This article presents five concrete use cases of AI applications in the public transport industry and illustrates how this sector can benefit from them.
Europe is at the forefront of developing AI in transport and in the creation of autonomous transport. In October, in France, RATP announced an innovative application. The company decided to launch an autonomous bus line in 2019. The tests will be carried out in the “Val de Marne” on line 393, with passengers on board. The initiative may go as far as full automation.
Despite the buzz around it, autonomous transportation is not the only revolutionary high value-added project that AI could bring to the sector. The public transport industry contains a large number of possible applications for AI and visual recognition. Thus, AI can significantly benefit this industry.
To give you an idea, here are some examples of concrete use cases in the industry.
Station security enhancement
Equipping existing video surveillance cameras with automatic detection systems may prevent many accidents and restore users confidence. A study published in 2018 by the “Observatoire national de la délinquance et des réponses pénales” (ONDRP) shows that 51% of women and 38% of men feel insecure when using public transport. An AI trained to recognize a potential danger (e.g., an assault or abandoned baggage) can alert a security guard in real time. The guard can then immediately respond on site. Similarly, real-time detection of people falling on the tracks would allow to rescue them as quickly as possible and automatically stop a vehicle in case of danger.
Passenger flow management
Cameras equipped with visual recognition can accurately count users at stations, both on platforms and in vehicles. Thus, they optimize the management of passenger flows and the hourly frequency of trains. Smart cameras provide a better understanding of what is happening inside public transport. They also help to collect data on empty seats, off-peak hours, and also discomfort and incivility on some networks. These valuable indicators allow companies to quickly adapt to conditions on the ground.
Fraud prevention
In stations, visual recognition supports the detection and estimation of fraud. According to estimates by the “Court of Auditors'”, fraud-related expenses represented a loss of €191 million for RATP and SNCF in 2016. Smart cameras may automatically detect people who straddle the access turnstile and do not stamp their tickets.
Predictive maintenance
Video recognition may also benefit the entire maintenance sector. In fact, smart cameras can detect problems on the tracks such as missing screws, cracks on the rails, worn pantographs, etc. This information goes directly to the technicians in charge of maintenance, who can then act quickly and effectively.
Improved customer service on board
Finally, there are other possible applications of AI in less obvious areas but that are just as interesting for companies. An example is in-train catering equipped with automatic cash registers. By detecting food and drinks on passengers’ trays, they may make the queues at the bar more fluid and the traveler’s experience more pleasant.
Conclusion
The public transport industry aggregates several sectors (i.e. safety, mobility, and catering) that make it a real attractor of use cases for visual recognition. The good news is that its applications can be implemented as early as 2019 since they are mainly based on existing video surveillance camera networks.
This allows for both accelerated implementation and scalability and better amortization of the existing systems. Production start-up costs are low due to the reuse of existing camera fleets. Also, the availability of data reduces the development of the algorithms. Indeed, data emitted by video surveillance cameras are already collected to train detection algorithms. Thus, it is possible to develop visual recognition systems in only a few weeks, and then increase performance over time in the field.
In the public transport industry, profits can be made even in the short term if AI is implemented. Moreover, the return on investment is very high because the value provided is identifiable and the benefits are multiple.
Public transport industry players are taking advantage of this golden opportunity. An example is RATP’s autonomous buses. Another is SNCF, which recently launched a call for tenders for a video protection project. France is on track to launch industrial projects led by AI in 2019, for the greater benefit of all citizens!
Thanks for reading!
Augustin Marty, CEO Deepomatic
