As industrial environments become increasingly dynamic and complex, the need for robust, real-time depth perception systems continues to grow. Among the most widely adopted 3D vision technologies are stereo vision, time-of-flight, structured light, and LiDAR, each offering distinct advantages and trade-offs.  This presentation will provide a comparison of these technologies with a focus on stereo vision. We will examine the key design considerations for stereo vision and highlight recent advancements driven by deep learning techniques. Through real-world use cases, we will discuss how stereo vision can be effectively deployed to enhance autonomy, safety, and operational efficiency.  We will also address common challenges encountered in industrial deployments and present practical strategies to mitigate them. Whether you're designing perception systems for navigation or manipulation, this presentation will provide actionable insights to leverage stereo vision in industrial robotic applications.

Speaker

Stephen Se Sr. Engineering Manager Teledyne FLIR (Canada)

Stephen Se is Senior Engineering Manager at Teledyne FLIR, where he leads research and product development in depth sensing, computer vision, and machine learning. With more than 20 years of experience spanning academia, space, defense, and industry, he has directed multidisciplinary teams and delivered advanced vision systems for mining, defense, manufacturing, and robotic applications.

Stephen earned his PhD in Information Engineering from the University of Oxford and completed postdoctoral research at the University of British Columbia, where he developed one of the earliest visual SLAM systems for mobile robots. He has authored more than 40 publications, holds multiple patents in 3D modeling and vision systems, and has been recognized with numerous technical and leadership awards.

 

---

Event Details

FORMAT: Oral presentation followed by audience Q&A.
MENU: Coffee, decaf, tea, and water will be available nearby.
SETUP: Theater seating.