Environment

Environment

Crop verses Weed Recognition

NeuroMem can easily classify objects using one or multiple features such as color, edges and texture. In this study the neurons are put at work to discriminate between tomato leaves and weeds in order to optimize the spraying of nutrient or pesticide from a tractor moving across a field.

Onboard Feature Indexing from Satellite Lidar Images

The purpose of the onboard feature indexing system is to
perform pattern recognition and data compression onboard.
We use the unsupervised machine learning algorithm kmeans
to classify the lidar profile data and generate an
index dictionary.