Pavement Crack Detection for a Smarter Urban Management

About IMM

The Intendencia de Montevideo (IMM) serves as the local government body managing public services for Montevideo, the capital of Uruguay. IMM oversees critical areas such as public transportation, waste collection, and the maintenance of public spaces. Additionally, it champions sustainable urban development and cultural initiatives, collaborating with the community to address urban challenges and foster social inclusion. IMM’s vision is to create a more equitable and livable city for all residents.

The project began with a Proof of Concept (PoC) to validate the feasibility of using state-of-the-art computer vision technology to generate the required insights. Once the technology proved viable, data collection commenced, focusing on key areas:

• Detecting signage and identifying its condition, including vandalism or other damage.
• Evaluating pavement conditions for cracks, breaks, and defects in paint.
• Assessing the state of sidewalks.

A significant dataset of images was collected and labeled according to the project’s objectives. This included tagging signage in poor condition and vandalized states to ensure accurate training of the AI model. The trained network provided reliable and actionable insights, tailored to IMM’s operational needs.