Proceedings of IIAE Annual Conference

The new system for investigating violation of traffic is proposed. Shutter speed of a camera is made late. The photograph of the car which is running with the camera is taken. The line of the light by the headlight of a car can be created by this.It is possible to measure the speed of a car from a line. By this method, the speed of a car is measurable only with a camera night also. From the actual verification result, although there were a little errors, speed has been measured.

View full abstract

Show abstractHide abstract

In recent years, the touchscreen is adopted as various electronic devices. However, on a flat touchscreen, for a vision disabled person, tactile feeling with the finger which is important information may not be obtained. Therefore operativity may be spoiled. We have proposed a wearable supporting system to operate a capacitive touchscreen for them. In a proposal system, an image sensor is equipped under the middle finger and an ear is equipped with the earphone for audio assists. And if a touchscreen is traced by the middle finger, the color barcode which the image sensor caught will be recognized, and the audio assist according to a result will be made. A user pushes an icon not by the middle finger but by an index finger, following an audio assist. In this paper, the hardware platform of the camera -control part in a proposal supporting system is developed. This platform consists of an interface with a camera or a host and an image processing part. The implementation result to FPGA showed that the interface was small and most resources could be used for an image processing part. The image from a camera was able to be displayed on the display through a fundamental verification of operation.

View full abstract

Download PDF (493K)

Independent component analysis (ICA) is a signal separation technique inspired by the famous psychological phenomenon called cocktail party effect. Various kinds of its applications have been undertaken by a lot of researchers so far, and an alternative method based on a layered neural network with structural pruning was tried in the preceding studies. However, how to develop such a signal separation matrix was the center of attention, so how to apply it after training was not discussed a lot. Then, from the viewpoint of adaptability to untrained signals, some computer simulations are carried out in this study. As a result, it is found experimentaly that a vocal signal separation task with the developed separation matrix is accomplished successfully as we have intended in advance.

View full abstract

Register with J-STAGE for free!