Concrete column recognition in images and videos

The automated detection of structural elements (e.g., columns and beams) from visual data can be used to facilitate many construction and maintenance applications. The research in this area is under initial investigation. The existing methods solely rely on color and texture information, which makes them unable to identify each structural element if these elements connect each other and are made of the same material. The paper presents a novel method of automated concrete column detection from visual data. The method overcomes the limitation by combining columns’ boundary information with their color and texture cues. It starts from recognizing long vertical lines in an image/video frame through edge detection and Hough transform. The bounding rectangle for each pair of lines is then constructed. When the rectangle resembles the shape of a column and the color and texture contained in the pair of lines are matched with one of the concrete samples in knowledge base, a concrete column surface is assumed to be located. This way, one concrete column in images/videos is detected. The method was tested using real images/videos. The results are compared with the manual detection ones to indicate the method’s validity.

Automated Detection of Concrete Columns from Visual Data

After earthquakes, licensed inspectors use the established codes to assess the impact of damage on structural elements. It always takes them days to weeks. However, emergency responders (e.g. firefighters) must act within hours of a disaster event to enter damaged structures to save lives, and therefore cannot wait till an official assessment completes. This is a risk that firefighters have to take. Although Search and Rescue Organizations offer training seminars to familiarize firefighters with structural damage assessment, its effectiveness is hard to guarantee when firefighters perform life rescue and damage assessment operations together. Also, the training is not available to every firefighter. The authors therefore proposed a novel framework that can provide firefighters with a quick but crude assessment of damaged buildings through evaluating the visible damage on their critical structural elements (i.e. concrete columns in the study). This paper presents the first step of the framework. It aims to automate the detection of concrete columns from visual data. To achieve this, the typical shape of columns (long vertical lines) is recognized using edge detection and the Hough transform. The bounding rectangle for each pair of long vertical lines is then formed. When the resulting rectangle resembles a column and the material contained in the region of two long vertical lines is recognized as concrete, the region is marked as a concrete column surface. Real video/image data are used to test the method. The preliminary results indicate that concrete columns can be detected when they are not distant and have at least one surface visible.

Large Scale Column Detection for Bridge Inspection

Manually inspecting bridges is a time-consuming and costly task. There are over 600,000 bridges in the US, and not all of them can be inspected and maintained within the specified time frame as some state DOTs cannot afford the essential costs and manpower. This paper presents a novel method that can detect bridge concrete columns from visual data for the purpose of eventually creating an automated bridge condition assessment system. The method employs SIFT feature detection and matching to find overlapping areas among images. Affine transformation matrices are then calculated to combine images containing different segments of one column into a single image. Following that, the bridge columns are detected by identifying the boundaries in the stitched image and classifying the material within each boundary. Preliminary test results using real bridge images indicate that most columns in stitched images can be correctly detected and thus, the viability of the application of this research.

Testing of Depth-Encoded Hough Voting for Infrastructure Object Detection

The lack of viable methods to map and label existing infrastructure is one of the engineering grand challenges for the 21st century. For instance, over two thirds of the effort needed to geometrically model even simple infrastructure is spent on manually converting a cloud of points to a 3D model. The result is that few facilities today have a complete record of as-built information and that as-built models are not produced for the vast majority of new construction and retrofit projects. This leads to rework and design changes that can cost up to 10% of the installed costs. Automatically detecting building components could address this challenge. However, existing methods for detecting building components are not view and scale-invariant, or have only been validated in restricted scenarios that require a priori knowledge without considering occlusions. This leads to their constrained applicability in complex civil infrastructure scenes. In this paper, we test a pose-invariant method of labeling existing infrastructure. This method simultaneously detects objects and estimates their poses. It takes advantage of a recent novel formulation for object detection and customizes it to generic civil infrastructure scenes. Our preliminary experiments demonstrate that this method achieves convincing recognition results.

Enhancement of Construction Equipment Detection in Video Frames by Combining with Tracking

Vision-based object detection has been introduced in construction for recognizing and locating construction entities in on-site camera views. It can provide spatial locations of a large number of entities, which is beneficial in large-scale, congested construction sites. However, even a few false detections prevent its practical applications. In resolving this issue, this paper presents a novel hybrid method for locating construction equipment that fuses the function of detection and tracking algorithms. This method detects construction equipment in the video view by taking advantage of entities' motion, shape, and color distribution. Background subtraction, Haar-like features, and eigen-images are used for motion, shape, and color information, respectively. A tracking algorithm steps in the process to make up for the false detections. False detections are identified by catching drastic changes in object size and appearance. The identified false detections are replaced with tracking results. Preliminary experiments show that the combination with tracking has the potential to enhance the detection performance.

