Electrical and Computer Engineering Commons^™

Learning Local Features Using Boosted Trees For Face Recognition, Rajkiran Gottumukkal

Electrical & Computer Engineering Theses & Dissertations

Face recognition is fundamental to a number of significant applications that include but not limited to video surveillance and content based image retrieval. Some of the challenges which make this task difficult are variations in faces due to changes in pose, illumination and deformation. This dissertation proposes a face recognition system to overcome these difficulties. We propose methods for different stages of face recognition which will make the system more robust to these variations. We propose a novel method to perform skin segmentation which is fast and able to perform well under different illumination conditions. We also propose a method …

Feature Pruning For Action Recognition In Complex Environment, Adarsh Nagaraja

Electronic Theses and Dissertations

A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video …

Design Of A Monocular Multi-Spectral Skin Detection, Melanin Estimation, And False-Alarm Suppression System, Keith R. Peskosky

Theses and Dissertations

A real-time skin detection, false-alarm reduction, and melanin estimation system is designed targeting search and rescue (SAR) with application to special operations for manhunting and human measurement and signatures intelligence. A mathematical model of the system is developed and used to determine how the physical system performs under illumination, target-to-sensor distance, and target-type scenarios. This aspect is important to the SAR community to gain an understanding of the deployability in different operating environments. A multi-spectral approach is developed and consists of two short-wave infrared cameras and two visible cameras. Through an optical chain of lenses, custom designed and fabricated dichroic …

Electronic Image Stabilization For Mobile Robotic Vision Systems, Michael John Smith

Theses and Dissertations

When a camera is affixed on a dynamic mobile robot, image stabilization is the first step towards more complex analysis on the video feed. This thesis presents a novel electronic image stabilization (EIS) algorithm for small inexpensive highly dynamic mobile robotic platforms with onboard camera systems. The algorithm combines optical flow motion parameter estimation with angular rate data provided by a strapdown inertial measurement unit (IMU). A discrete Kalman filter in feedforward configuration is used for optimal fusion of the two data sources. Performance evaluations are conducted by a simulated video truth model (capturing the effects of image translation, rotation, …

Real-Time Optical Flow Sensor Design And Its Application On Obstacle Detection, Zhaoyi Wei

Theses and Dissertations

Motion is one of the most important features describing an image sequence. Motion estimation has been widely applied in structure from motion, vision-based navigation and many other fields. However, real-time motion estimation remains a challenge because of its high computational expense. The traditional CPU-based scheme cannot satisfy the power, size and computation requirements in many applications. With the availability of new parallel architectures such as FPGAs and GPUs, applying these new technologies to computer vision tasks such as motion estimation has been an active research field in recent years. In this dissertation, FPGAs have been applied to real-time motion estimation …

An Optical Flow Implementation Comparison Study, John M. Bodily

Theses and Dissertations

Optical flow is the apparent motion of brightness patterns within an image scene. Algorithms used to calculate the optical flow for a sequence of images are useful in a variety of applications, including motion detection and obstacle avoidance. Typical optical flow algorithms are computationally intense and run slowly when implemented in software, which is problematic since many potential applications of the algorithm require real-time calculation in order to be useful. To increase performance of the calculation, optical flow has recently been implemented on FPGA and GPU platforms. These devices are able to process optical flow in real-time, but are generally …

Model-Based Control Using Model And Mechanization Fusion Techniques For Image-Aided Navigation, Constance D. Hendrix

Theses and Dissertations

Unmanned aerial vehicles are no longer used for just reconnaissance. Current requirements call for smaller autonomous vehicles that replace the human in high-risk activities. Many times these activities are performed in GPS-degraded environments. Without GPS providing today's most accurate navigation solution, autonomous navigation in tight areas is more difficult. Today, image-aided navigation is used and other methods are explored to more accurately navigate in such areas (e.g., indoors). This thesis explores the use of inertial measurements and navigation solution updates using cameras with a model-based Linear Quadratic Gaussian controller. To demonstrate the methods behind this research, the controller will provide …

Communication Free Robot Swarming, Zachary C. Gray

Theses and Dissertations

As the military use of unmanned aerial vehicles increases, a growing need for novel strategies to control these systems exists. One such method for controlling many unmanned aerial vehicles simultaneously is the through the use of swarm algorithms. This research explores a swarm robotic algorithm developed by Kadrovach implemented on Pioneer Robots in a real-world environment. An adaptation of his visual sensor is implemented using stereo vision as the primary method of sensing the environment. The swarm members are prohibited from explicitly communicating other than passively through the environment. The resulting implementation produces a communication free swarming algorithm. The algorithm …

