Research Interests:
Integrating evidence from a single sensor over time is becoming more common due to the Internet of Things (IoT). It can play a critical role in Heritage site monitoring, as networks of sensors are required to catalog and analyze data over... more
Integrating evidence from a single sensor over time is becoming more common due to the Internet of Things (IoT). It can play a critical role in Heritage site monitoring, as networks of sensors are required to catalog and analyze data over extended periods of time. Researchers have often adopted the mechanisms used for multi-source integration, such as Bayesian conditioning and Dempster- Shafer reasoning. Research in human cognitive models provides an interesting alternative insights for accumulating evidence over time. We used this research as a foundation for the current approach which integrates the set theoretic nature of Dempster-Shafer theory with an estimation structure based on Kalman filtering. It is well suited for applications to Wide-area Sensor Networks (WSN) that are commonly found in heritage sites.
Research Interests:
Accurate and robust attention direction has been of substantial interest in the computer vision community, particularly for industrial surveillance systems that initiate recording at the onset of motion or an interesting contextual event.... more
Accurate and robust attention direction has been of substantial interest in the computer vision community, particularly for industrial surveillance systems that initiate recording at the onset of motion or an interesting contextual event. One key issue is minimizing false alarms to limit video record bandwidth and capacity. One issue that these systems face is high false alarm rates under sudden illumination change. In this paper we propose a system which applies measures from chaos theory and fractal analysis to provide a robust pre-attentive processing engine for motion detection. Results compare quite favorably in terms of probability of detection versus false detection rate against traditional methods for low-level change detection, namely Sum of Absolute Differences, and Gaussian Mixture Models. The proposed chaos-based method is shown to have superior performance. Additionally the proposed approach has an intuitive justification based on creation and flow of information between image frames, and consequently a very intuitive and problembased threshold determination.
Research Interests:
ABSTRACT Accurate and robust registration of image pairs is of interest in many fields that use computer vision such as surveillance and medical diagnostics. In each of these fields the area-based (or voxel-based) approach to image... more
ABSTRACT Accurate and robust registration of image pairs is of interest in many fields that use computer vision such as surveillance and medical diagnostics. In each of these fields the area-based (or voxel-based) approach to image registration is popular, however it is known that these methods are sensitive to illumination change where incorrect results are common. Past work in applying chaos theory to computer vision has demonstrated that the underlying physics of illumination change versus contextual change result in very different behavior when analyzed in phase space. Illumination is deterministic and results in non-fractal phase space behavior, while contextual change is chaos-like and results in complex fractal regions in phase space. A chaos-theoretic approach to image registration is presented with favorable results compared to the traditional and very popular Mutual Information measure.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Accurate and robust image motion detection has been of substantial interest in the image processing and computer vision communities. Unfortunately, no single motion detection algorithm has been universally superior; while biological... more
Accurate and robust image motion detection has been of substantial interest in the image processing and computer vision communities. Unfortunately, no single motion detection algorithm has been universally superior; while biological vision systems are adept at motion detection. Recent research in neural signals have shown biological neural systems are highly responsive to chaotic signals. In this paper, we analyze image sequences using frame-wise phase plots and demonstrate that the changes in pixel amplitudes due to the motion of objects in an image sequence, results in apparently chaotic behavior in phase space. We explore these chaotic phenomena in a variety of image datasets to show their repeatability, to validate the assumption of ergodicity, and to demonstrate their uniqueness from the changes due to illumination, particularly spatio-temporally varying illumination.
Research Interests:
ABSTRACT Recent research has demonstrated that tools from chaos theory can be applied to robustly detect motion and change in image sequences, even in the presence of spatiotemporally varying illumination. One key issue in digital imaging... more
ABSTRACT Recent research has demonstrated that tools from chaos theory can be applied to robustly detect motion and change in image sequences, even in the presence of spatiotemporally varying illumination. One key issue in digital imaging systems, however, is the effect of the quantization. This paper first demonstrates the effects of quantization on the phase space trajectories of pixel amplitudes and then proposes a method for addressing these effects by combining of multi-fractal measures with algebraic curve-based trajectory analysis to identify regions of the phase space with quantized chaotic trajectories. This proposed method is demonstrated in the application of object motion detection in video image sequences, but the results may prove applicable for other digitized information sources which may be produced by non-linear systems or processes.
Research Interests:
Research Interests:
ABSTRACT Recent research in neural signals have shown biological neural systems are highly responsive to chaotic signals. In this paper, we analyze image sequences using tools from chaos theory associated with the phase plot of time... more
ABSTRACT Recent research in neural signals have shown biological neural systems are highly responsive to chaotic signals. In this paper, we analyze image sequences using tools from chaos theory associated with the phase plot of time series signals. We demonstrate that the changes in pixel amplitudes due to the motion of objects in an image sequence result in interesting behavior, visible as fractal patterns in the phase space, reminiscent of chaotic strange attractors. Likewise we demonstrate that changes in image amplitude due to spatio-temporally varying illumination are non-chaotic and well structured in phase space. We use the Lambertian reflectance model to explain the source of the non-linearities responsible for this chaotic behavior.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Tools for automatic image understanding for managing operator workloads are essential. One common task for image analysts is the scanning large collections of real-time images looking for particular objects of interest. This task is... more
Tools for automatic image understanding for managing operator workloads are essential. One common task for image analysts is the scanning large collections of real-time images looking for particular objects of interest. This task is difficult to automate due to variable imaging geometries and environmental conditions. This variability of conditions can make automating image strong segmentation for eventual object classification extremely
Research Interests:
In recent decades, imaging became a very powerful tool, offering new possibilities for medical diagnostic investigations. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important source of information to... more
In recent decades, imaging became a very powerful tool, offering new possibilities for medical diagnostic investigations. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important source of information to improve cancer diagnosis; however, evaluation of an image is a challenging task, requiring automated means of assisting the human expert. Automatic detection implies there is a classification process to identify
Research Interests:
Accurate and robust tracking of humans is of growing interest in the image processing and computer vision communities. The ability of a vision system to track the subjects and accurately predict their future locations is critical to many... more
Accurate and robust tracking of humans is of growing interest in the image processing and computer vision communities. The ability of a vision system to track the subjects and accurately predict their future locations is critical to many surveillance and camera control applica- tions. Further, an inference of the type of motion as well as to rapidly detect and switch
Research Interests:
Page 1. The Effects of Motion and Spatio-temporal Non-uniform Illumination on Image-pair Joint Scattergrams Michael E. Farmer§ and Sushma Kittali* Department of Computer Science, Engineering Science and Physics, University ...
