CCTV

AI trained on CCTV footage to be used to fight harassment and violence on public transport

Artificial intelligence (AI) will be applied to CCTV footage from cameras on the Sydney train network to detect threatening behaviours.

The trial is the result of Transport for NSW’s Safety After Dark Innovation Challenge, which sought initiatives to improve safety for women travelling on public transport.

The AI CCTV solution was proposed by the University of Wollongong’s SMART Infrastructure Facility. The software would automatically analyse real-time footage and alert an operator when it detect a suspicious incident or unsafe environment.

Lead researcher John Barthelemy said the software could be applied in a number of ways.

“The AI will be trained to detect incidents such as people fighting, a group of agitated persons, people following someone else, and arguments or other abnormal behaviour,” he said.

“It can also identify an unsafe environment, such as where there is a lack of lighting. The system will then alert a human operator who can quickly react if there is an issue.”

The project is based on PhD student Yan Qian’s research that is using computer vision across multiple cameras to improve understandings of traffic and pedestrian movements.

“We are using open-source code that tries to estimate the poses of a human being and predict if there’s a fight,” she said.

“As far as we know, nothing like this has been attempted globally. We are pushing the limits of the technology.”

Other successful projects came from data sharing platform She’s a Crowd, safety technology vendors Guardian LifeStream and Cardno/UNSW.

Minister for Transport Andrew Constance said that transport operators had an obligation to improve the experience of travelling on their networks.

“We want all our customers to feel safe on the network and it is not good enough that 9 out of 10 Australian women experience harassment on the street and modify their behaviour in response,” Constance said.

“The winners were chosen for their potential to meaningfully address real safety issues, and their ability to use creative and sophisticated new technologies to make a real difference.”

Alstom

Alstom using AI solution to manage social distancing in Panama

Alstom is using artificial intelligence (AI) technology to manage passenger flow and maintain social distancing.

The system is currently in use on the Panama Metro, where Alstom has deployed its Mastria multimodal supervision and mobility orchestration solution.

Initially used to manage passenger crowding in peak periods, the system has been adapted to maintain social distancing requirements due to the coronavirus (COVID-19).

“The ability of this tool to analyse millions of pieces data in real time makes it an indispensable ally for operators at all times, but especially in the current context. Simply put, it matches transport offer to demand, no matter the conditions,” said Stephane Feray-Beaumont, vice president innovation & smart mobility of Alstom Digital Mobility.

The system gathers data from a various of data sources, including train weight sensors, ticketing machines, traffic signalling, management systems, surveillance cameras, and mobile network.

This data is then fed into an algorithm, which determines when the network is reaching its capacity limit. The operator can then carry out actions in response to the data, whether that be increasing train frequency, adjusting entry to the system, managing people on the platform, or suggesting changes to transport systems that feed into the rail network.

Since being installed on the Panama Metro late in 2019, Mastria has been mining the system’s data to be able to intelligently predict when the system will be reaching capacity through machine learning techniques. After three months, the system could predict saturation up to 30 minutes before it was visibly observed, enabling remedial action to be taken, and reducing wait times in stations by 12 per cent.

During COVID-19, the system has been used to limit train loads to 40 per cent of maximum capacity. To achieve this, new features such as real time monitoring of passenger density and flows, simulating limiting access to stations, and analysing the distribution of passengers along trains have been developed.

When the COVID-19 threat recedes, Panamanian operators will be able to use the new features to manage the return to public transport, said Feray-Beaumont.

“All experts agree that public transportation, and particularly rail, will continue to be the backbone of urban mobility. Artificial intelligence will be our best travel partner in this new era of mobility.”

Computing around artificial intelligence and autonomous vehicles for the rail industry

There have been significant advances in the realm of artificial intelligence (AI) and autonomous vehicles in industry, with segments such as the mining sector pioneering the implementation of this technology – including autonomous trains – in Australia. Driving these developments is the computing systems that enable autonomous platforms and AI to operate effectively and securely. This white paper discusses the technology in context of its global growth and Australian adoption. It provides insights into the features that enable the success of in-vehicle computing systems in harsh environments, along with examples of why and how these systems are best suited to industrial rail applications.

