Cameras and Sensors for Embedded Vision


While analog cameras are still used in many vision systems, this section focuses on digital image sensors—usually either a CCD or CMOS sensor array that operates with visible light. However, this definition shouldn’t constrain the technology analysis, since many vision systems can also sense other types of energy (IR, sonar, etc.).

The camera housing has become the entire chassis for a vision system, leading to the emergence of “smart cameras” with all of the electronics integrated. By most definitions, a smart camera supports computer vision, since the camera is capable of extracting application-specific information. However, as both wired and wireless networks get faster and cheaper, there still may be reasons to transmit pixel data to a central location for storage or extra processing.

A classic example is cloud computing using the camera on a smartphone. The smartphone could be considered a “smart camera” as well, but sending data to a cloud-based computer may reduce the processing performance required on the mobile device, lowering cost, power, weight, etc. For a dedicated smart camera, some vendors have created chips that integrate all of the required features.


Until recent times, many people would imagine a camera for computer vision as the outdoor security camera shown in this picture. There are countless vendors supplying these products, and many more supplying indoor cameras for industrial applications. Don’t forget about simple USB cameras for PCs. And don’t overlook the billion or so cameras embedded in the mobile phones of the world. These cameras’ speed and quality have risen dramatically—supporting 10+ mega-pixel sensors with sophisticated image processing hardware.

Consider, too, another important factor for cameras—the rapid adoption of 3D imaging using stereo optics, time-of-flight and structured light technologies. Trendsetting cell phones now even offer this technology, as do latest-generation game consoles. Look again at the picture of the outdoor camera and consider how much change is about to happen to computer vision markets as new camera technologies becomes pervasive.


Charge-coupled device (CCD) sensors have some advantages over CMOS image sensors, mainly because the electronic shutter of CCDs traditionally offers better image quality with higher dynamic range and resolution. However, CMOS sensors now account for more 90% of the market, heavily influenced by camera phones and driven by the technology’s lower cost, better integration and speed.

“High-Bandwidth Multicamera Systems with PCIe Backbone: Snapshot and Outlook on Technologies and Applications,” a Presentation from XIMEA

Kevin Toerne, Sales Engineer at XIMEA, presents the “High-Bandwidth Multicamera Systems with PCIe Backbone: Snapshot and Outlook on Technologies and Applications” tutorial at the September 2020 Embedded Vision Summit. In this presentation, Toerne explores high-bandwidth cameras and their application to multi-camera and embedded systems. He presents solutions for machine vision… “High-Bandwidth Multicamera Systems with PCIe

Read More »

“Embedded Vision for Autonomous Drones,” an Alliance Conversation with Skydio

Jeff Bier, Founder of the Edge AI and Vision Alliance, interviews Hayk Martiros, Head of Autonomy at Skydio, about the critical technical challenges for implementing embedded vision in autonomous drones that operate under difficult, real-world conditions. Skydio is hiring! The company is the leading U.S. drone manufacturer and world leader in autonomous flight. Skydio leverages

Read More »

“How to Create Your Own AI-Enabled Camera Solution in Days,” a Presentation from IDS Imaging Development Systems

Carsten Traupe, Director of Product Management at IDS Imaging Development Systems, presents the “How to Create Your Own AI-Enabled Camera Solution in Days” tutorial at the September 2020 Embedded Vision Summit. Cameras coupled with AI can solve numerous real-world problems. But developing an AI camera solution can be a complex… “How to Create Your Own

Read More »

“Designing Cameras to Detect the “Invisible”: Handling Edge Cases Without Supervision,” a Presentation from Algolux

Felix Heide, Co-Founder and Chief Technology Officer at Algolux, presents the “Designing Cameras to Detect the “Invisible”: Handling Edge Cases Without Supervision” tutorial at the September 2020 Embedded Vision Summit. Vision systems play an essential role in safety-critical applications, such as advanced driver assistance systems, autonomous vehicles, video security, and… “Designing Cameras to Detect the

Read More »

Ultrasound: a New Era of Prosperity for CMUT and PMUT

OUTLINE: Market figures and trends: The ultrasound sensing module market is expected to reach US$6.2 billion in 2025 with a 5.1% CAGR between 2019 and 2025. Ultrasound sensing market could be divided in different applications in which technologies and frequencies, as well as main drivers could highlight the technology of choice. ADAS applications are the

Read More »

Automotive Interior: Please Take a Seat In a High-tech Living Room…

OUTLINE: C.A.S.E paradigm: connectivity, autonomy and sharing megatrends are changing car interiors. And behind, sensing, lighting and displays are playing a key role. Market figures and trends: As a key segment for electronics and semiconductor industry, the automotive interior market will reach more than US$22 billion by 2025. The in-cabin sensing market is showing one

Read More »

Thermal Imager Industry: The Chinese Triumph

OUTLINE: Market figures & trends: 2020 has been exceptional for thermal imaging and sensing technologies. The thermal imaging market will reach around US $7.5 billion market value by 2025, at an 8% CAGR from 2019 to 2025. The thermal detector market will jump in 2020 by 23% in value to reach US$362 million. Smart building

Read More »

New High-end Sensors with MIPI Interface

November 18, 2020 – Vision Components presents various new camera modules that combine high image quality and frame rates with the advantages of the MIPI CSI-2 interface and consist of the sensor board and a fully integrated MIPI adapter board. Thereby high-end image sensors from the Sony Pregius and Sony Starvis series, which have no

Read More »

Octonion Releases Expansion Package Dedicated to AI-Based Industrial Condition Monitoring on STMicroelectronics STM32 MCUs

The solution enables industrial-equipment vendors to quickly evaluate Octonion’s embedded AI models, running on-device learning directly on STM32 MCUs Lausanne and Geneva, Switzerland – November 18, 2020 — Octonion SA, a deep tech software company specializing in Artificial Intelligence (AI) at the Edge for industrial-equipment diagnosis, announced an STM32Cube expansion package optimized for STM32L4+ microcontroller-based

Read More »

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.



1646 North California Blvd.,
Suite 360
Walnut Creek, CA 94596 USA

Phone: +1 (925) 954-1411
Scroll to Top