A flexural crack model for damage detection in reinforced concrete structures

The use of changes in vibration data for damage detection of reinforced concrete structures faces many challenges that obstruct its transition from a research topic to field applications. Among these is the lack of appropriate damage models that can be deployed in the damage detection methods. In this paper, a model of a simply supported reinforced concrete beam with multiple cracks is developed to examine its use for damage detection and structural health monitoring. The cracks are simulated by a model that accounts for crack formation, propagation and closure. The beam model is studied under different dynamic excitations, including sine sweep and single excitation frequency, for various damage levels. The changes in resonant frequency with increasing loads are examined along with the nonlinear vibration characteristics. The model demonstrates that the resonant frequency reduces by about 10% at the application of 30% of the ultimate load and then drops gradually by about 25% at 70% of the ultimate load. The model also illustrates some nonlinearity in the dynamic response of damaged beams. The appearance of super-harmonics shows that the nonlinearity is higher when the damage level is about 35% and then decreases with increasing damage. The restoring force-displacement relationship predicted the reduction in the overall stiffness of the damaged beam. The model quantitatively predicts the experimental vibration behaviour of damaged RC beams and also shows the damage dependency of nonlinear vibration behaviour. © 2011 Published under licence by IOP Publishing Ltd.

The sensitivity of vibration characteristics of reinforced concrete beams under incremental static and cyclic loading

The use of changes in vibration properties for global damage detection and monitoring of existing concrete structures has received great research attention in the last three decades. To track changes in vibration properties experimentally, structures have been artificially damaged by a variety of scenarios. However, this procedure does not represent realistically the whole design-life degradation of concrete structures. This paper presents experimental work on a set of damaged reinforced concrete beams due to different loading regimes to assess the sensitivity of vibration characteristics. Of the total set, three beams were subject to incremental static loading up to failure to simulate overloading, and two beams subject to 15 million loading cycles with varying amplitudes to produce an accelerated whole-life degradation scenario. To assess the vibration behaviour in both cases, swept sine and harmonic excitations were conducted at every damage level. The results show that resonant frequencies are not sensitive enough to damage due to cyclic loading, whereas cosh spectral and root mean square distances are more sensitive, yet more scattered. In addition, changes in non-linearity follow a softening trend for beams under incremental static loading, whilst they are significantly inconsistent for beams under cyclic loading. Amongst all examined characteristics, changes in modal stiffness are found to be most sensitive to damage and least scattered, but modal stiffness is tedious to compute due mainly to the difficulty of constructing restoring force surfaces from field measurements. © (2013) Trans Tech Publications.

Detection of microcystins in environmental samples using surface plasmon resonance biosensor

An indirect inhibitive surface plasmon resonance (SPR) immunoassay was developed for the microcystins (MCs) detection. The bioconjugate of MC-LR and bovine serum albumin (BSA) was immobilized on a CM5 sensor chip. A serial premixture of MC-LR standards (or samples) and monoclonal antibody (mAb) were injected over the functional sensor surface, and the subsequent specific immunoreaction was monitored on the BIAcore 3000 biosensor and generated a signal with an increasing intensity in response to the decreasing MCs concentration. The developed SPR immunoassay has a wide quantitative range in 1-100 mu g L-1. Although not as sensitive as conventional enzyme-linked immunosorbent assay (ELISA), the SPR biosensor offered unique advantages: (I) the sensor chip could be reusable without any significant loss in its binding activity after 50 assay-regeneration cycles, (2) one single assay could be accomplished in 50 min (including 30-min preincubation and 20-min BIAcore analysis), and (3) this method did not require multiple steps. The SPR biosensor was also used to detect MCs in environmental samples, and the results compared well with those obtained by ELISA. We conclude that the SPR biosensor offers outstanding advantages for the MCs detection and may be further developed as a field-portable sensor for real-time monitoring of MCs on site in the near future. (C) 2009 Published by Elsevier B.V.

