The Journal of The Institute of Image Information and Television Engineers

We propose a remote transmission system of hand clapping from the audience to the performer on live video streaming. This system consists of a collection system for a clapping button and hand clapping machines. The collection system for these buttons is to count the number of clicks they receive on the related website. The hand clapping machine is a mechanical device that imitates hand clapping and works by increasing the number of the clicks to produce a clapping sound and the physical movements of hands at the shooting location. This system is intended to reproduce the simple presence of the audience at the shooting location by transmitting movement and sound of hand clapping in real-time. We consider and evaluate this system by observing the behavior and the evaluation of the performer and audience at performances where this system is used.

View full abstract

Show abstractHide abstract

The position tracking of the pupils and corneal reflections (features) from the video camera images that capture the entire human face is important to precisely and remotely detect eye-gaze. However, doing this was difficult under intense illumination even when using the conventional two light sources and image difference method. In our former study, to resolve the difficulties, bright and dark pupil images and their corresponding non-lighting images were consecutively obtained while turning two light sources on and off.A new image processing algorithm was proposed. In the present study, a high-speed (2000 fps) camera was introduced to decrease the intervals of time need to capture the three images. In addition, the near-infrared light sources were improved to increase the brightness of the small pupil in the bright pupil image. The newly developed system enabled the detection of the features when the subject was wearing glasses and moving their head quickly (20 cm/s) and there was intense illumination (40,000 lx).

View full abstract

Download PDF (4444K)

Cystoscopy is an examination that allows medical doctors to look inside the bladder. In examinations with a flexible cystoscope, doctors need to observe whole interior of the bladder which is broadly divided into seven parts. However, since five of the parts are similar in shape and color, it is difficult to grasp the location that the cystoscope is projecting. We have proposed the use of a system for estimating the handling patterns of a flexible cystoscope, i.e., the use of neural networks to cystoscopic images and thus give more detailed observations. However, the system could not be used to estimate the handling patterns against images which have poor characteristics. We propose a method for estimating sequential handling patterns for flexible cystoscope using prediction probabilities obtained from the neural networks. The experimental results show that the average recognition rate for estimating the handling patterns has increased by 8.3% compared with the rate of the existing method.

View full abstract

This paper describes a web database system that stores specific human emotional motion data sets for 3D CG short animation. An evaluation of sample 3D CG animation movies produced by two creators with and without the proposed database showed the following results: (1) production time is drastically reduced to less than one-fifth of the conventional production time by using the developed system, and (2) the coincidence ratio between the creator's intended emotional motion and the audience's impression was more than 80%, which indicates that the proposed system generates good nonverbal communication in 3D CG animation.

View full abstract

Register with J-STAGE for free!