SimActive announces the use of its Correlator3D product in conjunction with machine learning to determine land use in New Zealand.
Raw images were pre-processed with a machine learning / artificial intelligence (ML/AI) algorithm developed by Lynker Analytics Ltd. for New Zealand’s lighting conditions, removing shading effects from clouds between image runs.
A coalition of data providers and land use experts was led by Lynker, with imagery processed over 7,400 sites by Gordon Morris, an independent geospatial specialist. The high-quality data were captured by UAV Mapping NZ Ltd. using a non-parametric camera mounted on a Cessna 172 airplane.
“By applying a targeted low frequency filter over the luminance of the image, we remove large scale light and dark variations such as those caused by cloud shadow,” said Matt Lythe, Managing Director of Lynker Analytics. “This gives an overall blended appearance, which further enhances mosaic color-balancing in Correlator3D and leads to seamless integration of new survey data into existing basemaps.”
About Lynker Analytics Ltd.
Lynker Analytics is a New Zealand company with expertise in data infrastructure, machine learning and geospatial analytics. It has developed sophisticated tools to extract new knowledge and insights about the earth’s surface and build environment from satellite imagery, aerial photography, drones, Lidar and other types of data. Using neural networks and related AI techniques, Lynker Analytics can monitor and quantify change in the environment at local, city or national scales to support better decision making.