Masahito Kumano

Automatic Production System of Soccer Sports Video by Digital Camera Work Based on Situation Recognition

We are studying about automatic production of soccer sports videos for easy understanding by using digital camera work on camera fixed videos. The digital camera work is a movie technique which uses virtual panning and zooming by clipping frames from hi-resolution images and controlling the frame size and position. We have studied so far digital panning. In this paper, we propose a method of digital zooming by automatically recognizing the game situation or events such as penalty kick and free kick based on player and ball tracking. These recognition results are used as key indices to retrieve the event scenes from soccer videos. We compared the proposed technique with a conventional technique by AHP method that can reflect an individual subjectivity

Highlight scene extraction in real time from baseball live video

This paper proposes a method to automatically extract highlight scenes from sports (baseball) live video in real time and to allow users to retrieve them. For this purpose, sophisticated speech recognition is employed to convert the speech signal into the text and to extract a group of keywords in real time. Image processing detects, also in real time, the pitcher scenes and ending at the successive pitcher scene. Highlight scenes are extracted as the pitching sections with the keywords such as home run, two-base hit and three-base hit extracted from speech signals.

Automatic extraction of PC scenes based on feature mining for a real time delivery system of baseball highlight scenes

To deliver baseball highlight scenes broadcast live to baseball fans outside, image processings such as an online video analyzing, meta information extraction and automatic editing have to be performed in real time. This paper proposes a high-speed image processing to automatically extract PC (pitcher and catcher) scenes, based on feature mining, from a baseball live game broadcast in real time as a part of the baseball highlight scene delivery system. This method showed 95.5% accuracy in the F-measure score within 1/30 of real time.

Online Training-Oriented Video Shooting Navigation System Based on Real-Time Camerawork Evaluation

In this paper, we propose an online training-oriented video shooting navigation system focused on camerawork based on video grammar by real-time camerawork evaluation to train users shooting nice shots for the later editing work. In this system, the processing speed must be very high so that we use a luminance projection correlation and a structure tensor method to extract the camerawork parameters in real-time. From the results of camerawork analysis, the results of each frame are classified into 7 camerawork types and the system issues 6 types of alarms and navigates users along the specified shot depending on camerawork based on video grammar in real-time while shooting the shot. Thereby, users can naturally acquire shooting style by trying to decrease alarms of improper camerawork without a consideration of the video grammar

Video shooting navigation system by real-time useful shot discrimination based on video grammar

In this paper, we propose a video shooting navigation system by real-time useful shot discrimination based on video grammar to support users shooting nice shots for later editing work. In this system, the processing speed must be very high so that we use a gray value projection method to extract the camerawork parameters in real-time. From the result of camerawork and gray value analysis, the shots are classified into 16 states and the system issues alarms and instructions about the usefulness and uselessness of the shots in real-time just after shooting the shot. Thereby, users can retake a shot necessary for later editing efficiently

Island model genetic programming based on frequent trees

The Island Model encourages genetic diversity, and often displays better search performance than single population models. In order to enhance the Island Model in the framework of genetic programming (GP), we propose a novel migration strategy based on frequent trees, where the frequent trees in an island mean the sub-trees appearing frequently among the individuals in the island. The proposed method evaluates each island by measuring its activation level in terms of not only how high the best fitness value is but also how many types of frequent trees are newly created, and then makes several individuals migrate from an island with high activation level to an island with low activation level, and vice versa. Using three benchmark problems widely adopted in the literature, we demonstrate that performance improvement can be achieved through incorporating the information of frequent trees into a migration strategy, and the proposed method significantly outperforms a typical method of the Island Model GP.

Depth-dependent crossover in genetic programming with frequent trees

One of the most well studied issues in genetic programming is how to make building blocks efficiently. To make building blocks, it is important to find the substructures that appear in the individuals with higher fitness. Recently, a method based on frequent substructures has been proposed, and it has shown good performance; however, the depth of trees is not considered in the method. In this paper, we propose a hybrid crossover that involves the consideration of a combination of frequent trees and the depth of trees and apply the proposed method to symbolic regression problems. We experimentally demonstrate the effectiveness of the proposed method.

A method of digital camera work focused on players and a ball

We aim at the realization of automatic adaptive contents production system of commentary soccer video based on digital shooting technique which is composed of digital camera work and digital switching technique for small audience such as a fellow some enthusiast and a individual. The digital camera work is defined as virtual panning and virtual zooming. Also, the digital switching is defined as the change of some virtual camera by controlling rapid change of frame location or size on a HD(high definition) material video. In this paper, we describe a method of digital camera work technique focused on players and a ball as a sub-system of automatic contents production system for commentary soccer video. The produced video contents with digital camera work is subjectively evaluated by AHP (Analytic Hierarchy Process).

Enhancing Island Model Genetic Programming by Controlling Frequent Trees

Abstract In evolutionary computation approaches such as genetic programming (GP), preventing premature convergence to local minima is known to improve performance. As with other evolutionary computation methods, it can be difficult to construct an effective search bias in GP that avoids local minima. In particular, it is difficult to determine which features are the most suitable for the search bias, because GP solutions are expressed in terms of trees and have multiple features. A common approach intended to local minima is known as the Island Model. This model generates multiple populations to encourage a global search and enhance genetic diversity. To improve the Island Model in the framework of GP, we propose a novel technique using a migration strategy based on textit f requent trees and a local search, where the frequent trees refer to subtrees that appear multiple times among the individuals in the island. The proposed method evaluates each island by measuring its activation level in terms of the fitness value and how many types of frequent trees have been created. Several individuals are then migrated from an island with a high activation level to an island with a low activation level, and vice versa. The proposed method also combines strong partial solutions given by a local search. Using six kinds of benchmark problems widely adopted in the literature, we demonstrate that the incorporation of frequent tree information into a migration strategy and local search effectively improves performance. The proposed method is shown to significantly outperform both a typical Island Model GP and the aged layered population structure method.

Analyzing Mediator-Activity Effects for Trust-Network Evolution in Social Media

We analyze evolution of trust networks in social media sites from a perspective of mediators. To this end, we propose two stochastic models that simulate the dynamics of creating a trust link under the presence of mediators, the A-ME and A-MAE models, where the A-ME model analyzes mediator effects for trust-network evolution in terms of mediator types, and the A-MAE model, an extension of the A-ME model, analyzes mediator-activity effects for trust-network evolution. We present an efficient method of inferring the values of model parameters from an observed sequence of trust links and user activities. Using real data from Epinions, we experimentally show that the A-MAE model significantly outperforms the A-ME model for predicting trust links in the near future under the presence of mediators, and demonstrate the effectiveness of mediator-activity information for trust-network evolution. We further clarify, by using the A-ME and A-MAE models, several characteristic properties of trust-link creation probability in the Epinions data.