Module-based intelligent video surveillance system and antitheft method for real-time detection of livestock theft

摘要

The present invention relates to a housing, a python. The present invention relates to a real time theft monitoring system for livestock using an intelligent image sensing system based on modularization, and more particularly to a system for monitoring a live theft of livestock using a network camera (IP-CCTV) and analyzing real-time input images, it is possible to analyze real-time input images by using modularization-based intelligent video surveillance to monitor real-time theft of livestock such as cattle, pigs, Systems and methods.The present invention relates to an intelligent animal products monitoring and alarm device for real time monitoring of theft of a domestic animal growing in a large / medium / small scale farmhouse by analyzing images inputted from IP-CCTV in real time, Wired / wireless IP-CCTV that generates and transmits by wire / wireless; A wired / wireless video receiving apparatus for receiving video from wired / wireless IP-CCTV; A module based intelligent image analyzing device for receiving and analyzing images from a wired / wireless video receiving device; An alarm notification service module for reading an alarm condition from an image analyzed by a module-based intelligent image analyzing device and issuing an alarm signal to the first stage of the intrusion prevention and the second stage of the theft prevention; A monitoring GUI for monitoring images analyzed by a module-based intelligent image analysis device; An embedded alarm device for generating an alarm signal by reading an intruding state or a stolen state from an image analyzed by a module-based intelligent image analyzing apparatus; An administrator terminal for receiving an alarm signal from the embedded alarm device; And an affiliate institution terminal for receiving an alarm signal from the embedded alarm device, wherein the module-based intelligent image analyzing apparatus includes an input image inputting unit for inputting an intelligent ROI (Region of Interest) through a Sobel Operator Edge extraction function, lateral edge grouping function and interest area fence automatic setting function; A moving object recognition module in a housing with a background separation algorithm function, a motion region extraction function, a motion region noise control function, and a moving object extraction function for detecting moving objects by combining Min-Max background modeling and GMM; Classification module for classifying people and livestock with the functions of extracting geometry information and object classification algorithm using Histogram of Oriented Gradient (HOG) modeling method and livestock / person classification function; An intrusion detection module for detecting a livestock movement path learning function comparing with the learned path and detecting an outbreaking presence of a person containing a path learning function; A theft detection module for detecting a livestock stolen situation that identifies a human intrusion by data stored in a human path learning DB through a human path learning function; A person movement path learning DB storing a person movement path; And a livestock route learning DB storing the livestock movement route.;