An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.

Closing the gap: Improved bounds on optimal POMDP solutions

POMDP algorithms have made significant progress in recent years by allowing practitioners to find good solutions to increasingly large problems. Most approaches (including point-based and policy iteration techniques) operate by refining a lower bound of the optimal value function. Several approaches (e.g., HSVI2, SARSOP, grid-based approaches and online forward search) also refine an upper bound. However, approximating the optimal value function by an upper bound is computationally expensive and therefore tightness is often sacrificed to improve efficiency (e.g., sawtooth approximation). In this paper, we describe a new approach to efficiently compute tighter bounds by i) conducting a prioritized breadth first search over the reachable beliefs, ii) propagating upper bound improvements with an augmented POMDP and iii) using exact linear programming (instead of the sawtooth approximation) for upper bound interpolation. As a result, we can represent the bounds more compactly and significantly reduce the gap between upper and lower bounds on several benchmark problems. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.

Forecasting high-frequency futures returns using online langevin dynamics

Forecasting the returns of assets at high frequency is the key challenge for high-frequency algorithmic trading strategies. In this paper, we propose a jump-diffusion model for asset price movements that models price and its trend and allows a momentum strategy to be developed. Conditional on jump times, we derive closed-form transition densities for this model. We show how this allows us to extract a trend from high-frequency finance data by using a Rao-Blackwellized variable rate particle filter to filter incoming price data. Our results show that even in the presence of transaction costs our algorithm can achieve a Sharpe ratio above 1 when applied across a portfolio of 75 futures contracts at high frequency. © 2011 IEEE.

Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation

The safety of post-earthquake structures is evaluated manually through inspecting the visible damage inflicted on structural elements. This process is time-consuming and costly. In order to automate this type of assessment, several crack detection methods have been created. However, they focus on locating crack points. The next step, retrieving useful properties (e.g. crack width, length, and orientation) from the crack points, has not yet been adequately investigated. This paper presents a novel method of retrieving crack properties. In the method, crack points are first located through state-of-the-art crack detection techniques. Then, the skeleton configurations of the points are identified using image thinning. The configurations are integrated into the distance field of crack points calculated through a distance transform. This way, crack width, length, and orientation can be automatically retrieved. The method was implemented using Microsoft Visual Studio and its effectiveness was tested on real crack images collected from Haiti.

Automated Computation of the Fundamental Matrix for Vision-Based Construction Site Applications

Estimating the fundamental matrix (F), to determine the epipolar geometry between a pair of images or video frames, is a basic step for a wide variety of vision-based functions used in construction operations, such as camera-pair calibration, automatic progress monitoring, and 3D reconstruction. Currently, robust methods (e.g., SIFT + normalized eight-point algorithm + RANSAC) are widely used in the construction community for this purpose. Although they can provide acceptable accuracy, the significant amount of required computational time impedes their adoption in real-time applications, especially video data analysis with many frames per second. Aiming to overcome this limitation, this paper presents and evaluates the accuracy of a solution to find F by combining the use of two speedy and consistent methods: SURF for the selection of a robust set of point correspondences and the normalized eight-point algorithm. This solution is tested extensively on construction site image pairs including changes in viewpoint, scale, illumination, rotation, and moving objects. The results demonstrate that this method can be used for real-time applications (5 image pairs per second with the resolution of 640 × 480) involving scenes of the built environment.

Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

The commercial far-range (>10 m) spatial data collection methods for acquiring infrastructure’s geometric data are not completely automated because of the necessary manual pre- and/or post-processing work. The required amount of human intervention and, in some cases, the high equipment costs associated with these methods impede their adoption by the majority of infrastructure mapping activities. This paper presents an automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras. In this process SURF features are automatically detected and matched between each pair of stereo video frames. 3D coordinates of the matched feature points are then calculated via triangulation. The detected SURF features in two successive video frames are automatically matched and the RANSAC algorithm is used to discard mismatches. The quaternion motion estimation method is then used along with bundle adjustment optimization to register successive point clouds. The method was tested on a database of infrastructure stereo video streams. The validity and statistical significance of the results were evaluated by comparing the spatial distance of randomly selected feature points with their corresponding tape measurements.

