Computer Vision incorporates vision and machine-learning technology to allow a machine to gain an understanding of its surroundings through visual recognition. Using optical sensory as an input, a device equipped with machine-learning capabilities can extract and classify its surroundings so that it can better “react” to the environment that it is in. This is part of the Artificial Intelligence (AI) initiative, where machines are trained to interpret sensory inputs so that they can behave and perform human-like tasks.

With an increasing number of AI applications operated on the EDGE, the ability to create low-power deep learning models becomes crucial in a battery-operated device. Similarly, visual sensors are no exception to these power constraints. To fuel the next wave of always-on sensing needs on these so-called edge devices, optical sensors must also support the notion of always-on visual sensing.

The Global Shutter Image Sensor product line integrates PixArt’s proprietary motion detection algorithm and low-power architecture, which allow the sensors to deliver outstanding image quality with the lowest power consumption in the market. Such characteristics can effectively realize “always-on” applications, which is especially beneficial to a diversified number of battery-powered systems or devices, including AI applications. Its built-in Auto-Exposure Control and Auto-Gain Control functions can ease the work in the subsequent end-product design and development lifecycles. These sensor products can fit perfectly with a wide range of applications related to consumer electronics, machine vision, and industrial fields, including augmented reality (AR), virtual reality (VR), artificial intelligence classification and recognition, obstacle avoidance, barcode scanning, and factory automation.

Related News: Syntiant Unveils NDP200 Neural Decision Processor for Always-On Vision Edge AI Applications