Garbage dumper detection system and method using multi-characteristic information in surveillance camera environment

摘要

The present invention relates to a system and method for detecting a garbage dumping actor using multiple feature information in a surveillance camera environment, comprising: a feature database in which feature data for extracting features of a target is stored; an image acquisition unit for acquiring an image photographed through a pre-installed camera; a target setting unit for setting a person holding the object as a feature extraction target using a deep learning model previously learned from the image acquired through the image acquisition unit; a feature extraction unit for extracting feature data for determining whether a specific action is performed from a set feature extraction target; and a specific behavior detection unit configured to detect a garbage dumping behavior by using the characteristic information extracted through the characteristic extraction unit.