A Fuzzy Human Detection for Security System Using Infrared Laser Camera
Takahiro Takeda, K. Kuramoto, Syoji Kobashi, Yutaka Hata · 2013
This paper describes an object classification method using infrared laser camera. The method detects moving objects from a distance distribution data. We classify the object to adults, children and other objects. The objects are extracted and clustered by fuzzy c-means clustering method. To classify the object, we calculate the height, thickness, aspect ratio and occupancy of the object as features from a sampling time. Fuzzy if-then rules and fuzzy membership functions are derived from knowledge of human and object. The system classifies the object based on fuzzy logic. In our experiment, we employed seven volunteers, two dogs and a box, and the system successfully classified them.