Levente Attila Kovács

Focus Area Extraction by Blind Deconvolution for Defining Regions of Interest

We present an automatic focus area estimation method, working with a single image without a priori information about the image, the camera, or the scene. It produces relative focus maps by localized blind deconvolution and a new residual error-based classification. Evaluation and comparison is performed and applicability is shown through image indexing

Relative focus map estimation using blind deconvolution

An automatic focus map extraction method is presented that uses a modification of blind deconvolution for estimation of localized blurring functions. We use these local blurring functions [so-called point-spread functions (PSFs)] for extraction of focus areas on ordinary images. In this inverse task our goal is not image reconstruction but the estimation of localized PSFs and the relative focus map. Thus the method is less sensitive than general deconvolution is to noise and ill-posed deconvolution problems. The focus areas can be estimated without any knowledge of the shooting conditions or of the optical system used.

Flexible test-bed for unusual behavior detection

Visual surveillance and activity analysis is an active research field of computer vision. As a result, there are several different algorithms produced for this purpose. To obtain more robust systems it is desirable to integrate the different algorithms. To help achieve this goal, we propose a flexible, distributed software collaboration framework and present a prototype system for automatic event analysis.

Creating animations combining stochastic paintbrush transformation and motion detection

In this paper we propose a method for creating animation and animation-like video sequences from any ordinary video recorded by any means available. The method is based on paintbrush transformation, developed and patented by our department, and on different motion detection algorithms. One of the goals of the method is to obtain animations, cartoon-like outputs from a usual camera-recorded image sequence. The method inherits properties of the paintbrush transformation method like well-defined contours, acceptable distortion, and a painting-like view with no fine details below a limit. The resulting output is a series of video frames stored as brush-strokes and motion data between the frames, compressed for size reduction. This output can be converted to any available video format by decompression, frame-reconstruction and recompression.

Intelligent Multi Sensor Fusion System for Advanced Situation Awareness in Urban Environments

This paper presents a distributed multi sensor data processing and fusion system providing sophisticated surveillance capabilities in the urban environment. The system enables visual/non-visual event detection, situation assessment, and semantic event-based reasoning for force protection and civil surveillance applications. The novelties lie in the high level system view approach, not only concentrating on data fusion methodologies per se, but rather on a holistic view of sensor data fusion that provides both lower (sensor) level and higher level (semantic) fusion. At the same time, we concentrate on easy and quick extensibility with new sensors and processing capabilities. The system also makes provisions for visualizing and processing space-time alerts from sensor detections up to high level alerts based on rule-based semantic reasoning over sensor data and fusion events. The proposed architecture has been validated in a number of different synthetic and live urban scenarios.

VISRET - a content based annotation, retrieval and visualization toolchain

This paper presents a system for content-based video retrieval, with a complete toolchain for annotation, indexing, retrieval and visualization of imported data. The system contains around 20 feature descriptors, a modular infrastructure for descriptor addition and indexing, a web-based search interface and an easy-to-use query-annotation-result visualization module. The features that make this system differ from others is the support of all the steps of the retrieval chain, the modular support for standard MPEG-7 and custom descriptors, and the easy-to-use tools for query formulation and retrieval visualization. The intended use cases of the system are content- and annotation-based retrieval applications, ranging from community video portals to indexing of image, video, judicial, and other multimedia databases.

Shape-and-motion-fused multiple flying target recognition and tracking

This paper presents an automatic approach for camera/image based detection, recognition and tracking of flying objects (planes, missiles, etc.). The method detects appearing objects, and recognizes re-appearing targets. It uses a feature-based statistical modeling approach (e.g. HMM) for motion-based recognition, and an image feature (e.g. shape) based indexed database of pre-trained object classes, suitable for recognition on known and alerting on unknown objects. The method can be used for detection of flying objects, recognition of the same object category through multiple views/cameras and signal on unusual motions and shape appearances.

Image indexing by focus map

Content-based indexing and retrieval (CBIR) of still and motion picture databases is an area of ever increasing attention. In this paper we present a method for still image information extraction, which in itself provides a somewhat higher level of features and also can serve as a basis for high level, i.e. semantic, image feature extraction and understanding. In our proposed method we use blind deconvolution for image area classification by interest regions, which is a novel use of the technique. We prove its viability for such and similar use.

Efficient coding of stroke-rendered paintings

There are more and more applications of non-photorealistic rendered images, sketches and drawings. Several techniques for generating such imagery are widely known. The stochastic painting-based painterly image (and video) generation presented herein is a multi-purpose image rendering and representation method, suitable for many purposes: painterly rendering, storing, compression or indexing. It incorporates many new features like multiscale edge following, stroke-set optimizations, templates, color morphology, etc. We demonstrate that the presented technique (called enhanced stochastic paintbrush transformation or eSPT) is suitable for fast high quality painterly rendering, providing good lossless painted compression ratios and features that make it suitable for many applications. One of these we wish to emphasize is the suitability to code painted images in a way that does not introduce any coding artifacts (blockiness, ringings, etc.) but provides a compact form of representation that still retains the main property of a painting: that it is a painting after all.

Visual Monocular Obstacle Avoidance for Small Unmanned Vehicles

This paper presents and extensively evaluates a visual obstacle avoidance method using frames of a single camera, intended for application on small devices (ground or aerial robots or even smartphones). It is based on image region classification using so called relative focus maps, it does not require a priori training, and it is applicable in both indoor and outdoor environments, which we demonstrate through evaluations using both simulated and real data.