Machine vision accelerating image sensing

Motivation for emerging image sensor technologies

While conventional CMOS detectors for visible light are well established and somewhat commoditised, at least for low-value applications, there is an extensive opportunity for more complex image sensing hardware that offer capabilities beyond simply acquiring red, green, and blue (RGB) intensity values at each pixel.

This largely stems from the ever-increasing adoption of machine vision, in which image analysis is performed by computational algorithms. Machine learning requires as much input data as possible to establish correlations that can facilitate object identification and classification, so acquiring optical information over different wavelength ranges, or with spectral resolution, for example, is highly advantageous.

Of course, emerging image sensor technologies offer many other benefits. This can include similar capabilities at a lower cost, increased dynamic range, improve temporal resolution, spatially variable sensitivity, global shutters at high resolution, reducing the unwanted influence of scattering, flexibility/conformality, and more.

The brand new IDTechEx report, ‘Emerging Image Sensor Technologies 2021-2031: Applications and Markets’, covers many emerging technologies, specifically:

• Quantum dots on silicon hybrid image sensors
• Organic photodetectors on silicon hybrid image sensors
• Emerging SWIR image sensor technologies, including extended range silicon.
• Organic and perovskite photodiodes (OPDs and PPDs)
• Event-based vision
• Hyperspectral imaging
• Flexible x-ray image sensors
• Wavefront imaging

Emerging image sensor technologies within the report include:

Hybrid image sensors - Adding an additional light-absorbing layer on top of a CMOS read-out circuit is a hybrid approach that utilises either organic semiconductors or quantum dots to increase the spectral sensitivity into the SWIR region. Currently dominated by expensive InGaAs sensors, this new technology promises a substantial price reduction and hence the adoption of SWIR imaging for new applications such as autonomous vehicles.

Extended-range silicon - Given the very high price of InGaAs sensors, there is considerable motivation to develop much lower-cost alternatives that can detect light towards the lower end of the SWIR spectral region. Such SWIR sensors could then be employed in vehicles to provide better vision through fog and dust due to reduced scattering.

Thin film photodetectors - Detection of light over a large area, rather than at a single small detector, is highly desirable for acquiring biometric data and, if flexible, for imaging through the skin. Emerging approaches that utilise solution processable semiconductors offer a compelling way to produce large-area conformal photodetectors for applications such as under-display fingerprint detection.

Event-based vision - Autonomous vehicles, drones, and high-speed industrial applications require image sensing with a high temporal resolution. However, with conventional frame-based imaging, a high temporal resolution produces vast amounts of data that requires computationally intensive processing. Event-based vision is a new way of obtaining optical information that combines greater temporal resolution of rapidly changing image regions with much reduced data transfer and subsequent processing requirements.

Overview

In summary, the increasing adoption of machine vision provides a great opportunity for emerging image sensing technologies that offer capabilities beyond conventional CMOS sensors. This report offers a comprehensive overview of the market for emerging image sensor technologies, covering a multitude of applications that range from autonomous vehicles to industrial quality control.

‘Emerging Image Sensor Technologies 2021-2031: Applications and Markets’, outlines the current status and future application for a wide range of emerging image sensors. Also included are highly granular ten-year market forecasts by revenue and volume (split by technology and application), along with multiple application case studies and technological/commercial readiness assessments. The report also includes many company profiles based on interviews with early-stage and established companies.