Depth measurement method with applying stereo vision to one-dimensional brightness distribution sensors

In recent years, aging society is a serious problem which the whole Japan has to face to. As an important aspect of the aging society problem, safety in daily life of the elderly attracts much attention. Thus, sensors and integrated systems for confirming safety of the elderly people in daily life have been developing. Thereby, the developments are expected to relieve burdensome safety confirmation tasks of care workers. A system with employing a sensor named as One-dimensional brightness distribution sensor (Obrid-Sensor), which is able to get localization of a subject without privacy offending, was proposed in previous research. By employing the proposed sensor, the information of the subject's presence, position, and motion can be acquired without using two-dimensional texture image. However, the system wasn't able to acquire the depth information between the sensor and a subject. Accordingly, we propose a depth measurement method with applying stereo vision to two Obrid-Sensors to solve the problem. In this proposed method, the error in horizontal direction of Obrid-Sensor is experimentally-verified before the measuring of depth distance. By this way, we confirm that the depth measurement is feasible by employing Obrid-Sensors. It is possible to estimate the size of the subject according to the information fetched by Obrid-Sensors employing the proposed depth measurement method. Therefore, this method using Obrid-Sensors is expected to improve the recognizing accuracy of conditions in the elderly's daily life.