Here at team West Coast UAV we've been hard at work integrating all the different requirements for the 2016 Medical Express Challenge to be held in Queensland, Australia later this year. One of the key requirements is to accurate locate poor old Joe.
We know Joe is within 100m of his reported location, and he will be wearing his trusty blue jeans. Our approach is to take an image of the entire area from an altitude of 250 metres. Once Joe is identified we can then using the aircraft’s known position and attitude we can determine his exact location.
Our imaging system is responsible for finding Joe’s location to within 10 metre accuracy. This must be done quickly and with potentially limited bandwidth (as low as 3Kbit a second) which has led us to refining and developing a number of novel solutions.
Just as important. is a streamlined workflow to minimise the time from initial image capture to landing waypoint upload. For this we have developed an integrated web browser solution that interfaces with the many components involved in imaging and locating Joe.
Comments
No web app for our set up. We are running a combination of bash and python scripts that control the aircraft during imaging. GCS is vanilla Mission Planner.
Very impressive, I've been using the RPi on-board for some time now, very handy, but I haven't nearly utilised it to this extent! I'm planning to use it for real time image stabilising for a simple gimbal I'm building. All the white papers are giving me a headache..
Do you have the web app running on-board?
Hi Hein, yes we are running a Raspberry Pi on the aircraft which is receiving the telemetry data and combining this with the image captured from it's camera to give us geo-referencing. It also is doing a lot of image post-processing, hosting and also handling the thumbnail generation based on GCS requests.