Content Based Integration of Construction Site Images in AEC/FM Model Based Systems

The Architecture, Engineering, Construction and Facilities Management (AEC/FM) industry is rapidly becoming a multidisciplinary, multinational and multi-billion dollar economy, involving large numbers of actors working concurrently at different locations and using heterogeneous software and hardware technologies. Since the beginning of the last decade, a great deal of effort has been spent within the field of construction IT in order to integrate data and information from most computer tools used to carry out engineering projects. For this purpose, a number of integration models have been developed, like web-centric systems and construction project modeling, a useful approach in representing construction projects and integrating data from various civil engineering applications. In the modern, distributed and dynamic construction environment it is important to retrieve and exchange information from different sources and in different data formats in order to improve the processes supported by these systems. Previous research demonstrated that a major hurdle in AEC/FM data integration in such systems is caused by its variety of data types and that a significant part of the data is stored in semi-structured or unstructured formats. Therefore, new integrative approaches are needed to handle non-structured data types like images and text files. This research is focused on the integration of construction site images. These images are a significant part of the construction documentation with thousands stored in site photographs logs of large scale projects. However, locating and identifying such data needed for the important decision making processes is a very hard and time-consuming task, while so far, there are no automated methods for associating them with other related objects. Therefore, automated methods for the integration of construction images are important for construction information management. During this research, processes for retrieval, classification, and integration of construction images in AEC/FM model based systems have been explored. Specifically, a combination of techniques from the areas of image and video processing, computer vision, information retrieval, statistics and content-based image and video retrieval have been deployed in order to develop a methodology for the retrieval of related construction site image data from components of a project model. This method has been tested on available construction site images from a variety of sources like past and current building construction and transportation projects and is able to automatically classify, store, integrate and retrieve image data files in inter-organizational systems so as to allow their usage in project management related tasks.

Shape-Based Retrieval of Construction Site Photographs

Digital photographs of construction site activities are gradually replacing their traditional paper based counterparts. Existing digital imaging technologies in hardware and software make it easy for site engineers to take numerous photographs of “interesting” processes and activities on a daily basis. The resulting photographic data are evidence of the “as-built” project, and can therefore be used in a number of project life cycle tasks. However, the task of retrieving the relevant photographs needed in these tasks is often burdened by the sheer volume of photographs accumulating in project databases over time and the numerous objects present in each photograph. To solve this problem, the writers have recently developed a number of complementary techniques that can automatically classify and retrieve construction site images according to a variety of criteria (materials, time, date, location, etc.). This paper presents a novel complementary technique that can automatically identify linear (i.e., beam, column) and nonlinear (i.e., wall, slab) construction objects within the image content and use that information to enhance the performance of the writers’ existing construction site image retrieval approach.

Rapid entropy-based detection and properties measurement of concrete spalling with machine vision for post-earthquake safety assessments

The current procedures in post-earthquake safety and structural assessment are performed manually by a skilled triage team of structural engineers/certified inspectors. These procedures, and particularly the physical measurement of the damage properties, are time-consuming and qualitative in nature. This paper proposes a novel method that automatically detects spalled regions on the surface of reinforced concrete columns and measures their properties in image data. Spalling has been accepted as an important indicator of significant damage to structural elements during an earthquake. According to this method, the region of spalling is first isolated by way of a local entropy-based thresholding algorithm. Following this, the exposure of longitudinal reinforcement (depth of spalling into the column) and length of spalling along the column are measured using a novel global adaptive thresholding algorithm in conjunction with image processing methods in template matching and morphological operations. The method was tested on a database of damaged RC column images collected after the 2010 Haiti earthquake, and comparison of the results with manual measurements indicate the validity of the method.

Carbon nanotubes: carbon nanotube based high resolution holograms (adv. Mater. 44/2012).

By using carbon nanotubes as the smallest possible scattering element, light can be diffracted in a highly controlled manner to produce a 2D image, as reported by Haider Butt and co-workers on page OP331. An array of carbon nanotubes is elegantly patterned to produce a high resolution hologram. In response to incident light on the hologram, a high contrast and wide field of view "CAMBRIDGE" image is produced.

