Local Features in Image and Video Processing - Object Class Matching and Video Shot Detection

The usage of digital content, such as video clips and images, has increased dramatically during the last decade. Local image features have been applied increasingly in various image and video retrieval applications. This thesis evaluates local features and applies them to image and video processing tasks. The results of the study show that 1) the performance of different local feature detector and descriptor methods vary significantly in object class matching, 2) local features can be applied in image alignment with superior results against the state-of-the-art, 3) the local feature based shot boundary detection method produces promising results, and 4) the local feature based hierarchical video summarization method shows promising new new research direction. In conclusion, this thesis presents the local features as a powerful tool in many applications and the imminent future work should concentrate on improving the quality of the local features.

Design and implementation of machine vision system for the mobile assembly robot

The review of intelligent machines shows that the demand for new ways of helping people in perception of the real world is becoming higher and higher every year. This thesis provides information about design and implementation of machine vision for mobile assembly robot. The work has been done as a part of LUT project in Laboratory of Intelligent Machines. The aim of this work is to create a working vision system. The qualitative and quantitative research were done to complete this task. In the first part, the author presents the theoretical background of such things as digital camera work principles, wireless transmission basics, creation of live stream, methods used for pattern recognition. Formulas, dependencies and previous research related to the topic are shown. In the second part, the equipment used for the project is described. There is information about the brands, models, capabilities and also requirements needed for implementation. Although, the author gives a description of LabVIEW software, its add-ons and OpenCV which are used in the project. Furthermore, one can find results in further section of considered thesis. They mainly represented by screenshots from cameras, working station and photos of the system. The key result of this thesis is vision system created for the needs of mobile assembly robot. Therefore, it is possible to see graphically what was done on examples. Future research in this field includes optimization of the pattern recognition algorithm. This will give less response time for recognizing objects. Presented by author system can be used also for further activities which include artificial intelligence usage.

Video Object Tracking And Analysis For Computer Assisted Surgery

Pedicle screw insertion technique has made revolution in the surgical treatment of spinal fractures and spinal disorders. Although X- ray fluoroscopy based navigation is popular, there is risk of prolonged exposure to X- ray radiation. Systems that have lower radiation risk are generally quite expensive. The position and orientation of the drill is clinically very important in pedicle screw fixation. In this paper, the position and orientation of the marker on the drill is determined using pattern recognition based methods, using geometric features, obtained from the input video sequence taken from CCD camera. A search is then performed on the video frames after preprocessing, to obtain the exact position and orientation of the drill. An animated graphics, showing the instantaneous position and orientation of the drill is then overlaid on the processed video for real time drill control and navigation

Evaluation Of A Novel Method Of Real Time Computer Assisted Spine Surgery

In this paper the effectiveness of a novel method of computer assisted pedicle screw insertion was studied using testing of hypothesis procedure with a sample size of 48. Pattern recognition based on geometric features of markers on the drill has been performed on real time optical video obtained from orthogonally placed CCD cameras. The study reveals the exactness of the calculated position of the drill using navigation based on CT image of the vertebra and real time optical video of the drill. The significance value is 0.424 at 95% confidence level which indicates good precision with a standard mean error of only 0.00724. The virtual vision method is less hazardous to both patient and the surgeon

