Stanislav Kovacic

Multiresolution elastic matching

Matching of locally variant data to an explicit 3-dimensional pictorial model is developed for X-ray computed tomography scans of the human brain, where the model is a voxel representation of an anatomical human brain atlas. The matching process is 3-dimensional without any preference given to the slicing plane. After global alignment the brain atlas is deformed like a piece of rubber, without tearing or folding. Deformation proceeds step-by-step in a coarse-to-fine strategy, increasing the local similarity and global coherence. The assumption underlying this approach is that all normal brains, at least at a certain level of representation, have the same topological structure, but may differ in shape details. Results show that we can account for these differences.

A trajectory-based analysis of coordinated team activity in a basketball game

This paper proposes a novel, trajectory-based approach to the automatic recognition of complex multi-player behavior in a basketball game. First, a probabilistic play model is applied to the player-trajectory data in order to segment the play into game phases (offense, defense, time out). In this way, both the temporal boundaries of the observed activity and its broader context are obtained. Next, the teams activity is analyzed in more detail by detecting the key elements of basketball play. Following basketball theory, these key elements (starting formation, screen, and move) are the building blocks of basketball play, and therefore their temporal order is used to produce a semantic description of the observed activity. Finally, the activity is recognized by comparing its semantic description with the descriptions of manually defined templates, stored in a database. The effectiveness and robustness of the proposed approach is demonstrated on two championship games and 71 examples of three types of basketball offense.

Observation and analysis of large-scale human motion

Many team sports include complex human movement, which can be observed at different levels of detail. Some aspects of the athletes motion can be studied in detail using commercially available high-speed, high-accuracy biomechanical measurement systems. However, due to their limitations, these devices are not appropriate for studying large-scale motion during a game (for example, the motion of a player running across the entire playing field). We describe an alternative approach to studying such large-scale motion, and present a video-based, computer-aided system, developed specifically for the purpose of acquiring large-scale motion data. The baseline of our approach consists of sacrificing much of the spatial accuracy and temporal resolution of widely used biomechanical measurement systems, to obtain data on human movement that span large areas and long intervals of time. Data can be obtained for each of the observed athletes with reasonable amount of operator work. The system was developed using the recordings of a handball match. Several field tests were performed to assess measurement error, including comparison to one of the widely available biomechanical measurement systems. With the help of the system presented, we could obtain position data for all 14 handball players on a 40 x 20 m large court with RMS error better than 0.6 m, covering 1 h of action. Several results, obtained during the handball match study are presented, in order to highlight the importance of large-scale motion acquisition.

A Bayes-spectral-entropy-based measure of camera focus using a discrete cosine transform

In this paper we present a novel measure of camera focus based on the Bayes spectral entropy of an image spectrum. In order to estimate the degree of focus, the image is divided into non-overlapping sub-images of 8x8 pixels. Next, sharpness values are calculated separately for each sub-image and their mean is taken as a measure of the overall focus. The sub-image spectra are obtained by an 8x8 discrete cosine transform (DCT). Comparisons were made against four well-known measures that were chosen as reference, on images captured with a standard visible-light camera and a thermal camera. The proposed measure outperformed the reference measures by exhibiting a wider working range and a smaller failure rate. To assess its robustness to noise, additional tests were conducted with noisy images.

Symmetric image registration.

Abstract This paper presents an original non-rigid image registration approach, which tends to improve the registration by establishing a symmetric image interdependence. In order to gather more information about the image transformation it measures the image similarity in both registration directions. The presented solution is based on the interaction between the images involved in the registration process. Images interact through forces, which according to Newton’s action–reaction law form a symmetric relationship. These forces may transform both of the images, although in our implementation one of the images remains fixed. The experiments performed to demonstrate the advantages of the symmetric registration approach involve the registration of simple objects, the recovery of synthetic deformation, and the inter-patient registration of real images of the head. The results show that the symmetric approach improves both the registration consistency and the registration correctness.

