Drone navigation and license place detection for vehicle location in indoor spaces
This addresses safety issues in vehicle transport by enabling real-time location tracking, but it is incremental as it applies existing methods like wall-following and CNNs to a new domain.
The paper tackled the problem of locating vehicles in indoor spaces by using a nano-drone to navigate and detect license plates, achieving the ability to read all plates across eight test cases through aggregation of measurements from multiple drone journeys.
Millions of vehicles are transported every year, tightly parked in vessels or boats. To reduce the risks of associated safety issues like fires, knowing the location of vehicles is essential, since different vehicles may need different mitigation measures, e.g. electric cars. This work is aimed at creating a solution based on a nano-drone that navigates across rows of parked vehicles and detects their license plates. We do so via a wall-following algorithm, and a CNN trained to detect license plates. All computations are done in real-time on the drone, which just sends position and detected images that allow the creation of a 2D map with the position of the plates. Our solution is capable of reading all plates across eight test cases (with several rows of plates, different drone speeds, or low light) by aggregation of measurements across several drone journeys.