Xingzhi Luo

Detection of cracks in computer tomography images of logs

Computer Tomography (CT) is being increasingly employed for automated detection and localization of internal defects in logs prior to their sawing. Reliable detection and localization of cracks in CT images of logs is particularly important from the viewpoint of lumber production planning since the presence of cracks substantially reduces the value and also compromises the structural strength of the resulting lumber. A crack is hard to detect in a cross-sectional CT image of a log because it has geometric properties and grayscale values that are similar to those associated with the ring structure of the log. In this paper, a method for crack detection is presented, which exploits the fact that the line defining the crack makes a significant non-zero angle with the log ring structure. Sobel-like operators are used to extract both, the line defining the crack and the contours corresponding to the grayscale valleys between two neighboring rings. Fork detection and grouping methods are subsequently employed to localize the actual crack line using a RANSAC-based line fitting procedure. Experimental results show the advantages of the proposed technique for crack detection when compared to techniques that employ straightforward grayscale histogram-based thresholding.

Automated Planning and Optimization of Lumber Production Using Machine Vision and Computed Tomography

An automated system for planning and optimization of lumber production using Machine Vision and Computed Tomography (CT) is proposed. Cross-sectional CT images of hardwood logs are analyzed using machine vision algorithms. Internal defects in the hardwood logs pockets are identified and localized. A virtual in silico 3-D reconstruction of the hardwood log and its internal defects is generated using Kalman filter-based tracking algorithms. Various sawing operations are simulated on the virtual 3-D reconstruction of the log and the resulting virtual lumber products automatically graded using rules stipulated by the National Hardwood Lumber Association (NHLA). Knowledge of the internal log defects is suitably exploited to formulate sawing strategies that optimize the value yield recovery of the resulting lumber products. A prototype implementation shows significant gains in value yield recovery when compared with lumber processing strategies that use only the information derived from the external log structure.

A Multiscale Parametric Background Model for Stationary Foreground Object Detection

Detection of stationary foreground objects within a dynamic scene is one of the goals of a video surveillance system. A parametric background maintenance and updating scheme, based on a multiple Gaussian mixture model that operates on multiple time scales, is proposed. Each color cluster in the proposed model is assigned a weight which measures the time duration and temporal recurrence frequency of the cluster. Sudden illumination changes are handled by using an adaptive histogram template whereas gradual illumination changes are automatically resolved with the adaptive background model. Stationary foreground objects are detected by maintaining their temporal history in the dynamic scene at multiple time scales. Experimental results show that the proposed scheme performs well in three distinct real-world settings.

Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring

Background updating is an important aspect of dynamic scene analysis. Three critical problems: sudden camera perturbation, sudden or gradual illumination change and the sleeping person problem, which arise frequently in realworld surveillance and monitoring systems, are addressed in the proposed scheme. The paper presents a multi-color model where multiple color clusters are used to represent the background at each pixel location. In the proposed background updating scheme, the updates to the mean and variance of each color cluster at each pixel location incorporate the most recently observed color values. Each cluster is assigned a weight which measures the time duration and temporal recurrence frequency of the cluster. The sleeping person problem is tackled by virtue of the observation that at a given pixel location, the time durations and recurrence frequencies of the color clusters representing temporarily static objects are smaller compared to those of color clusters representing the true background colors when measured over a sufficiently long temporal history. The camera perturbation problem is solved using a fast camera motion detection algorithm that allows the current background image to be registered with the background model maintained in memory. Sudden illumination changes are handled by using an adaptive histogram template whereas gradual illumination changes are automatically resolved with the adaptive background model. The background updating scheme is shown to be robust even when the scene is very busy and also computationally efficient, making it suitable for realtime traffic surveillance and monitoring systems. Experimental results on real traffic monitoring and surveillance videos are presented.

Real-Time and robust background updating for video surveillance and monitoring

Background updating is an important aspect of dynamic scene analysis. Two critical problems: sudden camera perturbation and the sleeping person problem, which arise frequently in real-world surveillance and monitoring systems, are addressed in the proposed scheme. The paper presents a multi-color model where multiple color clusters are used to represent the background at each pixel location. In the proposed background updating scheme, the updates to the mean and variance of each color cluster at each pixel location incorporate the most recently observed color values. Each cluster is assigned a weight which measures the time duration and temporal recurrence frequency of the cluster. The sleeping person problem is tackled by virtue of the observation that at a given pixel location, the time durations and recurrence frequencies of the color clusters representing temporarily static objects are smaller compared to those of color clusters representing the true background colors when measured over a sufficiently long history. The camera perturbation problem is solved using a fast camera motion detection algorithm, allowing the current background image to be registered with the background model maintained in memory. The background updating scheme is shown to be robust even when the scene is very busy and also computationally efficient, making it suitable for real-time surveillance and monitoring systems. Experimental results on real traffic monitoring and surveillance videos are presented.