Molecular characterization of Chinese sturgeon gonadotropins and cellular distribution in pituitaries of mature and immature individuals

Chinese sturgeon (Acipenser sinensis) is a rare and endangered species, and also an important resource for the sturgeon aquaculture industry. To understand molecular characterization of Chinese sturgeon gonadotropins (GTHs), we cloned the full-length cDNAs of gonadotropin subunits common alpha (GTH-alpha), follicle-stimulating hormone (FSH) and luteinizing hormone (LH) from a pituitary cDNA library of mature female. Two subtypes of GTH-alpha were identified. The nucleotide sequences of A. sinensis common alpha I (AsGTH-alpha I), common alpha II (AsGTH-alpha II), FSH beta (AsFSH beta) and LH beta (AsLH beta) subunit cDNAs are 345, 363, 387 and 414 bp in length, and encode mature peptides of 115, 121, 129 and 138 aa, respectively. Then, three polyclonal antibodies were prepared from the in vitro expressed AsGTH-alpha I, AsFSH beta and AsLH beta mature proteins, respectively. Significant expression differences were revealed between immature and mature sturgeon pituitaries. Western blot detection and immunofluoresence localization revealed the existence of three-gonadotropin subunits (AsGTH-alpha, AsFSH beta and AsLH beta) in mature sturgeon pituitaries, but only AsFSH beta was detected in immature individual pituitaries during early stages in the sturgeon life, and obvious difference was observed between males and females. In males, AsFSH beta was expressed in 4-year-old individuals, whereas in females, AsFSH beta was just expressed in 5-year-old individuals. (C) 2009 Elsevier Ireland Ltd. All rights reserved.

Development and characterization of monoclonal antibodies to spring viraemia of carp virus

Five monoclonal antibodies (mAbs) against spring viraemia of carp (SVCV0504, isolated from common carp in China) were produced from mice immunized with purified virus preparations. The virion of SVCV contains five structural proteins, representing the nucleoprotein (N), phosphoprotein (P), matrix protein (M), glycoprotein (G) and RNA-dependent RNA polymerase (Q. Western blotting analysis revealed that three mAbs (1145, IE10, and 11-17) recognized specifically to a single protein of 47 kDa (N), the mAb 3G4 reacted with, two SVCV0504 proteins of 69 kDa (G) and 47 kDa (N), while the mAb 1A9 reacted with three SVCV0504 proteins of 69 kDa (G), 50 kDa (P), and 47 kDa (N). By indirect ELISA, two mAbs (1H5 and 11-17) showed cross-reactivity with pike fry rhabdovirus (PFRV), but no cross-reactions with the Siniperca chuatsi rhabdovirus (SCRV), Scophthalmus maximus rhabdovirus (SMRV), Paralichthys olivaceus rhabdovirus (PoRV) were demonstrated with the five mAbs. Indirect immunofluorescence showed intense fluorescence in the cytoplasm of the SVCV0504-infected epithelioma papulosum cyprini (EPC) cells in areas corresponding to the location of granular structures. The sucrose gradient-purified SVCV0504 particles could be detected successfully by these mAbs using immunodot blotting. mAb 1A9 could completely neutralize 100 TCID50 (50% tissue culture infective dose) of SVCV0504 at a dilution of 1:8. This is the first report of development of the neutralizing mAbs against SVCV. The mAb 1A9 was analyzed further and could be used to successfully detect viral antigens in the infected-EPC cell cultures or in cryosections from experimentally infected crucian carp (Carassius auratus) by immunohistochemistry assay. Furthermore, a flow cytometry procedure for the detection and quantification of cytoplasmic SVCV0504 in cell cultures was developed with mAb 1A9. At 28 h after inoculation with the virus (0.01 PFU/cell), 10.12% of infected cells could be distinguished from the uninfected cells. These mAbs will be useful in diagnostic test development and pathogenesis studies for fish rhabdovirus. (c) 2008 Elsevier B.V. All rights reserved.

Achievements and challenges in machine vision-based inspection of large concrete structures

Large concrete structures need to be inspected in order to assess their current physical and functional state, to predict future conditions, to support investment planning and decision making, and to allocate limited maintenance and rehabilitation resources. Current procedures in condition and safety assessment of large concrete structures are performed manually leading to subjective and unreliable results, costly and time-consuming data collection, and safety issues. To address these limitations, automated machine vision-based inspection procedures have increasingly been proposed by the research community. This paper presents current achievements and open challenges in vision-based inspection of large concrete structures. First, the general concept of Building Information Modeling is introduced. Then, vision-based 3D reconstruction and as-built spatial modeling of concrete civil infrastructure are presented. Following that, the focus is set on structural member recognition as well as on concrete damage detection and assessment exemplified for concrete columns. Although some challenges are still under investigation, it can be concluded that vision-based inspection methods have significantly improved over the last 10 years, and now, as-built spatial modeling as well as damage detection and assessment of large concrete structures have the potential to be fully automated.

