Products / Discover the Sky: Unleashing the Potential of Sense Aeronautics / Revolutionizing Precision: The Power of Automatic Target Recognition

logo sense positivo.webp

Cutting-Edge AI-powered Drone Video Analytics Solutions for Object Detection

Discover the Sky: Unleashing the Potential of Sense Aeronautics / Revolutionizing Precision: The Power of Automatic Target Recognition

Revolutionizing Precision: The Power of Automatic Target Recognition

AI-powered real-time object detection and classification

Socials
Revolutionizing Precision: The Power of Automatic Target Recognition

Revolutionizing Target Recognition with AI

Sense Aeronautics has developed an innovative Automatic Target Recognition (ATR) system powered by artificial intelligence, which autonomously identifies and categorizes targets of interest within electro-optical (EO) and infrared (IR) video feeds. This advanced solution offers quicker,more economical,and more reliable results compared to customary human operators. It’s scalability allows it to manage multiple video streams simultaneously, making it especially suitable for applications involving drone fleets and swarms.

Streamlined Integration and Efficiency

The ATR system integrates effortlessly into existing mission workflows, ensuring precise identification of critical information while minimizing storage and bandwidth needs. It can relay data regarding potential threats and significant events to external platforms, including video management systems, ground control stations, and infrastructure monitoring tools.

Enhanced Data Retrieval and Geolocation

The latest iteration of the ATR solution facilitates the extraction of telemetry data from drones, considerably boosting AI capabilities. This enhancement allows for the geolocation of identified targets, enabling their visualization on mapping interfaces.

Flexible Deployment Options

The ATR technology is versatile, available for deployment on the edge, as well as in local, public, and private cloud environments.

Technical Specifications

input Sources USB and GbE cameras
IP Cameras
Video files (MPEG-4, H.264, etc.)
Video streams (RTP, RTSP, RTMP)
Video platforms (Milicast, Dolby.io, DJI)
Output Formats dolby, RTMP, RTSP, WebRTC, HLS
Training Data 150,000 images with over 2 million annotations
Latency <200ms for detection
<1s for remote video access in cloud deployment
Detection Probability >90%
detectable Target Size <10%
Detection Range (Person) DJI Zenmuse H20 – 3000m
DJI Zenmuse Z30 – 4500m
Flir BlackFly (6mm lens) – 250m
Mavic 3ET – Thermal Camera – 200m
Detection Range (Vehicle) DJI Zenmuse H20 – 5000m
DJI Zenmuse Z30 – 8000m
Flir BlackFly (6mm lens) – 400m
Mavic 3ET – Thermal Camera – 300m
Deployment Edge (onboard), Local (GCS), private cloud, or public cloud

Other Products

Mastering the Art of Detect-and-Avoid: Your Guide to Safety and Precision
Collision avoidance solution detecting both collaborative and non-collaborative aircraft