Germany-based processor IP provider videantis, launched in 2004, was one of the first of what has since become a plethora of vision processor suppliers. The company's latest fifth-generation v-MP6000UDX product line, anchored by an enhanced v-MP (media processor) core, is tailored for the deep learning algorithms that are rapidly becoming the dominant approach to implementing visual perception (Figure 1).

By adding a second front-end instruction decoder to the ARC HS3x high-end 32-bit RISC architecture, along with doubling the number of ALUs, Synopsys has created its latest ARC HS4x processor IP core family (Figure 1).

The effectiveness of a computer vision system is highly dependent not only on the algorithms but also on the quality of the images fed into the algorithms. "Garbage in, garbage out," as the saying goes. More than 20 years of consumer digital camera-fueled image sensor innovations have also delivered cost, resolution, sensitivity, dynamic range, power consumption, and other benefits to visible-light-based computer vision applications.

As a kid, I was fascinated with electronics – especially digital electronics. The idea that one could build a computing machine out of simple logic gates was a revelation, and designing such things was thrilling. But as powerful and flexible as digital computers are, we live in an analog world. Hence, analog-to-digital converters play a critical role.

The buzz around artificial intelligence, computer vision and machine learning intensifies on a daily basis: There are a dizzying number of new processors, algorithms and tools for computer vision and machine learning. Investment and acquisition activity around AI companies is furious. Announcements of new AI-based applications and products are non-stop. Competition for engineering talent is fierce.

With the proliferation of deep learning, NVIDIA has realized its longstanding aspirations to make general-purpose graphics processing units (GPGPUs) a mainstream technology. The company's GPUs are commonly used to accelerate neural network training, and are also being adopted for neural network inference acceleration in self-driving cars, robots and other high-end autonomous platforms.

Hot on the heels of announced production availability for the Neural Compute Stick based on the Myriad 2 vision processor comes a next-generation SoC from Movidius (an Intel company), the Myriad X.

About seven years ago, my colleagues and I realized that it would soon become practical to incorporate computer vision into cost- and power-constrained embedded systems. We recognized that this would be a world-changing development, due to the vast range of valuable capabilities that vision enables. It’s been gratifying to see this potential come to fruition, with a growing number of innovative vision-enabled products finding market success.

Algorithms are the essence of embedded applications; they are the mathematical processes that transform data in useful ways. They’re also often computationally demanding. When designing a new product, companies often need to assess whether an algorithm will fit within their cost and power consumption targets. Sometimes, an algorithm won’t fit in its initial form.