Hidehiro Ohki

Denighting: Enhancement of nighttime images for a surveillance camera

Nighttime images of a scene from a surveillance camera have lower contrast and higher noise than their corresponding daytime images of the same scene due to low illumination. Denighting is an image enhancement method for improving nighttime images, so that they are closer to those that would have been taken during daytime. The method exploits the fact that background images of the same scene have been captured all day long with a much higher quality. We present several results of the enhancement of low quality nighttime images using denighting.

An evaluation on robustness and brittleness of HOG features of human detection

Detecting humans in an image sequence is one of the most difficult problems in object recognition. It is necessary to define a robust descriptor which can extract human features from images, to improve the detecting performance. Histograms of Oriented Gradients(HOG) descriptor significantly outperforms compared with the others on human detection. The descriptor is known as a robustness descriptor for illumination changes and geometrical changes in local regions. To obtain the high detection performance using the descriptor effectively, it is necessary to know the robustness and brittleness of the descriptor. In this paper, we experiment the descriptor to verify its robustness to illumination changes and to scrutinize its brittleness. For the experiments, we use LogitBoost which can create a human-detector by learning human features.

A comparison with covariance features on player uniform number recognition

Broadcast sports video report is expected be the generated player data in real time. Therefore, uniform number recognition need to fast computing. Covariance feature has possibilities to do it in real time. We present a method for uniform number recognition using the covariance feature as a region descriptor. The covariance feature is represented by the covariance matrix of image features such as spatial position, intensity, higher order derivatives, etc. Thus, the covariance feature vary by used image features. Feature matching is a simple nearest neighbor search under a distance measure [1]. In the experiments, the six covariances compared. The recognition rate is 79% in a multiple player game.

Two layered classification using qualitative and quantitative attributes for QRS complex analysis

QRS complex classification in Holter electrocardiogram have been developed using the correlation coefficient methods. However, the accuracy of this traditional classification is not fully satisfied the clinical needs. In this paper, we propose a two-layered classification using qualitative and quantitative attributes. In the first layer, 24 components in a FFT power spectrum for each beat are calculated as the quantitative attributes and are classified using K-means algorithm. In the second layer, the numbers of low, middle and high peaks before/after an R wave are computed as the qualitative attributes and are also classified by the same way. We evaluated our method for ten cases from MIT-BIH arrhythmia databases and compared with a standard cross correlation coefficient method. The classification error rate of the correlation coefficient method and proposed method is 1.10% and 0.79%. We confirmed that the accuracy in our method for the QRS complex analysis is significantly improved.

Digital scorebook: football logging and visualization using image processing support

We propose a digital scorebook for football game which digitizes a football game video and presents it as an animation. The proposed system consists of player position estimation from the game video, event selection interface and player movement animation. Player position estimation allows for flexible movements and angles of the cameras including zoom in and out, pan, tilt, and yaw. This reliable and robust estimation of the player movement is based on image analysis by synthesis and Generalized Hough Transform(GHT). The operator can annotate game scenes based on player movement data using event selection interface. The player movement is represented by the animation whose characters have number or letter figures to emphasize the data. We demonstrate the applicability of player position estimation and play annotation scheme via the character behaviors in animation.

Denight : Nighttime Image Enhancement using Daytime Image

Nighttime images of a scene from a surveillance camera have lower contrast and higher noise than their corresponding daytime images of the same scene due to low illumination. Denighting is an image enhancement method for improving nighttime images, so that they are closer to those that would have been taken during daytime. The method exploits the fact that background images of the same scene have been captured all day long with a much higher quality. We present several results of the enhancement of low quality nighttime images using denighting.

A self-diagnosis under 2D projectivity for local descriptor base template matching

2D projectivity is an invertible mapping to present the perspective imaging of a world plane by projective translation, called homography. Good image feature have to be robust under 2D projectivity caused by any camera movements. In the standard performance evaluation of template matching, many real captured images of many scenes are ordinarily used. However it is not enough to evaluate the robustness under 2D projectivity in detail because the variations of real camera pose and position in the 3D world are limited and the capturing cost is expensive. During the early stage of the template matching development, an easy performance evaluation method is required to examine the behavior. We propose a self-diagnosis method to measure the robustness of local descriptor base template matching between a template image and reference images which are created by projective translation of the template image. We focus on the template matching consisting of a feature point extraction and a local descriptor matching. The proposed method evaluates the spatial accuracy of the feature points and the estimated template positions in the reference images with local descriptor matchings. Four metrics, feature point precision (PP), feature point recall (PR), local descriptor matching precision (MP) and local descriptor matching recall (MR) are introduced to evaluate the performance. The experiment results will be appeared in the final manuscript to show the effectiveness of our method.

An Impressive Data Animating for Positional Movement of Soccer Players

In this paper, we propose a system which decides camera work in a 3D virtual soccer game and generates 3DCG animation automatically, called data animating. The 3D virtual soccer game is represented by the play events including player IDs, player positions, types of play and so on. These properties are created by real soccer video analysis system, called digital scorebook. The system generates a 3DCG animation according to two user selections of soccer play events. To create impressive soccer animation from real soccer game, we focus on virtual cinematography as the art of rhetoric of animation scene. The system can automate a composition of animation story and decide camera work based on the virtual cinematography. Our animation story has the three part, introduction, development and conclusion, selected from the organization of Chinese poetry. The appropriate camera work is decided in each part. Moreover, the picture composition for each part in a screen is calculated based on golden ratio. In the experimental result, the system can generate 3DCG animation automatically from the play events selected by user

A color feature learning and robust interpretation of moving object using HMM

Spot observation by computer vision is the one of fundamental key technology. In this paper, we propose a moving object color learning and robust recognition with Hidden Markov Model(HMM) from various scenes under different light conditions. Feature box which is a small area in a image is defined to observe a spot. The time series data of such as averages of R, G, B intensities in feature boxes are the input signals of our system. The HMMs learn correspondences of input signals with object color of moving object and background. Baum-Welch and Vi-terbi algorithms are used to learning and interpret the spot scene transition. In moving object color interpretation, the system selects a best HMM model for input signals using maximum likelihood method based on a given object color appearance grammar. In the experiment, we examine the number of feature boxes and its shapes under some light conditions. The feature boxes adjoining in vertical column whose height is almost same as objects results best score in the experiment. It shows the effectiveness of our method.