Improving Convolutional Neural Networks at the Edge (Download)
The concept of a perception neural network was first described as early as the 1950s. However, it wasn’t until recently that the necessary training data, neural-network frameworks, and the requisite processing power came together to help launch an artificial-intelligence (AI) revolution. Despite the tremendous growth of AI technology, the AI revolution continuously requires new tools and methods to take full advantage of its promise, especially when dealing with imaging data beyond visible wavelengths of the electromagnetic spectrum.
One such data type is thermal imaging, or the ability to capture long-wave infrared (LWIR) data. Thermal is a sub-type of a much larger world of imaging that emerged in the latter half of the 20th century, including LiDAR and radar.