Point similarity measures for non-rigid registration of multi-modal data

High-dimensional non-rigid registration of multi-modal data requires similarity measures with two important properties: multi-modality and locality. Unfortunately all commonly used multi-modal similarity measures are inherently global and cannot operate on small image regions. In this paper, we propose a new class of multi-modal similarity measures, which are constructed from information of the whole images but can be applied pointwise. Due to their capability of measuring correspondence for individual image points we call them point similarity measures. Point similarity measures can be derived from global measures and enable detailed relative comparison of local image correspondence. We present a set of multimodal point similarity measures based on joint intensity distribution and test them as an integral part of non-rigid multi-modal registration system. The comparison results show that segmentation-based measure, which models the joint distribution as a sum of intensity classes, performs best. When intensity classes do not exist or cannot be accurately modeled, each intensity pair can be treated as a separate class, which results in a more general measure, suitable for various non-rigid registration tasks.

Closed-world tracking of multiple interacting targets for indoor-sports applications

In this paper we present an efficient algorithm for tracking multiple players during indoor sports matches. A sports match can be considered as a semi-controlled environment for which a set of closed-world assumptions regarding the visual as well as the dynamical properties of the players and the court can be derived. These assumptions are then used in the context of particle filtering to arrive at a computationally fast, closed-world, multi-player tracker. The proposed tracker is based on multiple, single-player trackers, which are combined using a closed-world assumption about the interactions among players. With regard to the visual properties, the robustness of the tracker is achieved by deriving a novel sports-domain-specific likelihood function and employing a novel background-elimination scheme. The restrictions on the players dynamics are enforced by employing a novel form of local smoothing. This smoothing renders the tracking more robust and reduces the computational complexity of the tracker. We evaluated the proposed closed-world, multi-player tracker on a challenging data set. In comparison with several similar trackers that did not utilize all of the closed-world assumptions, the proposed tracker produced better estimates of position and prediction as well as reducing the number of failures.

Machine vision system for inspecting electric plates

This paper presents a machine vision system for automated visual inspection of plates of electric cookers, with the goal to reduce labour cost and ensure consistent product quality. A number of dimensions of an electric plate are accurately defined by using two cameras with telecentric lenses, by applying sub-pixel edge detection techniques, and by semiautomatically calibrating the system. The dimensions of plates, which are manufactured by CNC lathes, may fall in or out of prescribed tolerance standards and are as such a valuable indicator of the lathe tool blunt or breakage. Extensive experiments showed that the inspecting system is fast, accurate and robust. The machine vision system is, thus, able to keep up with the plate production process, inspect every plate and reject the defective ones.

A Two-Stage Dynamic Model for Visual Tracking

We propose a new dynamic model which can be used within blob trackers to track the targets center of gravity. A strong point of the model is that it is designed to track a variety of motions which are usually encountered in applications such as pedestrian tracking, hand tracking, and sports. We call the dynamic model a two-stage dynamic model due to its particular structure, which is a composition of two models: a liberal model and a conservative model. The liberal model allows larger perturbations in the targets dynamics and is able to account for motions in between the random-walk dynamics and the nearly constant-velocity dynamics. On the other hand, the conservative model assumes smaller perturbations and is used to further constrain the liberal model to the targets current dynamics. We implement the two-stage dynamic model in a two-stage probabilistic tracker based on the particle filter and apply it to two separate examples of blob tracking: 1) tracking entire persons and 2) tracking of a persons hands. Experiments show that, in comparison to the widely used models, the proposed two-stage dynamic model allows tracking with smaller number of particles in the particle filter (e.g., 25 particles), while achieving smaller errors in the state estimation and a smaller failure rate. The results suggest that the improved performance comes from the models ability to actively adapt to the targets motion during tracking.

Computer vision system for tracking players in sports games

The development of a computer vision system for tracking players in indoor team games is presented. Several image processing and tracking methods are described, along with camera calibration and lens distortion correction. The output of the system consists of spatio-temporal trajectories of the players, which can be further processed and analyzed by sport experts. In some critical situations the automatic tracking process must be manually interrupted. To correct miss-trackings, human supervision is required. Some experimental results are presented as well.