Anzeige
Erschienen in:
2013 | OriginalPaper | Buchkapitel
Restroom Human Detection Using One-Dimensional Brightness Distribution Sensor
verfasst von : Shorta Nakashima, Shenglin Mu, Okabe Shintaro, Kanya Tanaka, Yuji Wakasa, Yuhki Kitazono, Seiichi Serikawa
Erschienen in: Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing
Verlag: Springer International Publishing
As aging society problem goes serious; systems to confirm safety of elders in daily life are expected. In this paper, a sensor, which detects person localization without privacy offending, applying brightness distribution is realized. In the proposed design, the sensor is constructed with a line sensor and cylindrical lens to obtain one-dimensional brightness distribution. Comparing with conventional line sensors, CMOS area sensors are with low cost, and high sensitivity. Therefore, in the proposed sensor, the CMOS area sensor is applied as covered in certain areas physically, so that it behaves as a line sensor. The proposed sensor is able to obtain one-dimensional horizontal brightness distribution that is approximately equal to integration value of each vertical pixel line of two-dimensional image. By employing this method, the information of the target person’s position and movement status can be obtained without using two-dimensional detail texture image.