Key Challenges.

Cracks on a concrete buildings and infrastructures should be ideally detected at an early stage in order to prevent further damage. To ensure safety, it is necessary to inspect the quality of concrete infrastructures at regular intervals. Conventional methods usually include manual inspection of concrete surfaces to determine defects. Though effective, these methods are extremely time- inefficient and labour intensive. The traditional methods of crack detection on concrete buildings and infrastructures involve significant manual labor. Grids are first marked along the entire length of the concrete buildings and infrastructures. A skilled engineer then walks from one section of a grid to another closely inspecting the surface and marking the location of cracks. Apart from being extremely time exhaustive task, such methods heavily depend on the experience of the specialist. This method also tends to be inaccurate. Failure of detection of these initial cracks might lead to decrease in longevity of infrastructures and sometimes collapse.

Currently, the big problem managing construction projects is accurately predicting and measuring a single metric: labor productivity. While managers can easily tabulate how many hours a construction worker spends on a task, they don’t have an accurate measure of how much work is actually accomplished or whether that work is being done correctly

The result is a gross disparity between expectations and results. According to McKinsey & Company, ninety-eight percent of large-scale construction projects are delivered, on average, eighty percent over budget and twenty months behind schedule.

The Solution.

The companies can use autonomous devices to visually monitor every inch of a project day-by-day. It feeds that data to proprietary deep learning algorithms that inspect the quality of installed work and quantify progress in real time.

We use computer-vision and machine learning platform to process images captured via Smart Glasses to be able to further detect defects/cracks, classify and measure them on a concrete buildings and infrastructures.

High quality images of concrete surfaces are captured using Smart Glasses and subsequently analyzed by an automated computer vision and machine learning powered crack detection and classification platform. Precise measurements for area of damage in sq inches or sq feet given a single camera image capture system.

Aindra Product Analytics

The Impact.

Reduces cost

Reduces cost by approx 15-20%

less time

Approx 30-35% less time taken than the original process

Accuracy

Improved accuracy in crack measurement