Camera systems used for computer vision at the edge are smarter than ever, but when they perceive the world in 2D, they remain limited for many applications because they lack information about the third dimension: depth. Sensing technologies that capture and integrate depth allow us to build smarter and safer applications across a wide variety of applications including robotics, surveillance, AR/VR and gesture detection. In this presentation, we will examine three common technologies used for optical depth sensing: stereo camera systems, time-of-flight (ToF) sensors and structured light systems. We will review the core ideas behind each technology, compare and contrast them, and identify the tradeoffs to consider when selecting a depth sensing technology for your application, focusing on accuracy, sensing range, performance under difficult lighting conditions, optical hardware requirements and more.
When 2D Is Not Enough: An Overview of Optical Depth Sensing Technologies
Session Speakers
-
Dinesh Balasubramaniam
Senior Manager Product Marketing, Ambarella
With expertise in systems engineering, software development, video compression, and product design, Dinesh Balasubramaniam is responsible for leading applications engineering and customer support, overseeing the definition and development of reference designs and applications that showcase the capability and versatility of Ambarella SoCs. These designs integrate a variety of modern technologies, including machine learning models and depth sensing, and are ultimately deployed in surveillance, robotics, and IoT markets. Over the past five years, Dinesh has helped develop a number of hardware designs that integrate the most popular depth-sensing technologies available—stereo, structured light, and ToF sensors—to solve real-world problems for customers. Formerly with Dolby Laboratories, Maxim Integrated Products, and Mobilygen, Dinesh earned his MS EE in Signal Processing from the University of Texas at Dallas.