Read more:

Sentinel Safety

Sentinel Safety brings the latest AI technology to protect pedestrians in the rail industry

The risk of injury and near misses for workers around mobile plant and machinery is always a concern during the construction and maintenance of railways where separation of people and plant is not possible. To date, most hazard prevention technologies involve a tag-based system or administrative controls which are not always the most comprehensive solution to the dynamic rail maintenance and construction environment.

Developed over three years by an in-house team of Brisbane-based engineers, PRM Engineering Services have produced the Sentinel Vision A.I. pedestrian detection system, for the specific safety requirements of the rail industry. The system uses the latest in artificial intelligence and pedestrian recognition to detect when a pedestrian is in a machine’s blind spots or enters hazardous zones near mobile machinery, warning both the operator and the pedestrian.

Working in real-time, the Sentinel Vision A.I. system incorporates multiple cameras, that are mounted to mobile machines such as wheel loaders, excavators, and on-track vehicles with as many or as few cameras installed as needed to cover blind spots and assist the operator in identifying people around the machine. Sentinel Vision A.I. is the first pedestrian detection system to alert both the operator and pedestrian. This innovation has been found to cause long-term behavioural change in pedestrians working around mobile plant and machinery. Sentinel Vision A.I. uses a unique voice alarm system to ‘talk’ to the pedestrian, cutting through the beeps and buzzes that that workers hear on sites every day.

The system has been trialled by several top tier rail authorities with positive results and many have reported that when people are alerted by the voice alarm, behavioural change and greater awareness of risky behaviour around mobile plant is achieved. Ideally, over time, Sentinel Vision A.I. will be activated less as people have learnt not to walk in front or behind active vehicles, reducing the risk of accidents and injuries.

The system takes images from the detection cameras and then processes the information through an A.I. neural network to determine if there is anything that looks like a person, or part of a person, and if there is, it triggers internal and external alarms. Detection zones are customisable and determined with an easy to use drag and drop interface, and an additional option of pre-warning zones.  The system has been trialled and used in a range of different operating environments and environmental conditions with positive feedback.

Sentinel Vision A.I. is one of a number of innovative products developed by PRM Engineering Services. Part of the PRM Group of companies, which has been providing safety systems and equipment to the rail industry for over 20 years, PRM Engineering Services designs bespoke safety and control systems that meet the unique needs of operators. Through our partnerships and experience gained in the rail and heavy machinery industries, PRM Engineering Services’ range of Sentinel Safety systems were developed to meet the changing safety and risk management requirements of rail authorities.

The Sentinel Safety range also includes several Height and Slew limiters used throughout the rail and construction industries to allow safe operation around powerlines and within confined spaces. The Sentinel Height and Slew limiters have been used by rail authorities Australia wide for a several years and can be retrofitted to any machine with articulated booms.

Based on this experience PRM has also recently released additional optional features including HV detection and RFID for attachment recognition. By combining the functionality of our widely used Sentinel Height and Slew limiters with a patented Sentinel HV Aerial Module, the system can ensure safe operation around powerlines from the moment the machine is turned on. The system prevents the machine moving within the exclusion zone around powerlines and motion-cut valving prevents the machine from moving closer while allowing the operator to direct the machine away from the electricity source.

The Sentinel Height and Slew limiters are perfect for the safe operation of excavators, loaders, skid steers and backhoes when working under overhead powerlines, in and around bridges and inside tunnels and can be installed on new and old machines alike. The Sentinel Height and Slew limiters also have are range of rail specific systems to the meet the machine safety requirements of multiple rail authorities and councils.

PRM Engineering Services are passionate about safety and have a long-standing heritage of safety system design and installation since 2002. With experience in the rail and earthmoving industries, PRM Engineering Services have become integrators and developers of a number of unique safety and control systems that meet customer requirements. These projects have ranged in scope from customisations of height or slew systems through to full redesign of control systems for on-track rail vehicles. Along with our team of talented engineers, the PRM Group of companies can also assist with the installation or modification of electrical, hydraulic, and control systems for heavy machinery, enabling PRM Engineering Services to offer end-to end innovative and customised solutions to our wide range of customers.

Find out more at: https://www.sentinelsafety.com.au/.