Surface Reflectance Recognition and Real-World Illumination Statistics

Humans distinguish materials such as metal, plastic, and paper effortlessly at a glance. Traditional computer vision systems cannot solve this problem at all. Recognizing surface reflectance properties from a single photograph is difficult because the observed image depends heavily on the amount of light incident from every direction. A mirrored sphere, for example, produces a different image in every environment. To make matters worse, two surfaces with different reflectance properties could produce identical images. The mirrored sphere simply reflects its surroundings, so in the right artificial setting, it could mimic the appearance of a matte ping-pong ball. Yet, humans possess an intuitive sense of what materials typically "look like" in the real world. This thesis develops computational algorithms with a similar ability to recognize reflectance properties from photographs under unknown, real-world illumination conditions. Real-world illumination is complex, with light typically incident on a surface from every direction. We find, however, that real-world illumination patterns are not arbitrary. They exhibit highly predictable spatial structure, which we describe largely in the wavelet domain. Although they differ in several respects from the typical photographs, illumination patterns share much of the regularity described in the natural image statistics literature. These properties of real-world illumination lead to predictable image statistics for a surface with given reflectance properties. We construct a system that classifies a surface according to its reflectance from a single photograph under unknown illuminination. Our algorithm learns relationships between surface reflectance and certain statistics computed from the observed image. Like the human visual system, we solve the otherwise underconstrained inverse problem of reflectance estimation by taking advantage of the statistical regularity of illumination. For surfaces with homogeneous reflectance properties and known geometry, our system rivals human performance.

Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character both of natural kinds and of artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

Monocular-based 3-D seafloor reconstruction and ortho-mosaicing by piecewise planar representation

Photo-mosaicing techniques have become popular for seafloor mapping in various marine science applications. However, the common methods cannot accurately map regions with high relief and topographical variations. Ortho-mosaicing borrowed from photogrammetry is an alternative technique that enables taking into account the 3-D shape of the terrain. A serious bottleneck is the volume of elevation information that needs to be estimated from the video data, fused, and processed for the generation of a composite ortho-photo that covers a relatively large seafloor area. We present a framework that combines the advantages of dense depth-map and 3-D feature estimation techniques based on visual motion cues. The main goal is to identify and reconstruct certain key terrain feature points that adequately represent the surface with minimal complexity in the form of piecewise planar patches. The proposed implementation utilizes local depth maps for feature selection, while tracking over several views enables 3-D reconstruction by bundle adjustment. Experimental results with synthetic and real data validate the effectiveness of the proposed approach

A new approach to the classification of mammographic masses and normal breast tissue

A new approach to mammographic mass detection is presented in this paper. Although different algorithms have been proposed for such a task, most of them are application dependent. In contrast, our approach makes use of a kindred topic in computer vision adapted to our particular problem. In this sense, we translate the eigenfaces approach for face detection/classification problems to a mass detection. Two different databases were used to show the robustness of the approach. The first one consisted on a set of 160 regions of interest (RoIs) extracted from the MIAS database, being 40 of them with confirmed masses and the rest normal tissue. The second set of RoIs was extracted from the DDSM database, and contained 196 RoIs containing masses and 392 with normal, but suspicious regions. Initial results demonstrate the feasibility of using such approach with performances comparable to other algorithms, with the advantage of being a more general, simple and cost-effective approach

An overview of the advantages and constraints of coded pattern projection techniques for autonomous navigation

The absolute necessity of obtaining 3D information of structured and unknown environments in autonomous navigation reduce considerably the set of sensors that can be used. The necessity to know, at each time, the position of the mobile robot with respect to the scene is indispensable. Furthermore, this information must be obtained in the least computing time. Stereo vision is an attractive and widely used method, but, it is rather limited to make fast 3D surface maps, due to the correspondence problem. The spatial and temporal correspondence among images can be alleviated using a method based on structured light. This relationship can be directly found codifying the projected light; then each imaged region of the projected pattern carries the needed information to solve the correspondence problem. We present the most significant techniques, used in recent years, concerning the coded structured light method

Evolving features-algorithms knowledge map to support NIDS data intelligence and learning loop architecting – a generalised approach to NIDS pattern feature space knowledge processing

This paper describes a proposed new approach to the Computer Network Security Intrusion Detection Systems (NIDS) application domain knowledge processing focused on a topic map technology-enabled representation of features of the threat pattern space as well as the knowledge of situated efficacy of alternative candidate algorithms for pattern recognition within the NIDS domain. Thus an integrative knowledge representation framework for virtualisation, data intelligence and learning loop architecting in the NIDS domain is described together with specific aspects of its deployment.

