At Commercial UAV Expo Europe, Aerialtronics released a fully integrated computer vision platform with deep learning capabilities. PENSAR is a stand-alone twin sensor platform that utilizes the GPU-accelerated computing power to enable real-time video processing and immediate augmented insights.

The product is the first to integrate the new and powerful FLIR Boson thermal IR camera into a drone application, and additionally contains a 30x zoom Sony daylight camera. It’s designed to change the way operators perform aerial tasks in search and rescue, inspections, documenting assets, surveying, mapping and public privacy.

One of the most revolutionary features of the PENSAR is how it leverages deep learning networks in real-time to detect, recognize, track, classify and annotate certain objects or deviations of interest and conversely, to blur out and mask objects for privacy reasons. Users have access to deep learning methods and machine vision developers can automate dynamic decision-making systems quickly and easily. What’s really exciting though is that the way in which someone actually uses this product is totally up to them.

dsc02107The benefits of a single platform that has a thermal camera along with a daylight camera into a drone will create opportunities for emergency and inspection professionals, but the deep learning methods and machine vision will allow for countless possibilities. One of the most exciting questions professionals who are using drones can ask is, “wouldn’t it be great if…”, and with the ability to develop custom apps, this product is a perfect example of that potential. It allows users to not only ask this question regarding how they want to be using drones, but to answer it as well.

Full specs of the PENSAR are below…

• FLIR Boson thermal IR view / Radiometric measurements 1/1 (3:2)

• Day Vision with 30x zoom (HD 1920*1080) 1/1 (16:9)

• Side by side view (vision / IR) (HD 1920*1080) 1/2 (16:9)

• Sensor fusion (IR overlay on vision image stream)

• Dual-stream parallel onboard recording

• Image capturing

• AI-powered object detection, tracking & classification

• Real-time masking

• Optical character recognition (OCR)

• GPU-accelerated computing

• Ability to run unlimited computer vision powered algorithms