Object Detection And Texture Classification With Applications To The Diagnosis Of Skin Cancer, Jonathan Blackledge, D. A. Dubovitskiy

Books/Book chapters

We present an approach to object detection and recognition in a digital image using a classification method that is based on the application of a set of features that include fractal parameters such as the Lacunarity and Fractal Dimension. The principal issues associated with object recognition are presented and a self-learning procedure for designing a decision making engine using fuzzy logic and membership function theory considered. The methods discussed, and the ‘system’ developed, have a range of applications in ‘machine vision’ and in this publication, we focus on the development and implementation of a skin cancer screening system that can …

A Subspace Projection Methodology For Nonlinear Manifold Based Face Recognition, Praveen Sankaran

Electrical & Computer Engineering Theses & Dissertations

A novel feature extraction method that utilizes nonlinear mapping from the original data space to the feature space is presented in this dissertation. Feature extraction methods aim to find compact representations of data that are easy to classify. Measurements with similar values are grouped to same category, while those with differing values are deemed to be of separate categories. For most practical systems, the meaningful features of a pattern class lie in a low dimensional nonlinear constraint region (manifold) within the high dimensional data space. A learning algorithm to model this nonlinear region and to project patterns to this feature …

Vision-Based Detection, Tracking And Classification Of Vehicles Using Stable Features With Automatic Camera Calibration, Neeraj Kanhere

All Dissertations

A method is presented for segmenting and tracking vehicles on highways using a camera that is relatively low to the ground. At such low angles, 3D perspective effects cause significant appearance changes over time, as well as severe occlusions by vehicles in neighboring lanes. Traditional approaches to occlusion reasoning assume that the vehicles initially appear well-separated in the image, but in our sequences it is not uncommon for vehicles to enter the scene partially occluded and remain so throughout. By utilizing a 3D perspective mapping from the scene to the image, along with a plumb line projection, a subset of …

Real-Time Forward Urban Environment Perception For An Autonomous Ground Vehicle Using Computer Vision And Lidar, Christopher Richard Greco

Theses and Dissertations

The field of autonomous vehicle research is growing rapidly. The Congressional mandate for the military to use unmanned vehicles has, in large part, sparked this growth. In conjunction with this mandate, DARPA sponsored the Urban Challenge, a competition to create fully autonomous vehicles that can operate in urban settings. An extremely important feature of autonomous vehicles, especially in urban locations, is their ability to perceive their environment. The research presented in this thesis is directed toward providing an autonomous vehicle with real-time data that efficiently and compactly represents its forward environment as it navigates an urban area. The information extracted …

A Surface Inspection Machine Vision System That Includes Fractal Texture Analysis, Jonathan Blackledge, Dmitry Dubovitskiy

Articles

The detection, recognition and classification of features in a digital image is an important component of quality control systems in production and process engineering and industrial systems monitoring, in general. In this paper, a new pattern recognition system is presented that has been designed for the specific task of monitoring the quality of sheet-steel production in a rolling mill. The system is based on using both the Euclidean and Fractal geometric properties of an imaged object to develop training data that is used in conjunction with a supervised learning procedure based on the application of a fuzzy inference engine. Thus, …

Object Detection And Classification With Applications To Skin Cancer Screening, Jonathan Blackledge, Dmitryi Dubovitskiy

Articles

This paper discusses a new approach to the processes of object detection, recognition and classification in a digital image. The classification method is based on the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension. Thus, the approach used, incorporates the characterisation of an object in terms of its texture.

The principal issues associated with object recognition are presented which includes two novel fast segmentation algorithms for which C++ code is provided. The self-learning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and …

Seasonal Adaptation Of Vegetation Color In Satellite Images, Srinivas Jakkula, Vamsi K.R. Mantena, Ramu Pedada, Yuzhong Shen, Jiang Li, Hamid R. Arabnia (Ed.)

Electrical & Computer Engineering Faculty Publications

Remote sensing techniques like NDVI (Normal Difference vegetative Index) when applied to phenological variations in aerial images, ascertained the seasonal rise and decline of photosynthetic activity in different seasons, resulting in different color tones of vegetation. The rise and fall of NDVI values decide the biological response, either the green up or brown down [1]. Vegetation in green up period appears with more vegetative vigor and during brown down period it has a dry appearance. This paper proposes a novel method that identifies vegetative patterns in satellite images and then alters vegetation color to simulate seasonal changes based on training …

Vegetation Identification Based On Satellite Imagery, Vamsi K.R. Mantena, Ramu Pedada, Srinivas Jakkula, Yuzhong Shen, Jiang Li, Hamid R. Arabnia (Ed.)