Automated vision tracking of project related entities

Tracking of project related entities such as construction equipment, materials, and personnel is used to calculate productivity, detect travel path conflicts, enhance the safety on the site, and monitor the project. Radio frequency tracking technologies (Wi-Fi, RFID, UWB) and GPS are commonly used for this purpose. However, on large-scale sites, deploying, maintaining and removing such systems can be costly and time-consuming. In addition, privacy issues with personnel tracking often limits the usability of these technologies on construction sites. This paper presents a vision based tracking framework that holds promise to address these limitations. The framework uses videos from a set of two or more static cameras placed on construction sites. In each camera view, the framework identifies and tracks construction entities providing 2D image coordinates across frames. Combining the 2D coordinates based on the installed camera system (the distance between the cameras and the view angles of them), 3D coordinates are calculated at each frame. The results of each step are presented to illustrate the feasibility of the framework.

Detection of large-scale concrete columns for automated bridge inspection

There are over 600,000 bridges in the US, and not all of them can be inspected and maintained within the specified time frame. This is because manually inspecting bridges is a time-consuming and costly task, and some state Departments of Transportation (DOT) cannot afford the essential costs and manpower. In this paper, a novel method that can detect large-scale bridge concrete columns is proposed for the purpose of eventually creating an automated bridge condition assessment system. The method employs image stitching techniques (feature detection and matching, image affine transformation and blending) to combine images containing different segments of one column into a single image. Following that, bridge columns are detected by locating their boundaries and classifying the material within each boundary in the stitched image. Preliminary test results of 114 concrete bridge columns stitched from 373 close-up, partial images of the columns indicate that the method can correctly detect 89.7% of these elements, and thus, the viability of the application of this research.

Parameter optimization for automated concrete detection in image data

Several research studies have been recently initiated to investigate the use of construction site images for automated infrastructure inspection, progress monitoring, etc. In these studies, it is always necessary to extract material regions (concrete or steel) from the images. Existing methods made use of material's special color/texture ranges for material information retrieval, but they do not sufficiently discuss how to find these appropriate color/texture ranges. As a result, users have to define appropriate ones by themselves, which is difficult for those who do not have enough image processing background. This paper presents a novel method of identifying concrete material regions using machine learning techniques. Under the method, each construction site image is first divided into regions through image segmentation. Then, the visual features of each region are calculated and classified with a pre-trained classifier. The output value determines whether the region is composed of concrete or not. The method was implemented using C++ and tested over hundreds of construction site images. The results were compared with the manual classification ones to indicate the method's validity.

Toward automated generation of parametric BIMs based on hybrid video and laser scanning data

Only very few constructed facilities today have a complete record of as-built information. Despite the growing use of Building Information Modelling and the improvement in as-built records, several more years will be required before guidelines that require as-built data modelling will be implemented for the majority of constructed facilities, and this will still not address the stock of existing buildings. A technical solution for scanning buildings and compiling Building Information Models is needed. However, this is a multidisciplinary problem, requiring expertise in scanning, computer vision and videogrammetry, machine learning, and parametric object modelling. This paper outlines the technical approach proposed by a consortium of researchers that has gathered to tackle the ambitious goal of automating as-built modelling as far as possible. The top level framework of the proposed solution is presented, and each process, input and output is explained, along with the steps needed to validate them. Preliminary experiments on the earlier stages (i.e. processes) of the framework proposed are conducted and results are shown; the work toward implementation of the remainder is ongoing.

Automated On-Site Retrieval of Project Information

Among several others, the on-site inspection process is mainly concerned with finding the right design and specifications information needed to inspect each newly constructed segment or element. While inspecting steel erection, for example, inspectors need to locate the right drawings for each member and the corresponding specifications sections that describe the allowable deviations in placement among others. These information seeking tasks are highly monotonous, time consuming and often erroneous, due to the high similarity of drawings and constructed elements and the abundance of information involved which can confuse the inspector. To address this problem, this paper presents the first steps of research that is investigating the requirements of an automated computer vision-based approach to automatically identify “as-built” information and use it to retrieve “as-designed” project information for field construction, inspection, and maintenance tasks. Under this approach, a visual pattern recognition model was developed that aims to allow automatic identification of construction entities and materials visible in the camera’s field of view at a given time and location, and automatic retrieval of relevant design and specifications information.