3D surface point and wireframe reconstruction from multiview photographic images

This paper describes a new method for reconstructing 3D surface points and a wireframe on the surface of a freeform object using a small number, e.g. 10, of 2D photographic images. The images are taken at different viewing directions by a perspective camera with full prior knowledge of the camera configurations. The reconstructed surface points are frontier points and the wireframe is a network of contour generators. Both of them are reconstructed by pairing apparent contours in the 2D images. Unlike previous works, we empirically demonstrate that if the viewing directions are uniformly distributed around the object's viewing sphere, then the reconstructed 3D points automatically cluster closely on a highly curved part of the surface and are widely spread on smooth or flat parts. The advantage of this property is that the reconstructed points along a surface or a contour generator are not under-sampled or under-represented because surfaces or contours should be sampled or represented with more densely points where their curvatures are high. The more complex the contour's shape, the greater is the number of points required, but the greater the number of points is automatically generated by the proposed method. Given that the viewing directions are uniformly distributed, the number and distribution of the reconstructed points depend on the shape or the curvature of the surface regardless of the size of the surface or the size of the object. The unique pattern of the reconstructed points and contours may be used in 31) object recognition and measurement without computationally intensive full surface reconstruction. The results are obtained from both computer-generated and real objects. (C) 2007 Elsevier B.V. All rights reserved.

Motion cue analysis for parkinsonian gait recognition

This paper presents a computer-vision based marker-free method for gait-impairment detection in Patients with Parkinson's disease (PWP). The system is based upon the idea that a normal human body attains equilibrium during the gait by aligning the body posture with Axis-of-Gravity (AOG) using feet as the base of support. In contrast, PWP appear to be falling forward as they are less-able to align their body with AOG due to rigid muscular tone. A normal gait exhibits periodic stride-cycles with stride-angle around 45o between the legs, whereas PWP walk with shortened stride-angle with high variability between the stride-cycles. In order to analyze Parkinsonian-gait (PG), subjects were videotaped with several gait-cycles. The subject's body was segmented using a color-segmentation method to form a silhouette. The silhouette was skeletonized for motion cues extraction. The motion cues analyzed were stride-cycles (based on the cyclic leg motion of skeleton) and posture lean (based on the angle between leaned torso of skeleton and AOG). Cosine similarity between an imaginary perfect gait pattern and the subject gait patterns produced 100% recognition rate of PG for 4 normal-controls and 3 PWP. Results suggested that the method is a promising tool to be used for PG assessment in home-environment.

Graphical models and point set matching

Point pattern matching in Euclidean Spaces is one of the fundamental problems in Pattern Recognition, having applications ranging from Computer Vision to Computational Chemistry. Whenever two complex patterns are encoded by two sets of points identifying their key features, their comparison can be seen as a point pattern matching problem. This work proposes a single approach to both exact and inexact point set matching in Euclidean Spaces of arbitrary dimension. In the case of exact matching, it is assured to find an optimal solution. For inexact matching (when noise is involved), experimental results confirm the validity of the approach. We start by regarding point pattern matching as a weighted graph matching problem. We then formulate the weighted graph matching problem as one of Bayesian inference in a probabilistic graphical model. By exploiting the existence of fundamental constraints in patterns embedded in Euclidean Spaces, we prove that for exact point set matching a simple graphical model is equivalent to the full model. It is possible to show that exact probabilistic inference in this simple model has polynomial time complexity with respect to the number of elements in the patterns to be matched. This gives rise to a technique that for exact matching provably finds a global optimum in polynomial time for any dimensionality of the underlying Euclidean Space. Computational experiments comparing this technique with well-known probabilistic relaxation labeling show significant performance improvement for inexact matching. The proposed approach is significantly more robust under augmentation of the sizes of the involved patterns. In the absence of noise, the results are always perfect.