Integrated detection and tracking of multiple faces using particle filtering and optical flow-based elastic matching

The design and implementation of a multiple face tracking framework that integrates face detection and face tracking is presented. Specifically, the incorporation of a novel proposal distribution and object shape model within the face tracking framework is proposed. A general solution that incorporates the most recent observation in the proposal distribution using a multiscale elastic matching-based optical flow algorithm is proposed. The proposed multiscale elastic matching-based optical flow algorithm is shown to be general and powerful in three significant ways. First, it allows for the tracking of both, rigid and elastic objects. Second, it enables robust tracking even in the face of sudden and gradual changes in illumination, scale and viewpoint. Third, it is suitable for tracking using both, fixed cameras and moving cameras. The proposed object shape model is based on a kernel-based line segment matching algorithm, which incorporates a voting scheme similar to the Radon Transform. The incorporation of the object shape model is shown to improve the computational complexity and accuracy of the face tracking algorithm and also enhance its robustness to occlusion, noise and scene clutter. Efficient techniques for particle sampling based on the Genetic Algorithm and for computation of the region-based likelihood function using the integral image are proposed. The incorporation of face detection within the face tracking algorithm is also proposed. Experimental results show that the proposed face tracking system is very robust in its ability to handle occlusion, noise, scene clutter and changes in illumination, scale and viewpoint and is also computationally efficient.

A novel feature-based tracking approach to the detection, localization, and 3-D reconstruction of internal defects in hardwood logs using computer tomography

A novel feature-based tracking approach based on the Kalman filter is proposed for the detection, localization, and 3-D reconstruction of internal defects in hardwood logs from cross-sectional computer tomography (CT) images. The defects are simultaneously detected, classified, localized, and reconstructed in 3-D space, making the proposed scheme computationally much more efficient than existing methods where the defects are detected and localized independently in individual CT image slices and the 3-D reconstruction of the defects accomplished via correspondence analysis across the various CT image slices. Robust techniques for defect detection and classification are proposed. Defect class-specific tracking schemes based on the Kalman filter, B-spline contour approximation, and Snakes contour fitting are designed which use the geometric parameters of the defect contours as the tracking variables. Experimental results on cross-sectional CT images of hardwood logs from select species such as white ash, hard maple, and red oak are presented.

Tracking of multiple objects using optical flow based multiscale elastic matching

A novel hybrid region-based and contour-based multiple object tracking model using optical flow based elastic matching is proposed. The proposed elastic matching model is general in two significant ways. First, it is suitable for tracking of both, rigid and deformable objects. Second, it is suitable for tracking using both, fixed cameras and moving cameras since the model does not rely on background subtraction. The elastic matching algorithm exploits both, the spectral features and contour-based features of the tracked objects, making it more robust and general in the context of object tracking. The proposed elastic matching algorithm uses a multiscale optical flow technique to compute the velocity field. This prevents the multiscale elastic matching algorithm from being trapped in a local optimum unlike conventional elastic matching algorithms that use a heuristic search procedure in the matching process. The proposed elastic matching based tracking framework is combined with Kalman filter in our current experiments. The multiscale elastic matching algorithm is used to compute the velocity field which is then approximated using B-spline surfaces. The control points of the B-spline surfaces are used directly as the tracking variables in a Kalman filtering model. The B-spline approximation of the velocity field is used to update the spectral features of the tracked objects in the Kalman filter model. The dynamic nature of these spectral features are subsequently used to reason about occlusion. Experimental results on tracking of multiple objects in real-time video are presented.

Nonparametric Background Modeling Using the CONDENSATION Algorithm

Background modeling for dynamic scenes is an important problem in the context of real time video surveillance systems. Several nonparametric background models have been proposed to model dynamic scenes and promising results have been reported. However, a critical problem with existing nonparametric models is their high computational requirement because a large set of background samples is usually needed to model the background. In this paper, a nonparametric background model that uses an importance sampling method is proposed to overcome the problem of high computational complexity of conventional nonparametric background models. Instead of using a large number of samples to model the background probability densities, much fewer background samples are maintained and updated using the CONDENSATION algorithm. A Markov Random Field model is used to enhance the foreground detection results by imposing spatial constraints. Experimental results show that the proposed method is much faster and computationally more efficient than existing nonparametric background models. The proposed technique is observed to match the capabilities of existing nonparametric background models in terms of being able to effectively model dynamic backgrounds but with greatly reduced computational complexity.

Multiple object tracking using elastic matching

A novel region-based multiple object tracking framework based on Kalman filtering and elastic matching is proposed. The proposed Kalman filtering-elastic matching model is general in two significant ways. First, it is suitable for tracking of both, rigid and elastic objects. Second, it is suitable for tracking using both, fixed cameras and moving cameras since the method does not rely on background subtraction. The elastic matching algorithm exploits both the spectral features and structural features of the tracked objects, making it more robust and general in the context of object tracking. The proposed tracking framework can be viewed as a generalized Kalman filter where the elastic matching algorithm is used to measure the velocity field which is then approximated using B-spline surfaces. The control points of the B-spline surfaces are directly used as the tracking variables in a grid-based Kalman filtering model. The limitations of the Gaussian distribution assumption in the Kalman filter are overcome by the large capture range of the elastic matching algorithm. The B-spline approximation of the velocity field is used to update the spectral features of the tracked objects in the grid-based Kalman filter model. The dynamic nature of these spectral features are subsequently used to reason about occlusion. Experimental results on tracking of multiple objects in real-time video are presented.