High resolution satellite imagery will be used over the pre-selected area, with a UAV conducting sample area surveys, using a high-resolution, multispectral camera and Lidar.
About
Combining the potential of UAV’s (Unmanned Aerial Vehicles) with high resolution satellite imagery provides a highly accurate, low-cost solution to this challenge. High-resolution imagery collected by satellite will be cross checked with key sample areas, where the data will be gathered by UAV photogrammetry and Lidar. An A.I toolset along with algorithms have been developed to cross check the UAV sample data with the satellite imagery, to provide an accurate data base containing tree height and canopy cover. With the technology mentioned, the tree height and canopy cover for each tree with a location, time and date stamp can be autonomously calculated at low cost. The proprietary software will then record and produce a report for the client on the current survey and can be presented as a comparison to previous surveyed data. The Artificial Intelligence capability will not only reduce the time of producing the report but will also reduce the human errors on the accuracy of the measurement and counting. Our application programming interface (API) will allow the integration of the client’s management software already being used if they do not wish to change it. The data can be uploaded to a specific client forest management system if required. In a situation where there is no client management system, we can provide a complete turnkey solution for the end user.
Key Benefits
- Scalable solution to cover large areas quickly - Integrate high resolution, accurate data onto a GIS database - Fast and accurate field data - Environmentally friendly system - Highly accurate results - Low-cost solution The potential doesn’t stop with just tree height and canopy cover. Drones are very powerful pieces of technology, so if needed, can be used to monitor far more challenging data.
Applications
Applicable to organisations who are interested in collecting data from large sample regions.