Using AI to combat street crimes
20 July 2021
According to OSAC's Malaysia 2020 Crime & Safety Report, common crimes in Malaysia include snatch thefts and residential or commercial robberies. Snatch thefts and robberies seem like relatively common occurrences, but they can be fatal at times. Statistics show that over 2,000 snatch thefts or robberies were reported in Malaysia in 2019 alone, and this number could be substantially higher when factoring in unreported cases. The global pandemic and subsequent movement control order across the country may have reduced street crimes in 2020. However, such crimes are anticipated to continue with an upward trend as the nation progresses towards a post-pandemic era.
In an attempt to curb these crimes, city councillors, retailers, commercial and residential management have ramped up the deployment of closed-circuit television (CCTV) cameras across urban areas. As of last year, Kuala Lumpur alone has about 1,900 existing CCTVs for traffic management, 100 at flash flood hotpots, 270 at public parks, 130 at rivers and 309 for security surveillance. Thousands of CCTVs were also installed across various retail outlets, commercial and residential units. This trend will continue as the vast deployment of CCTV cameras is meant to serve as a deterrence against urban crimes.
These trends mentioned above, however, are at odds with each other. On the one hand, street robberies are projected to rise as the country continues with its rapid urbanisation in a post-pandemic era. On the other hand, video surveillance is a quintessentially passive driven system, whereby recorded or archived content is used primarily as evidence of a criminal activity that has taken place. Netizens have regularly witnessed the horrors of snatch thefts or robberies captured from CCTVs which frequently goes viral on social media. More often, these perpetrators are able to evade apprehension due to the delayed response of alerting authorities. Crucially, victims of such crimes would have to endure the consequences of being robbed both emotionally and physically. More worrying is that the flow of illegal firearms into Malaysia risks increasing the severity of robberies carried out by individuals or groups of criminals. Given this conflict, a natural question to ask is: Can a citizen remain safe despite the presence of CCTV cameras?
To answer this question, researchers at the School of Information Technology, Monash University Malaysia, embarked on a research and development endeavour to transform conventional CCTVs into an autonomously intelligent system to detect street crimes in real-time. This endeavour is led by Dr Vishnu Monn Baskaran and PhD student Marcus Lim Jun Yi and funded by the Ministry of Higher Education's Fundamental Research Grant Scheme. The feasibility of this research is motivated by the rapid evolution of artificial intelligence and, in particular, deep neural network algorithms. There is a new opportunity to realise a reliable smart video surveillance framework, coupled with significant advancements in high-performance computing technology. Typically, there are three stages in a smart video surveillance platform.
The first stage involves having AI-based software to process live video surveillance images to detect weapons. In most cases, urban robberies would involve the usage of weapons such as guns. Automatically identifying the presence of a weapon from a surveillance camera in real-time would increase the software's reliability in assessing a threat within a surveilled area. The second stage involves formulating a relation between the human wielding the weapon and the weapon itself for aggressive action recognition. Most importantly, the first and second stages are executed autonomously using AI developed software with minimal manual intervention. The third stage generates an alert that is relayed to medical crews and law enforcement officers to dispatch them quickly to provide aid to the victim and apprehend the perpetrator.
The significance of a real-time alert and response mechanism could re-envision how AI is used to strengthen law enforcement and to further deter criminal activities in enhancing public safety.
Presently, the research team at Monash University Malaysia has completed stage one in developing a smart surveillance system that can detect handguns from surveillance cameras in real-time accurately. The team initially focused on automated handgun detection, given that crimes using firearms are more prevalent globally, especially in the north and south of America and in parts of southeast Asia. The outcomes of their research were published in the Engineering Applications of Artificial Intelligence journal. The team also won a gold medal for their project, Monash Automatic Gun Detection System (MAGTS), at the 31st International Invention, Innovation & Technology Exhibition 2020 (ITEX 2020).
Dr Vishnu Monn, Marcus Lim and the team are now focusing their efforts towards formulating an accurate human to weapon relation model for classifying aggressive human actions, which represents the second stage in realising a smart video surveillance platform. They are also fine-tuning the outcomes from stage one of their research to detect knives and machetes, which are more prevalent in robberies that are carried out in Malaysia.
This research could also be extended to include person re-identification (i.e., spotting or tracking a person from one camera to another). Through person re-identification, the location or movement of a perpetrator can be translated into geographical coordinates. These coordinates are then relayed to multiple notification modules and plotted on a map, representing a unified urban/city alarm notification system. This, in turn, could further complement efforts in apprehending the law offender.
The importance and significance of this research are driven from the Government Transformation Programme (GTP) 1.0 report, which mentions the following, "Despite the improvements in the country's crime rate and its continued downward trajectory, public perception of safety is still a challenge as 52.8 per cent of the rakyat (citizens) say they still do not feel safe."
The government recognises that safety is paramount in sustaining robust economic growth. As such, the proposed outcomes of this research establish the fundamental components of an autonomous surveillance platform. The platform potentially expands law enforcement's omnipresence program by substantially reducing response time at the point of theft identification. These improvements align with version 2.0 of the GTP to reduce the crime index, which is expected to improve public perception of urban safety.
In addition, it is envisaged that machine-assisted analysis of human actions in real-time will provide additional support for social and scientific domains such as forensic science, criminal deterrence, criminal investigation, medical aid, and psychotherapy. These solutions can transform the nation's capital into a smart and safe city in line with Transformasi Nasional (TN50), thus paving the way for a vibrant economic and societal development.