Electrical & Computer Engineering Faculty Publications

Automatic vegetation identification plays an important role in many applications including remote sensing and high performance flight simulations. This paper presents a method to automatically identify vegetation based upon satellite imagery. First, we utilize the ISODATA algorithm to cluster pixels in the images where the number of clusters is determined by the algorithm. We then apply morphological operations to the clustered images to smooth the boundaries between clusters and to fill holes inside clusters. After that, we compute six features for each cluster. These six features then go through a feature selection algorithm and three of them are determined to …

Particle Filter Based Mosaicking For Forest Fire Tracking, Justin Mathew Bradley

Theses and Dissertations

Using autonomous miniature air vehicles (MAVs) is a cost-effective, simple method for collecting data about the size, shape, and location characteristics of a forest fire. However, noise in measurements used to compute pose (location and attitude) of the on-board camera leads to significant errors in the processing of collected video data. Typical methods using MAVs to track fires attempt to find single geolocation estimates and filter that estimate with subsequent observations. While this is an effective method of resolving the noise to achieve a better geolocation estimate, it reduces a fire to a single point or small set of points. …

Obstacle Avoidance For Small Unmanned Air Vehicles, Brandon R. Call

Theses and Dissertations

Small UAVs are used for low altitude surveillance flights where unknown obstacles can be encountered. These UAVs can be given the capability to navigate in uncertain environments if obstacles are identified. This research presents an obstacle avoidance system for small UAVs. First, a mission waypoint path is created that avoids all known obstacles using a genetic algorithm. Then, while the UAV is in flight, obstacles are detected using a forward looking, onboard camera. Image features are found using the Harris Corner Detector and tracked through multiple video frames which provides three dimensional localization of the features. A sparse three dimensional …

Human Identification Using Gait, Murat Eki̇nci̇

Turkish Journal of Electrical Engineering and Computer Sciences

Gait refers to the style of walking of an individual. This paper presents a view-invariant approach for human identification at a distance, using gait recognition. Recognition of a person from their gait is a biometric of increasing interest. Based on principal component analysis (PCA), this paper describes a simple, but efficient approach to gait recognition. Binarized silhouettes of a motion object are represented by 1-D signals, which are the basic image features called distance vectors. The distance vectors are differences between the bounding box and silhouette, and are extracted using 4 projections of the silhouette. Based on normalized correlation of …

Structure From Motion Using Optical Flow Probability Distributions, Paul Clark Merrell

Theses and Dissertations

Several novel structure from motion algorithms are presented that are designed to more effectively manage the problem of noise. In many practical applications, structure from motion algorithms fail to work properly because of the noise in the optical flow values. Most structure from motion algorithms implicitly assume that the noise is identically distributed and that the noise is white. Both assumptions are false. Some points can be track more easily than others and some points can be tracked more easily in a particular direction. The accuracy of each optical flow value can be quantified using an optical flow probability distribution. …

Determination Of Structure From Motion Using Aerial Imagery, Paul R. Graham

Theses and Dissertations

The structure from motion process creates three-dimensional models from a sequence of images. Until recently, most research in this field has been restricted to land-based imagery. This research examines the current methods of land-based structure from motion and evaluates their performance for aerial imagery. Current structure from motion algorithms search the initial image for features to track though the subsequent images. These features are used to create point correspondences between the two images. The correspondences are used to estimate the motion of the camera and then the three-dimensional structure of the scene. This research tests current algorithms using synthetic data …

Discovering The Merit Of The Wavelet Transform For Object Classification, Matthew D. Eyster

Theses and Dissertations

Vision is the primary sense by which most biological systems collect information about their environment. Computer vision is a branch of artificial intelligence concerned with endowing machines with the ability to understand images. Object recognition is a key part of machine vision with far reaching benefits ranging from target recognition, surveillance systems, to automation systems. Extraction of salient features from an image is one of the key steps in object recognition. Typically, geometric primitives are extracted from an image using local analysis. However, the wavelet transform provides a global approach with good locality. Additionally, the directional and multiresolution properties may …

Object Classfification In Computer Vision With Discriminant Analysis, Amir Hamzahan

Makara Journal of Technology

A robotic sensor system is always supported by a computer system called ‘computer vision’. The important concept of computer vision is object classfifi cation. In this study two algorithms for object classifi cation in this system will be compared. Firstly, A simple method that do not need complex computation and that considered as an informal method is called binary tree decision structure. This method is based on modest caracteristic decriptors of an object such as vertical line, horizontal line or ellipse line. Unfortunately this method has weakness in recognize an image that contaminated by a noise. Secondly, a more formal …

