The misperception of 3D perception: demystifying notions of cost to capabilities

Couldn’t attend Transform 2022? Discover all the summit sessions now in our on-demand library! Look here.


3D perception already plays a central role in shaping how we build our cities, how we make our cars, and how we interact with the physical world. Smart cities use knowledge of busy intersections to inform urban planning, manufacturers use 3D sensors to automate logistics, and sites track density limits to improve safety.

But for many people and organizations, this technology is widely misunderstood and therefore ignored, limiting the full potential of 3D perception. The misconception that it’s too expensive, with limited usability and “good enough” alternatives has caused companies to forego implementing 3D technology.

As more businesses invest in technology to improve efficiency and results, debunking these misperceptions is key to unlocking the market’s most powerful tool for insights and automation.

Myth: It’s automotive technology

Most people don’t realize how long 3D sensors have been around. The first light-based ranging experiments date back to the 1930s and began in the aerospace industry when companies used 3D sensing technology to study the atmosphere and measure cloud height. 3D radar sensors were also widely used during World War II and played an important role in the UK’s ability to survive the Battle of Britain in 1940. Decades later, during the Apollo 15 mission of 1971, 3D sensors were used to map the surface of the moon.

It took until the 2000s for 3D technology to be implemented in the automotive industry. Today, most 3D sensors are designed and developed for the automotive industry due to the involvement of original equipment manufacturers (OEMs) and the vast investments in technology by the automotive industry over the years. the “Great AV Hype” of 2016-2020.

Unfortunately, this meant that advances in 3D sensors became specialized for one market and the devices became less suitable for other applications. Now that the automated vehicle market is cooling and the industry realizes that the road to Level 5 autonomy is much longer and more difficult than expected, the 3D sensor industry is looking to other markets such than retail and security to fill the gap.

Myth: It’s too expensive

An expensive reputation precedes 3D perception technology, which is usually the first deterrent. In fact, the technology has become increasingly affordable. Yet most organizations do not explore the possibilities of 3D perception based on this preconceived notion. Prices for 3D sensors have plummeted over the past decade thanks to rapid adoption across industries – even smartphones are now equipped with this hardware.

Manufacturing 3D sensors used to be a very manual process where each laser and receiver had to be placed by hand by a skilled operator. Over the past two years, however, due to the involvement of a number of major automotive companies, including Lincoln Continental, Bosch and Valeo, the manufacturing process has become automated. Additionally, the technology has evolved to include mass-produced microoptoelectromechanical systems or hybrid solid-state devices with vertical cavity surface-emitting lasers (VCSELs), which do not require the manual labor of previous iterations.

On the perceptual side, the computing power required increases as the sensors are able to generate more data, but Moore’s Law ensures that the processors keep pace. Additionally, companies like AMD, Intel, and NVIDIA are working hard to produce smaller, more powerful, and cheaper computers with each iteration.

Myth: 2D cameras are enough

Often seen as the cheaper alternative, 2D cameras have been a go-to for most organizations to gain insights into safety and security, customer journey and productivity. While great for monitoring and retrospective viewing, they literally miss a whole dimension of information. 3D sensors add an extra dimension to transcend the viewpoints of 2D cameras. Having an accurate understanding of proximity is valuable for improving safety and efficiency in many areas of business operations.

On the other hand, traditional 2D sensors, such as cameras, are passive sensors that require little power and have been around for decades, which means there are many qualified system integrators available. They also include color information, something that most modern 3D active sensors do not provide.

3D sensors such as LiDAR and Radar are not intended to replace 2D sensors; they are intended to increase them. In many ways, traditional 2D sensors and 3D sensors complement each other perfectly. 3D sensors provide range information, an ability to work in light-deprived environments, and have been extensively developed over 2D alternatives to counter weather. Some 3D perception software on the market today uses deep learning and weather filtering AI to provide accurate information regardless of conditions such as snow and rain. The strength of 2D sensors comes from the aforementioned color information, and they often have much higher resolution, with 4K and 8K being available. Moreover, 2D computer vision tools are very advanced and popular among students all over the world.

Many 3D sensor manufacturers are now integrating 2D sensors into their units, which provides built-in 2D/3D calibration, and in turn allows each data point provided to contain both 3D location and color information. . The best of both worlds.

So what’s the next step?

Data is now the most important factor for organizations and governments looking to make major operational changes. From justifying expenses to optimizing efficiency, the more complete a data set is, the better those decisions will be. Arguably, information from 3D sensors will provide the most useful information to shape the world of tomorrow.

As we seek to build smarter cities, safer infrastructure and more efficient businesses, understanding 3D perception – and the role it plays in public and private environments – will become crucial. Beyond debunking misperceptions, it’s important to continually question what we know technology is capable of and find new ways to improve and implement the right technology to solve long time.

Jerone Floor is Vice President of Products and Solutions at Seoul Robotics

DataDecisionMakers

Welcome to the VentureBeat community!

DataDecisionMakers is where experts, including data technicians, can share data insights and innovations.

If you want to learn more about cutting-edge insights and up-to-date information, best practices, and the future of data and data technology, join us at DataDecisionMakers.

You might even consider writing your own article!

Learn more about DataDecisionMakers

Leave a Comment