Prism™ AI - Auto

Software Features

Authentication

Camera to ECU key handshake with 256-bit challenge/response

Camera Interface

USB, GMSL1, GMSL2, and FPD-Link III

Cross Modality Image Registration

Automatic alignment of thermal and EO to compensate for parallax and time sync differences

Deblurring

Blind and semi blind (motion known) methods supported to restore MTF (thermal video)

Dewarping

Radial and tangential lens dewarping

Haze Penetration

Locally adaptive compesnation for atmosperic dispertion (thermal)

Imaging Blending

Multi-spectrum blended image for display that automatically adjusts blending factor for day and night

Motion Compensated Temporal Noise Reduction

Advanced, mutiframe noise reduction (thermal video)

Multi-Object Tracker

Lightweight, signal-processing based tracker reduces false positives and maintains target lock between frames in the absence of detections. Image-plane and ground-plane configurations available.

Object Detector (CNN)

7 visible and thermal object detection categories: Person, car, large vehicle (bus, semi-truck, train, etc.), bicycle, motorcycle, traffic light, and large animal (deer, cow, horse)

Rectification

Visible & thermal camera calibration process with pixel-accurate registration of visible & thermal

Sensor Fusion

Lightweight late-fusion implementation for object perception from thermal and color information from visible (brake lights, traffic lights, street signs)

Supported Hardware

Qualcomm: Snapdragon 8 gen 1 (RB5/QRB5165) & Snapdragon 8 gen 2 (QCS8550); NVIDIA: Jetson Xavier & Jetson Orin; Other Qualcomm and NVIDA HW on request

Thermal Image Processing

Automatic Gain Control (AGC), super-resolution, denoising, and sharpening

Tone Mapping

Global and locally adaptive methods supported, optimized for highly dynamic scenes

Video Stabilization

Removal of high temporal frequency jitter (thermal and EO)