How Trash objects detection from a drone can halve the overall detection and collection cost

AI with Drones

Technology CV
Industry Government
Potential industries Real Estate, Logistics, and Transportation, Construction
Client Semi-government real estate organization

Summary

For a large semi-government organization, we developed a system to detect litter objects from images captured from a drone and manage trash collection activities. We designed and developed a GIS-based application allowing convenient interaction with detected litter objects as well as facilitating trash collection activities via optimal route planning and tracking of the collection progress. 

That resulted in significant cost savings halving the overall detection and collection costs. The collection time decreased by a factor of 4, while the automated computer vision solution achieved 7% higher detection accuracy than a human expert. Additionally, drone for inspection reduced carbon footprint by a factor of 19.

Challenge

Tons of litter were nailed by waves, scattering them across a territory of one thousand square km. Being located on many single islands, these objects were difficult and costly to identify by a human or a team of people. It was required to design and implement an efficient strategy to detect and collect those trash objects. Therefore, drone infrastructure inspection came as a suitable solution. 

Solution by AI Superior

We applied our proprietary computer vision technology along with drones for industrial inspection for object detection, classification, and segmentation, as well as designed and developed an interactive GIS-based application to consume results and operate collection activities. The computer vision detection technology was applied to images captured from a drone. Partnering team operated the drone that provided RGB images covering the whole territory. The flight altitude was around 50 meters high above the land.

drone_construction

This image shows the dashboard from the application for drone object detection (Detections and GIS application)

 

Outcome and Implications

The developed solution reduced the time required to perform trash detection activities by a factor of 25. That resulted in significant cost savings halving the overall detection and collection costs. The collection time decreased by a factor of 4, while the automated computer vision solution achieved 7% higher detection accuracy than a human expert. Additionally, such a system decreased carbon footprint by a factor of 19.