The challenge
A city municipality wanted to fully automate construction site compliance monitoring and detect abandoned construction debris such as bricks, cement blocks, sand heaps, and metal and wooden sticks.
The solution had to minimise human involvement in inspections, reducing both labour costs and the time each inspection takes.
Our solution
We applied our proprietary computer vision technology for object detection, classification and segmentation to detect 25 classes of construction debris in drone imagery, and built a GIS dashboard where users select a construction site and see all the debris detected within it.
For every detection, the system reports the estimated size (area) of the debris, for single objects and for clusters of objects of the same type, together with the number of detected objects. APIs expose the detection results, so the solution can be integrated with practically any other system.
- Detection, classification and segmentation of 25 construction debris classes
- GIS dashboard to select a site and view all detected debris
- Area estimates for single objects and same-type clusters, plus object counts
- APIs to query detection results and integrate with other systems
The outcome
The solution was adopted by multiple city municipalities, demonstrating its operational and economic effectiveness.
According to the customer's estimates, the system saved 320 man-hours per month and reduced average inspection costs by 40%.
