Owl Perception Software Suite

Designed for Thermal Imaging

Object identification from real-time 3D volumetric point cloud

Convolutional Neural Network

Introduction

Convolutional neural networks are computer simulations of pliable groups of neurons that operate by producing a positive response when they detect a strong correlation between objects in a new image and objects in a series of images that they have learned in training.

CNN training is similar to the method used to prepare humans for recognition tasks. In training radiologists to read x-rays, for instance, the saying is, “show interns 50,000 images and tell them what they mean and then they will be able to reliably decide what any new images show”.

The trick is to pick the right set of images for training to minimize both missed pathology and over interpretation.

Convolutional Neural Network
Software Suite

Owl AI Thermal Perception Suite

Owl Perception Stack

Classification & Segmentation

Provides object bounding in 2D
Combine with ranging CNN for 3D volumetric response
Crisp segmentation for data efficiency

Monocular Depth for Ranging

3D point cloud

Thermal & RGB Fusion

Ideal for visualization and refined computer vision with perfect frame synch

Combine all Owl CNNs

Object identification from real-time 3D volumetric point cloud