How to Build a Custom Stereo Vision System for Depth Perception

FlirStereoCam400x275

August 11, 2022

By Teledyne FLIR

Depth perception can be achieved by a variety of 3D sensors ranging from stereo vision with cameras to lidar and ToF sensors, each with its own strengths and weaknesses. While several off-the-shelf options exist, a custom embedded solution can cater to specific application requirements better. Our embedded depth perception solution provides a high-resolution colour point cloud using custom stereo setup with cameras. Depending on factors such as accuracy, baseline, field-of-view, and resolution, such a solution can be built using relatively inexpensive components and open-source software.

In this guide (download here), machine vision engineers at Teledyne FLIR share an overview of stereo vision while taking you through all the necessary steps to design your own depth perception solution. The article also covers pros and cons of 2 design options depending on space and computational requirements: with detailed steps for building, calibration and real-time depth mapping using one of the options. The setup does this without a host computer and uses off-the-shelf hardware and open-source software options. 

The guide also covers:

  • A simplified overview of a stereo vision system
  • How machine vision cameras can be used to build a depth perception solution
  • Two design options depending on your space and computational requirements
  • Step-by-step guide with sample code for building one of the options
  • Off-the-shelf hardware and open-source software required to build the system
  • Steps for calibration and real time depth mapping
  • Unique features, ease of use and integration enabled by Spinnaker SDK

To read more, visit the Teledyne FLIR website here.


Robotics World News

  • Phantom AI Raises $36.5M to Advance Autonomous Driving Platform

    Phantom AI Raises $36.5M to Advance Autonomous Driving Platform

    Phantom AI, a Silicon Valley-based startup developing an autonomous driving platform with computer vision, sensor fusion and control capabilities, has announced it raised $36.5 million in a Series C funding round. The company aims to help customers reduce accidents and make everyday driving more enjoyable, while also unlocking what is next in the advanced driving… Read More…

  • Raise Robotics Raises $2.2M in Seed Round Funding

    Raise Robotics Raises $2.2M in Seed Round Funding

    Raise Robotics, which develops robotic equipment for construction sites, has announced it raised $2.2 million in a pre-seed funding round (reported by Construction Dive). The company is currently providing fenestration and mass timber contractors with semi-autonomous equipment that completes bracket layout, installment and verification four times faster than standard methods. “Our mission at Raise is… Read More…


Products for Robots & Cobots

  • Xfuse Launches Phoenix ISP for AMD’s SOMs and Vision AI Starter Kit

    Xfuse Launches Phoenix ISP for AMD’s SOMs and Vision AI Starter Kit

    Xfuse LLC, which develops customizable imaging and video technology, has announced immediate availability of its Phoenix HDR ISP for the AMD Kria K26 System-on-Module (SOM) and the KV260 Vision AI Starter Kit. Designed for AI developers and computer vision engineers that need to capture real-time, data-rich imaging streams, the Phoenix HDR ISP delivers fully-tone mapped… Read More…

  • Sponsored Video: Oriental Motor BLV Series R

    Sponsored Video: Oriental Motor BLV Series R

    Brushless motors are commonly used in AGV/AMR designs for battery-powered, compact, and lightweight equipment movement. To assist with this development, Oriental Motors has created the BLV Series R Type of modular automation compatible products. The new motors provide DC power supply options of 60 W, 100 W, 200 W and 400 W. Features of the… Read More…