Title :
A Fuzzy Human Detection for Security System Using Infrared Laser Camera
Author :
Takeda, Takahiro ; Kuramoto, Koji ; Kobashi, Shoji ; Hata, Yuki
Author_Institution :
Grad. Sch. of Eng., Univ. of Hyogo, Himeji, Japan
Abstract :
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.
Keywords :
cameras; feature extraction; fuzzy logic; fuzzy set theory; image classification; infrared imaging; object detection; pattern clustering; sampling methods; surveillance; aspect ratio calculation; distance distribution data; fuzzy c-means clustering method; fuzzy human detection; fuzzy if-then rules; fuzzy logic; fuzzy membership functions; height calculation; infrared laser camera; moving object detection; object classification method; sampling time; security system; thickness calculation; Cameras; Educational institutions; Feature extraction; Lasers; Measurement by laser beam; Security; Three-dimensional displays; fuzzy logic; human detection; infrared laser camera; night visioin;
Conference_Titel :
Multiple-Valued Logic (ISMVL), 2013 IEEE 43rd International Symposium on
Conference_Location :
Toyama
Print_ISBN :
978-1-4673-6067-8
Electronic_ISBN :
0195-623X
DOI :
10.1109/ISMVL.2013.4