Adaptive-Rate Tree-Structured Residual Vector Quantization, Christian B. Peel, X. Liu, Scott E. Budge

Electrical and Computer Engineering Faculty Publications

Full-search vector quantization (VQ) provides optimal results only with high memory and computational cost. We describe the computational and memory requirements of tree-structured VQ, residual VQ (RVQ), and tree-structured RVQ. We present multiple-rate, adaptive-search implementations of these VQ structures, and simulation results with video sequences. Tree-structured RVQ provides up to 1.5 db PSNR quality improvements over RVQ, as well as significant perceptual improvement. These algorithms maintain many of the benefits of full-search VQ, while providing trade-offs between computational, storage, and performance requirements.

Realtime Color Stereovision Processing, Byron P. Formwalt

Theses and Dissertations

Recent developments in aviation have made micro air vehicles (MAVs) a reality. These featherweight palm-sized radio-controlled flying saucers embody the future of air-to-ground combat. No one has ever successfully implemented an autonomous control system for MAVs. Because MAVs are physically small with limited energy supplies, video signals offer superiority over radar for navigational applications. This research takes a step forward in real time machine vision processing. It investigates techniques for implementing a real time stereovision processing system using two miniature color cameras. The effects of poor-quality optics are overcome by a robust algorithm, which operates in real time and achieves …

Knowledge-Based Navigation For Autonomous Road Vehicles, Murat Eki̇nci̇, Franches W.J.Gibbs, Barry T. Thomas

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a computer vision system for an autonomous road vehicle (ARV) that is capable of negotiating complex road networks including road junctions in real time. The ultimate aim of the system is to enable the vehicle to drive automatically along a given complex road network whose geometric description is known. This computer vision system includes three main techniques which are necessary for an ARV: a) road following, b) road junction detection, c) manoeuvring at the road junction. The road following algorithm presents a method of executing a number of algorithms using different methods concurrently, fusing their outputs together …

Adaptive Shape From Shading, Ati̇lla Gülteki̇n, Muhi̇tti̇n Gökmen

Turkish Journal of Electrical Engineering and Computer Sciences

Extracting surface orientation and surface depth from one or more images is one of the classic problems in computer vision. Shape-from-shading (SFS) deals with the recovery of 3-D shape from a single shaded image. The shape is recovered by minimizing an energy functional involving constraints such as smoothness. In this constrained problem, although the smoothness constraint helps to stabilize the minimization process, it pushes the reconstruction toward a smooth surface. In this paper, we present a new adaptive shape-from-shading method which reduces this oversmoothing by controlling the smoothness spatially over the image space. In order to improve the quality of …

Novel High-Speed Architecture For Machine Vision Applications, Bassam S. Farroha, Raghvendra G. Deshmukh

Electrical Engineering and Computer Science Faculty Publications

This paper focuses on producing a state-of-the-art technique for designing an image recognition system for machine vision applications. The motivation behind the new system design is to provide a unique methodology, using strategic design techniques, to implement a system that addresses real-world image recognition applications. The introduction of application-specific, massively parallel array of processors, where low-level processing is accomplished on reconfigurable hardware structures, highlights the scheme. The system was built and simulated on a VLSI chip and results were verified using Electric Rules Check and Harris Timing Analysis examination tools. The system is composed of there functional layers and a …

Adaptive Color Correlation Of Knots In Wood Images And Weighted-Value Product Selection Methods In A Machine Vision System, John Robert Goulding

Dissertations and Theses

The biggest obstacle to robust color image processing of wood is in developing a color model that represents all possible defect colors. When the color model is too general or too specific, defect recognition fails because too many or too few non-defect pixels match the model, respectively. Because a color image of wood contains far more clear and clear-grain colored pixels than grain-knot and knot colored pixels, it is beneficial to first statistically identify and remove the clear and clear-grain colors and to use the accumulated data to simultaneously enhance and normalize the remaining grainknot and knot colored pixels. This …

An Implementation Of A Versatile Camera Calibration Technique For High-Accuracy 3d Machine Vision Metrology Using Off-The-Shelf Tv Camera And Lenses, Bolang Li

Theses

This thesis studies and implements a new versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV camera and lenses developed by Roger Tsai [1]. This technique builds up a unique relationship from the world coordinate system to the computer image coordinate system of calibration points by using a radial alignment constraint. The technique has advantage in terms of accuracy, speed, and versatility over existing techniques.

The fundamental knowledge for using this technique is presented in this thesis first, followed by an overview of the existing calibration techniques, and a detailed description of the new technique. The …