Electronics and Telecommunications Research Institute (ETRI) of South Korea is in the midst of developing real-time CCTVs and a system which predicts the level of crime risk based on the analysis of past crime statistics.
Location details and movement types are essential mechanisms for spotting criminals.
‘Foreseeing crime’ was regarded as something unrealistic, but surprisingly enough, it is not something impossible. Based on past crime statistics and CCTV footages, Korean researchers are developing an AI system which automatically analyses the probability of a crime. Such systems are crucial for preventing crime and creating a safer living environment.
The Electronics and Telecommunications Research Institute (ETRI) is currently working on the ‘Predictive Video Surveillance Core Technology’, in which CCTV analysis foresees the probability and the type of crime. The present situation analysis and its comparison with the past crime data, will enable the system to calculate the degree of danger and act against it in advance. The prediction of assaults taking place at a certain time & place as well as crime details regarding criminals who have committed violent crimes, are to be actualised.
CCTV video analysis working hand in hand with statistical crime prediction system
To aim for a more effective visualisation of public order, CCTV video analysis is currently being added onto the statistical crime predication system. In other words, if a crime prediction system was merely a tool to measure the risk based on the analysis of past crimes, this new technology manages to apply real time data and predict crime risk in minutes and hours. The devastating fact of how dangerous situations may be taking place in the present moment, was the trigger for the invention of such technology. >
The disadvantage of past crime CCTV footages is that they fail to spot abnormal behaviours within the time given. It is for such reasons that researchers try to depict the current situation by referring to past crime patterns i.e. a Déjà vu of crimes committed in the past. Since finding crime prone areas with the naked eye is in many cases almost impossible, risk prediction analysis consisting of an AI analysis procedure is highly effective.
‘Intelligent CCTV Video Analysis Technology’ enables researchers to make an accurate observation of the current situation, where certain movements are determined by a computer simulation of changing sound to an image. For example, the sound of footsteps determines whether the person is in a hurry or in a tranquil state. Visual intelligence technology offers clearer visibility on whether the person is wearing a hat, glasses, masks, carrying bags or tools on the screen.
An additional function of AI CCTV is comparing the current situation with past crimes in order to measure the level of danger. For example, if a man wearing a mask and a hat follows a woman along an obscure street at 2am, a high alert alarm will go off. On the contrary, if the same situation were to be observed in the town center at 2pm, the level of danger will decrease significantly.
The Development of Crime Data study and the Management of sexual assault by ex-convicts
The AI technology in which a research is currently being conducted on, observes factors which appear on a crime scene. The research consists of over 20,000 court decisions analysis and videos provided by the Florida State University which contain crime simulations.
Furthermore, specific technology which deals with the management of sexual assault by ex-convicts will also be thoroughly developed. Alarms dependent on location details is not to be fully relied on and using CCTVs for spotting criminals amidst a crowd of people is not accurate enough. For a more distinct identification of the victim, data from ETRI’s Person Re-ID (re-identification) technology and the route of those wearing electronic anklets, will be directly transferred to the nearest CCTV system. The result of such processes is clear - a more accurate management of those liable to committing crime and swifter actions against signs of crime. Criminal activities will be identified in real time once the above technology is applied to the CCTV Integrated Control Centre and Police Control System of 229 local governments.