Carbon nanotube based high resolution holograms.

Carbon nanotubes are used as the smallest possible scattering element for diffracting light in a highly controlled manner to produce a 2D image. An array of carbon nanotubes is elegantly patterned to produce a high resolution hologram. In response to incident light on the hologram, a high contrast and wide field of view CAMBRIDGE image is produced.

On sparsity and overcompleteness in image models

Computational models of visual cortex, and in particular those based on sparse coding, have enjoyed much recent attention. Despite this currency, the question of how sparse or how over-complete a sparse representation should be, has gone without principled answer. Here, we use Bayesian model-selection methods to address these questions for a sparse-coding model based on a Student-t prior. Having validated our methods on toy data, we find that natural images are indeed best modelled by extremely sparse distributions; although for the Student-t prior, the associated optimal basis size is only modestly over-complete.

Learning based automatic face annotation for arbitrary poses and expressions from frontal images only

Statistical approaches for building non-rigid deformable models, such as the Active Appearance Model (AAM), have enjoyed great popularity in recent years, but typically require tedious manual annotation of training images. In this paper, a learning based approach for the automatic annotation of visually deformable objects from a single annotated frontal image is presented and demonstrated on the example of automatically annotating face images that can be used for building AAMs for fitting and tracking. This approach employs the idea of initially learning the correspondences between landmarks in a frontal image and a set of training images with a face in arbitrary poses. Using this learner, virtual images of unseen faces at any arbitrary pose for which the learner was trained can be reconstructed by predicting the new landmark locations and warping the texture from the frontal image. View-based AAMs are then built from the virtual images and used for automatically annotating unseen images, including images of different facial expressions, at any random pose within the maximum range spanned by the virtually reconstructed images. The approach is experimentally validated by automatically annotating face images from three different databases. © 2009 IEEE.

Atmospheric turbulence mitigation using complex wavelet-based fusion

Restoring a scene distorted by atmospheric turbulence is a challenging problem in video surveillance. The effect, caused by random, spatially varying, perturbations, makes a model-based solution difficult and in most cases, impractical. In this paper, we propose a novel method for mitigating the effects of atmospheric distortion on observed images, particularly airborne turbulence which can severely degrade a region of interest (ROI). In order to extract accurate detail about objects behind the distorting layer, a simple and efficient frame selection method is proposed to select informative ROIs only from good-quality frames. The ROIs in each frame are then registered to further reduce offsets and distortions. We solve the space-varying distortion problem using region-level fusion based on the dual tree complex wavelet transform. Finally, contrast enhancement is applied. We further propose a learning-based metric specifically for image quality assessment in the presence of atmospheric distortion. This is capable of estimating quality in both full-and no-reference scenarios. The proposed method is shown to significantly outperform existing methods, providing enhanced situational awareness in a range of surveillance scenarios. © 1992-2012 IEEE.

Optical holograms based on carbon nanotubes

The size of pixels is one of the key limiting features in the state of the art of holographic displays systems. The resolution and field of view in these systems are dictated by the size of the pixel (the smallest light scattering element). We have demonstrated the utilization of carbon nanotubes (nanostructures) as the smallest possible scattering element for diffracting light in a highly controlled manner to produce a two dimensional image. An array of carbon nanotubes was elegantly patterned to produce a high resolution hologram. In response to the incident light on the hologram a high contrast image was produced. Due to the nanoscale dimension of the carbon nanotube array the image presented a wide field of view and high resolution. These results pave way towards the utilization of nanostructures for producing 3D holograms with wide field of view and high resolution. © 2013 IEEE.

