Overview

Description

STRADVISION’s SVNet is a hardware-optimized software for ADAS that allows vehicles to detect and identify objects accurately, such as other vehicles, lanes, pedestrians, animals, free space, traffic signs, and lights, even in harsh weather conditions or poor lighting. To achieve surround vision, SVNet’s camera and deep learning-based capabilities work seamlessly with other sensors, such as LiDAR and RADAR, to process collected road data with high speed and accuracy. The software also enables ADAS features such as Adaptive Cruise Control, Lane Keeping Assist, Forward Collision Warning, Automatic Parking Assist to be more precise and reliable than other solutions on the market.

Features

  • Vision perception for Driving
    • Object detection
      • Pedestrians
      • Two wheeler (Bike, Cycle)
      • Car, Bus, Truck
      • Static objects / General objects
      • Road sign
      • Animal
    • Lane Detection / Road boundary
    • Free Space Detection
    • Traffic Sign / Traffic Light Recognition
    • Light Source Detection
    • Depthmap / Pseudo lidar from camera
    • Semantic Segmentation
  • Vision perception for Parking
    • Parking Space Detection (PSD)
      • Line based PSD
      • No line PSD
    • Visual SLAM

Applications

Target Devices

Synergy Download

Documentation

Title Type Date
PDF862 KB
Product Brief
STRADVISION’s SVNet demo on RENESAS Platform (R-Car V3H2)

SVnet satisfies EU GSR and Euro NCAP5 star aiming at ADAS L0-L2.