Research Interests:
Page 1. Application of Genetic Algorithms for Wrapper-based Image Segmentation and Classification Michael E. Farmer and David Shugars Department of Computer Science, Engineering Science, and Physics University of ...
Research Interests:
Tools for automatic image understanding for damage assessment for environmental catastrophes or military operations are essential for managing operator workloads. The paper proposes a tool which integrates image segmentation and... more
Tools for automatic image understanding for damage assessment for environmental catastrophes or military operations are essential for managing operator workloads. The paper proposes a tool which integrates image segmentation and classification with the goal of providing accurate and timely information about the areas of study. Traditional methods involving image segmentation followed by classification have not lived up to their potential
Research Interests:
Research Interests: Computer Science, Fuzzy set theory, Fuzzy Sets, State Estimation, Kalman Filter, and 13 moreImage Classification, Motion estimation, Kalman Filtering, Image fusion, Tracking, Motion Tracking, Real Time Systems, Object Recognition, Fuzzy Set, Evidential Reasoning, Safety Systems, Vision system, and Dempster Shafer
Research Interests:
Research Interests:
... We have developed a robust integrated segmentation and classification framework that addresses the above-mentioned ... The framework has been devel-oped and tested on the application of segmenting various occupants from the vehicle... more
... We have developed a robust integrated segmentation and classification framework that addresses the above-mentioned ... The framework has been devel-oped and tested on the application of segmenting various occupants from the vehicle interior to support a vision ...
Research Interests:
Research Interests:
Page 1. Large Scale Feature Selection Using Modified Random Mutation Hill Climbing Michael E. Farmer § , Shweta Bapna § , and Anil K. Jain* § Eaton Corporation * Michigan State University Email: farmerm3@msu.edu, bapnashw@egr.msu.edu,... more
Page 1. Large Scale Feature Selection Using Modified Random Mutation Hill Climbing Michael E. Farmer § , Shweta Bapna § , and Anil K. Jain* § Eaton Corporation * Michigan State University Email: farmerm3@msu.edu, bapnashw@egr.msu.edu, jain@cse.msu.edu Abstract ...
Research Interests:
Accurate and robust tracking of humans is of growing interest in the image processing and computer vision communities. The ability of a vision system to track the subjects and accurately predict their future locations is critical to many... more
Accurate and robust tracking of humans is of growing interest in the image processing and computer vision communities. The ability of a vision system to track the subjects and accurately predict their future locations is critical to many surveillance and camera control applica- tions. Further, an inference of the type of motion as well as to rapidly detect and switch
Research Interests:
Research Interests: Computer Science, Computer Vision, Machine Vision, Automotive Engineering, Image Classification, and 11 moreReal Time Systems, Reliability, Feature Extraction, Air Transportation, Real Time, Digital Signal Processor, Real Time system, Embedded System, Classification Accuracy, Safety Systems, and System testing
The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest from the background image. It is extremely difficult to... more
The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest from the background image. It is extremely difficult to obtain a reliable segmentation without any prior knowledge about the object that is being extracted from the scene. This is further complicated by the lack of any clearly defined metrics for evaluating the quality of segmentation or for comparing segmentation algorithms. We propose a method of segmentation that addresses both of these issues, by using the object classification subsystem as an integral part of the segmentation. This will provide contextual information regarding the objects to be segmented, as well as allow us to use the probability of correct classification as a metric to determine the quality of the segmentation. We view traditional segmentation as a filter operating on the image that is independent of the classifier, much like the filter methods for feature selection. We propose a new paradigm for segmentation and classification that follows the wrapper methods of feature selection. Our method wraps the segmentation and classification together, and uses the classification accuracy as the metric to determine the best segmentation. By using shape as the classification feature, we are able to develop a segmentation algorithm that relaxes the requirement that the object of interest to be segmented must be homogeneous in some low-level image parameter, such as texture, color, or grayscale. This represents an improvement over other segmentation methods that have used classification information only to modify the segmenter parameters, since these algorithms still require an underlying homogeneity in some parameter space. Rather than considering our method as, yet, another segmentation algorithm, we propose that our wrapper method can be considered as an image segmentation framework, within which existing image segmentation algorithms may be executed. We show the performance of our proposed wrapper-based segmenter on real-world and complex images of automotive vehicle occupants for the purpose of recognizing infants on the passenger seat and disabling the vehicle airbag. This is an interesting application for testing the robustness of our approach, due to the complexity of the images, and, consequently, we believe the algorithm will be suitable for many other real-world applications.