescale, are important and challenging, especially in wireless platform that is either required (e.g., UAVs and robotic agents) or more suitable (e.g., camera monitoring networks) with only limited power and communication resources. This paper studies the computational algorithms for efficient and reliable transmission of the structural monitoring images; in particular, the compressed sensing (CS) technique is explored for robust data transmission and recovery. The sparse representation or data structure of the structural images is exploited, leading to the CS based central strategy: on some sparse domain, randomly encode large-scale image data into few relevant coefficients, which are then transferred (robust to random data loss) and recovered (in base station) for subsequent structural health diagnosis. Image data of bench scale pipe structure, concrete structure and full scale stay cable are employed for validation of the CS based method. Its performance is also compared with traditional transform coding and low-dimensional encoding ( age data subjected to random data loss for structural health diagnosis. 2. Exploit the sparsity and randomness of compressed sensing for efficient and robust image data transmission. 3. Accurate image recovery without losing structural health diagnostic quality from highly undersampled measurements. 4. Demonstrations and comparisons with other methods by four structural images of laboratory and field settings.

Identification framework for cracks on a steel structure surface by a restricted Boltzmann machines algorithm based on consumer-grade camera images

“…Structural health monitoring systems have been widely implemented into bridges. Recently, advanced signal processing techniques, for example, blind feature extraction, sparse representation classification, and compressive sensing algorithm, have been successfully applied in the structural health monitoring and damage detection . However, the regular structural health monitoring is still hard to precisely capture the local damages (e.g., fatigue cracks) in time.…”

“…Recently, advanced signal processing techniques, for example, blind feature extraction, sparse representation classification, and compressive sensing algorithm, have been successfully applied in the structural health monitoring and damage detection. [5,6] However, the regular structural health monitoring is still hard to precisely capture the local damages (e.g., fatigue cracks) in time. The regular nondestructive testing, such as ultrasonic technique [7] and acoustic emission technique, [8] are frequently employed for crack damage detection in practice.…”

Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network

“…A data‐driven and unsupervised approach based on low rank and sparse separation was proposed for real‐time detection of local structural damage that required no parametric model or prior structural information for calibration . An efficient and reliable transmission for robust data recovery was investigated by the compressed sensing (CS) technique with the exploitation of sparse representation of the structural images . A new framework was developed for the blind extraction and realistic visualization of the full‐field, high‐resolution, dynamics behaviors of an operating structure from only its digital video measurements to localize nonvisible structural damage at a pixel resolution .…”

Surface damage quantification of postearthquake building based on terrestrial laser scan data

“…Image‐based evaluation methods, such as photographic and video imaging methods, have also been proposed for surface damage assessment . Most image‐based methods adopt two‐dimensional viewpoint, which is a critical limitation for crack depth quantification and restricts the collection of full spatial data.…”