This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by h...This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by hands, as an alternative, the automated marionette is studied. However, the automtic marionette performance is limited in the silence and mobility. Therefore, an independent shifter to move freely on the stage is required. The magnetic device which connects the movable robot and the marionette controlling robot is conceived. The magnetic device is improved and applied by considering the features of the marionette robot, which is the irregular movement of the marionette controller and of the parallel limited area. The burden of being trapped on the magnet is minimized by dividing the robot to the upper and lower parts of the marionette performance stage. The direction of the magnet is considered to make the mobile robot to move freely. Thus, the efficiency and safety of the device is confirmed by balancing the strength with the permanent magnet.展开更多
The paper proposes a new method of ＂Separated Same Rectangle Feature （SSRF）＂ for face detection. Generally, Haar-like feature is used to make an Adaboost training algorithm with strong classifier. Haar-like featur...The paper proposes a new method of ＂Separated Same Rectangle Feature （SSRF）＂ for face detection. Generally, Haar-like feature is used to make an Adaboost training algorithm with strong classifier. Haar-like feature is composed of two or more attached same rectangles. Inefficiency of the Haar-like feature often results from two or more attached same rectangles. But the proposed SSRF are composed of two separated same rectangles. So, it is very flexible and detailed. Therefore it creates more accurate strong classifier than Haar-like feature. SSRF uses integral image to reduce execuive time. Haar-like feature calculates the Sanl of intmsities of pixels on two or more rectangles. But SSRF always calculates the stun of intensities of pixels on only two rectangles. The weak classifier of Ariaboost algorithm based on SSRF is fastex than one based on Haar-like feature. In the experiment, we use 1 000 face images and 1 000nm- face images for Adaboost training. The proposed SSRF shows about 0.9% higher acctwacy than Haar-like features.展开更多
The paper aims to execute puppet without restrictions by controling puppet using robot. We controling puppet in the same way as the present puppet, but we perform this by robot. It offers more advantages and lessen th...The paper aims to execute puppet without restrictions by controling puppet using robot. We controling puppet in the same way as the present puppet, but we perform this by robot. It offers more advantages and lessen the weak points. It needs various actions and expressions because of the nature of a puppet. The biggest problem which executes this is the ways to create a system. This thesis proposes motion capture of developed method with solution of this problem. So, we create various contents needed by puppet. In this part, developed method means a mixed method on the basis of optical system and magnetic system used mainly for the present method of motion capture. We lessen the weak points of each method and propoe solution of create motion for pupct by offering more advantages. So we solve difficulties of executing puppet and probable probkans when we execute puppet by using robot. The solution of this thesis is proven by applying control of puppet.展开更多
基金supported bythe Ministry of Knowledge Economy,Korea,theITRC(Information Technology Research Center)support program(NIPA-2010-(C1090-1021-0010))the Brain Korea 21 Project in 2010
文摘This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by hands, as an alternative, the automated marionette is studied. However, the automtic marionette performance is limited in the silence and mobility. Therefore, an independent shifter to move freely on the stage is required. The magnetic device which connects the movable robot and the marionette controlling robot is conceived. The magnetic device is improved and applied by considering the features of the marionette robot, which is the irregular movement of the marionette controller and of the parallel limited area. The burden of being trapped on the magnet is minimized by dividing the robot to the upper and lower parts of the marionette performance stage. The direction of the magnet is considered to make the mobile robot to move freely. Thus, the efficiency and safety of the device is confirmed by balancing the strength with the permanent magnet.
基金supported by the Korea Research Foundation Grant funded by the Korean Government(MOEHRD),the MKE(The Ministry of Knowledge Economy,Korea)the ITRC(Information Technology Research Center)support program(NIPA-2009-(C1090-0902-0007))
文摘The paper proposes a new method of ＂Separated Same Rectangle Feature （SSRF）＂ for face detection. Generally, Haar-like feature is used to make an Adaboost training algorithm with strong classifier. Haar-like feature is composed of two or more attached same rectangles. Inefficiency of the Haar-like feature often results from two or more attached same rectangles. But the proposed SSRF are composed of two separated same rectangles. So, it is very flexible and detailed. Therefore it creates more accurate strong classifier than Haar-like feature. SSRF uses integral image to reduce execuive time. Haar-like feature calculates the Sanl of intmsities of pixels on two or more rectangles. But SSRF always calculates the stun of intensities of pixels on only two rectangles. The weak classifier of Ariaboost algorithm based on SSRF is fastex than one based on Haar-like feature. In the experiment, we use 1 000 face images and 1 000nm- face images for Adaboost training. The proposed SSRF shows about 0.9% higher acctwacy than Haar-like features.
基金supported bythe Ministry of Knowledge Economy,Korea,the ITRC(Information Technology Research Center)support program(No.NIPA-2009-(C1090-0902-0007))
文摘The paper aims to execute puppet without restrictions by controling puppet using robot. We controling puppet in the same way as the present puppet, but we perform this by robot. It offers more advantages and lessen the weak points. It needs various actions and expressions because of the nature of a puppet. The biggest problem which executes this is the ways to create a system. This thesis proposes motion capture of developed method with solution of this problem. So, we create various contents needed by puppet. In this part, developed method means a mixed method on the basis of optical system and magnetic system used mainly for the present method of motion capture. We lessen the weak points of each method and propoe solution of create motion for pupct by offering more advantages. So we solve difficulties of executing puppet and probable probkans when we execute puppet by using robot. The solution of this thesis is proven by applying control of puppet.
