We extend the work of Black and Yucoob on the tracking and recognition of human facial expressions using parameterized models ($optical $ow to deal with the articulated motion of human limbs. We define U "cardhoard perJon model" in which a person's limbs are represented b y U set of connected planar patches. The pcm"er ized image motion of these patches is constrained to enforce articulated mot...

In this paper I try to show that through epipolar geometry we can unify the problems of image matching in stereo, motion and object recognition, which have been treated separately. Stereo matching has been known as a 1D search problem. But matching in motion and object recognition have been known as 2D search problems. I show that by recovering epipolar geometry underlying the images, the corre...

Algorithms for human action recognition usually observe human motion only on particular level of detail. This approach requires complex algorithms to match the complexity of motion. High recognition rates are possible, when actions are distinct and clearly visible. However, this is not the case in many practical applications. To solve this we explore the possibility of developing more general a...

Abstract: Thanks to the development of Internet of Things (IoT) technologies, wearable markets have been growing rapidly. Smartwatches can be said to be the most representative product in wearable markets, and involve various hardware technologies in order to overcome the limitations of small hardware. Motion recognition sensors are a representative example of those hardware technologies. Howev...

Database of human motion has been widely used for recognizing human motion and synthesizing humanoid motions. In this paper, we propose a data structure for storing and extracting human motion data and demonstrate that the database can be applied to the recognition and motion synthesis problems in robotics. We develop an efficient method for building a human motion database from a collection of...

We propose a recognition method of camera-captured characters using motion-blur parameters. One of the most challenging problems in recognizing characters with handheld cameras is motion-blur effect. In order to cope with this problem, a generationbased learning method is introduced in the training step to simulate blurred images. In the recognition step, motion-blur parameters are estimated an...

In this paper, we present a method for the recognition of human activities. The proposed approach is based on the construction of a set of templates for each activity as well as on the measurement of the motion in each activity. Templates are designed so that they capture the structural and motion information that is most discriminative among activities. The direct motion measurements capture t...

Seeing a face move can improve familiar face recognition, face matching, and learning. More specifically, familiarity with a face may facilitate the learning of an individual's "dynamic facial signature". In the outlined research we examine the relationship between participant ratings of familiarity, the distinctiveness of motion, the amount of facial motion, and the recognition of familiar mov...

We introduce a method for the recognition and prediction of motion, based on the idea that different motions trace out different shapes in some state space. In the recognition step we use a multidimensional generalization of the shape context [1] to find the closest prototype motion to the observed data. When tested against motion capture data, our model yields excellent (99%) recognition of ga...

In this paper I try to show that through epipolar geometry we can unify the problems of image matching in stereo, motion and object recognition, which have been treated separately. Stereo matching has been known as a 1D search problem. But matching in motion and object recognition have been known as 2D search problems. I show that by recovering epipolar geometry underlying the images, the corre...