Identification of Prorocentrum minimum and Takayama pulchella by fluorescence in situ hybridization through epifluorescence microscopy and flow cytometry

Partial rDNA sequences of Prorocentrum minimum and Takayama pulchella were amplified, cloned and sequenced. and these sequence data were deposited in the GenBank. Eight oligonucleotide probes (DNA probes) were designed based on the sequence analysis. The probes were employed to detect and identify P. minimum and T. pulchella in unialgal and mixed algal samples with a fluorescence in situ hybridization method using flow cytometry. Epifluorescence micrographs showed that these specific probes labeled with fluorescein isothiocyanate entered the algal cells and bound to target sequences, and the fluorescence signal resulting from whole-cell hybridization varied from probe to probe. These DNA probes and the hybridization protocol we developed were specific and effective for P. minimum and T. pulchella, without any specific binding to other algal species. The hybridization efficiency of different probes specific to P. minimum was in the order: PM18S02 > PM28S02 > PM28S01 > PM18S01, and that of the probes specific to T. pulchella was TP18S02 > TP28S01 > TP28S02 > TP18S01. The different hybridization efficiency of the DNA probes could also be shown in the fluorescent signals between the labeled and unlabeled cells demonstrated using flow cytometry. The DNA probes PM18S02, PM28S02; TP18S02 and TP28S01, and the protocol, were also useful for the detection of algae in natural samples.

The role of cell-surface-bound phosphatases in species competition within natural phytoplankton assemblage: an in situ experiment

Despite it is widely acknowledged that the ability to hydrolyze dissolved organic matter using extracellular phosphatases is diverse in fresh water phytoplankton, the competition within single species related to presence and quantity of cell-surface-bound phosphatases has not been examined in natural conditions yet. Here, we studied phytoplankton species competition in a freshwater reservoir during an in situ experiment. A natural plankton community, with the exclusion of large zooplankton, was enclosed in permeable dialysis bags inside two large containers of different bioavailable phosphate concentrations. Phytoplankton species biomass and the abundance of bacteria were determined in purpose to compare the development of enclosed microbial communities. Total and cell-surface-bound phosphatase activities in the phytoplankton were investigated using the Fluorescently Labelled Enzyme Activity (FLEA) technique that allows for direct microscopic detection of phosphatase-positive cells and, with image cytometry, enables quantification of phosphatase hydrolytic capacity. Production of extracellular phosphatases was not completely inhibited or stopped in the phosphate-enriched environment, phytoplankton cells only showed the activity less often. Under the phosphate-nonenriched conditions, the production of phosphatases was enhanced, but active species did not proliferate amongst phytoplankton assemblage. Further, specific growth rates of the phosphatase-positive species in the non-enriched environment were lower than the same phosphatase-positive species in phosphate-enriched environment. Interestingly, the phosphatase-positive cells of Ankyra ancora increased their size in both treatments equally, although the population in phosphate-enriched environment grew much faster and the cell-specific phosphatase activity was lower. We hypothesize that brand new daughter cells had sufficient phosphorus reserves and therefore did not employ extracellular phosphatases until they matured and needed extra bioavailable phosphorus to support their metabolism before cell division. Based on presented in situ experiment, we propose that the ability to hydrolyze organic polymers and particles with cell-surface-hound phosphatases is advantageous for longer persistence of given population in a phosphate-scarce environment; although phosphatase-positive species cannot dominate the reservoir phytoplankton solely because of specific phosphorus-scavenging strategy.

Digits speech recognition based on geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems.We observe that this may be true for a recognition tasks based on geometrical learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions via the Hilbert transform. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy, Experiments show method based on ICA and geometrical learning outperforms HMM in different number of train samples.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Research of Face Location System Based on Human Vision Simulations

In this paper we present a robust face location system based on human vision simulations to automatically locate faces in color static images. Our method is divided into four stages. In the first stage we use a gauss low-pass filter to remove the fine information of images, which is useless in the initial stage of human vision. During the second and the third stages, our technique approximately detects the image regions, which may contain faces. During the fourth stage, the existence of faces in the selected regions is verified. Having combined the advantages of Bottom-Up Feature Based Methods and Appearance-Based Methods, our algorithm performs well in various images, including those with highly complex backgrounds.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.