Single camera pose estimation using Bayesian filtering and Kinect motion priors

Traditional approaches to upper body pose estimation using monocular vision rely on complex body models and a large variety of geometric constraints. We argue that this is not ideal and somewhat inelegant as it results in large processing burdens, and instead attempt to incorporate these constraints through priors obtained directly from training data. A prior distribution covering the probability of a human pose occurring is used to incorporate likely human poses. This distribution is obtained offline, by fitting a Gaussian mixture model to a large dataset of recorded human body poses, tracked using a Kinect sensor. We combine this prior information with a random walk transition model to obtain an upper body model, suitable for use within a recursive Bayesian filtering framework. Our model can be viewed as a mixture of discrete Ornstein-Uhlenbeck processes, in that states behave as random walks, but drift towards a set of typically observed poses. This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information. Measurements are obtained using face detection and a simple skin colour hand detector, trained using the detected face. The suggested model is designed with analytical tractability in mind and we show that the pose tracking can be Rao-Blackwellised using the mixture Kalman filter, allowing for computational efficiency while still incorporating bio-mechanical properties of the upper body. In addition, the use of the proposed upper body model allows reliable three-dimensional pose estimates to be obtained indirectly for a number of joints that are often difficult to detect using traditional object recognition strategies. Comparisons with Kinect sensor results and the state of the art in 2D pose estimation highlight the efficacy of the proposed approach.

A novel hybrid phase-locked-loop frequency synthesizer using single-electron devices and CMOS transistors

This paper proposes a novel phase-locked loop (PLL) frequency synthesizer using single-electron devices (SEDs) and metal-oxide-semiconductor (MOS) field-effect transistors. The PLL frequency synthesizer mainly consists of a single-electron transistor (SET)/MOS hybrid voltage-controlled oscillator circuit, a single-electron (SE) turnstile/MOS hybrid phase-frequency detector (PFD) circuit and a SE turnstile/MOS hybrid frequency divider. The phase-frequency detection and frequency-division functions are realized by manipulating the single electrons. We propose a SPICE model to describe the behavior of the MOSFET-based SE turnstile. The authors simulate the performance of the PILL block circuits and the whole PLL synthesizer. Simulation results indicated that the circuit can well perform the operation of the PLL frequency synthesizer at room temperature. The PILL synthesizer is very compact. The total number of the transistors is less than 50. The power dissipation of the proposed PLL circuit is less than 3 uW. The authors discuss the effect of fabrication tolerance, the effect of background charge and the SE transfer accuracy on the performance of the PLL circuit. A technique to compensate parameter dispersions of SEDs is proposed.

CEC with tris(2,2 '-bipyridyl) ruthenium(II) electrochemiluminescent detection

For the first time, CEC was coupled with tris(2,2-bipyridyl) ruthenium(II) (Ru(bpy)(3)(2+) electrochemiluminescence detection. Efficient CEC separations of proline, putrescine, spermidine and spermine were achieved when the pH of the mobile phase is in the range of 3.5-7.0. The optimum mobile phase for CEC separation is much less acidic than that for CZE separation, which matches better with the optimum pH for Ru(bpy)(3)(2+) electrochemiluminescence detection and dramatically shortens the analysis time because of larger EOF at higher pH.

Determination of biogenic amines by capillary electrophoresis with pulsed amperometric detection

The biogenic amines, putrescine, cadaverine, spermidine and spermine were separated and quantified by capillary electrophoresis with pulsed amperometric detection. Detection potential of the pulsed amperometric detection was optimized as 0.6 V Optimal separation of the biogenic amines was achieved using a separation buffer of 30 mM citrate at pH 3.5, while keeping the buffer in the detection cell as 20 mM NaOH. Using these conditions, the four biogenic amines were baseline separated. Extrapolated limits of detection for putrescine, cadaverime, spermidine and spermine were 400, 200, 100 and 400 nM for the standard mixture (polyamines dissolved in running buffer), respectively. These are lower than ultraviolet detection and comparable or even lower than laser-induced fluorescence detection results as reported in the literature. The number of theoretical plates was maintained at the 105 level, which is absolutely higher than any reported method. When applying capillary electrophoresis-pulsed amperometric detection to milk analysis, only spermidine was found in amounts varying between 0.1 and 0.5 mg/kg.