Finding a parking spot in Brussels can be a real challenge. And for Parking Brussels, the organization responsible for managing on-street parking, it’s not just about finding a spot – it’s about ensuring fairness, efficiency, and accurate enforcement. They knew there had to be a better way to manage millions of parking events each year. That’s where the power of new tech came in, with a little help from Tensr and Google.
Who is parking.brussels?
Parking Brussels manages all on-street public parking in the city. They’re responsible for ensuring that parking spaces are available and used correctly, and that violations are handled appropriately. It’s a big job, involving a huge amount of data and a constant need to improve accuracy.
The problem: more data, more challenges
The agency uses “scanning vehicles” – vehicles equipped with cameras that capture images of parked cars. This data is then reviewed to ensure parking regulations are respected. With a vast amount of data generated daily, they wanted to empower their human reviewers with more insightful information to help them assess each situation accurately and efficiently.
The goal was to provide tools that could help reviewers better interpret complex scenarios, such as nuanced license plate details, vehicles engaged in permitted activities like loading/unloading, or the presence of valid disabled parking permits.
Why Tensr and Google?
Parking.brussels knew they wanted to explore AI, but they needed help understanding its potential and how to apply it to their specific challenges. They chose Tensr because of their expertise in building practical, results-driven solutions and their strong partnership with Google.
Because of the sensitive and public nature of the data, GDPR compliance was essential. Luckily, Google technology, properly configured by Tensr, is fully GDPR-compliant. At no point were citizen data or images shared with Google or any third party. All AI models were developed and executed within GDPR-compliant environments, with all data remaining fully under the control of parking.brussels and its local implementation partner.
Four key use cases
The collaboration explored how AI could enhance the ability of human reviewers to interpret complex parking scenarios. The project focused on improving the system’s capacity to provide clearer visual information in four key aspects:
- Enhanced detail extraction for vehicle identification: Improving the clarity and accuracy of crucial vehicle identifiers, such as license plates.
- Contextual Scene Analysis: Detecting relevant activities or objects in the immediate vicinity of a parked vehicle, providing reviewers with a more complete picture of the parking situation.
- Vehicle Interior Assessment Support: Assisting reviewers by providing information about the potential presence of occupants within a vehicle.
- Detection of Official Authorizations: Improving the system’s ability to identify officially recognized permits or placards displayed on or within vehicles.
The project leveraged various Google technologies, including:
- Gemini: Used because of its capacity for detail and recognition on partially obscured images.
- Vertex AI AutoML: Used to identify and classify objects within the images and train custom models.
- Vision API: Out-of-the-box vision model used to detect broader aspects of the images, such as a person being present in the image.
The results: significant improvements and a clear path forward
The solution demonstrated significant potential for improving the accuracy and efficiency of the review process. For instance, the AI-assisted approach showed an improved ability to present clear license plate information, aiding reviewers in their assessments.
Crucially, the project reaffirmed that the technology is designed to support, not replace, human oversight. The consensus was that human reviewers remain essential in the decision-making process.
The success of the project wasn’t just about impressive technical results, it also validated how the use of AI could directly lead to:
- Improved citizen experience: By equipping reviewers with more comprehensive information, the system aims to support more accurate fine assessments. This leads to less hassle for drivers regarding potentially incorrect tickets and fewer administrative follow-ups for Parking Brussels.
- Fairer revenue collection: Enhanced accuracy in identifying parking situations helps ensure that parking regulations are applied correctly and revenue is collected fairly.
- More efficient operations: The POC indicated potential for significant time savings and operational efficiencies. This allows staff to dedicate more attention to complex cases and streamlines the overall enforcement support process.
The future of parking (and beyond)
The Parking Brussels project is a great example of how AI can be used to solve real-world problems and deliver tangible benefits. It’s not about replacing humans – it’s about equipping them with better tools and insights.
As AI continues to advance, we can expect to see even more innovative applications in areas like transportation, urban planning, and beyond. The future of infrastructure is smarter, more efficient, and more citizen-friendly, and AI is playing a key role in making that happen.
Ready to unlock the power of AI for your organization?
GC innovate brings together leading Google Cloud experts to help you navigate the complex world of AI and develop tailored solutions that drive real business value. Contact us today to learn more.
Disclaimer – GDPR & Data Privacy
Though we mentioned it in the article, it is worth reiterating that we take data privacy and security very seriously. The environment set up by Tensr with Google technology is fully compliant with EU-regulations and highly suitable for public agencies looking to use their sensitive data for AI projects.
At no point were citizen data or images shared with Google or any third party. All AI models were developed and executed within GDPR-compliant environments, with all data remaining fully under the control of parking.brussels and its local implementation partner. GC innovate and Tensr ensured data privacy was safeguarded throughout the entire project.
