“Simplify the task. Continually look for faster, better, easier ways to get the job done.” — Brian Tracy, motivational public speaker, and self-development author.
Discussions on artificial intelligence appear to have taken over the world in recent months. One of the main reasons AI has recently attracted so much attention is that according to some measures, businesses like OpenAI (creators of ChatGPT) and others are close to solving, or at the very least significantly mitigating, what is known in computational, biological, and mechanical sciences as the speed-accuracy tradeoff, or SAT.
Modern AI can now approach genuine communication with speed and accuracy that resembles human-like conversations with a computer’s speed of data retrieval, however, it is still far from ideal. In 3D laser scanning and its related subfields, such as panoramic 360° photography and photogrammetry, this similar balancing act between speed and precision is evident.
High-accuracy scans in conventional 3D reality capture can take minutes to complete, and much longer to analyze the data and register the point-cloud data. precision while losing speed. Which might potentially result in a loss of business for any organization trying to execute high-volume scans. However, a panoramic camera can quickly record an image, but the corresponding data is much less accurate than a 3D point cloud. accuracy at the sacrifice of speed.
But what is the next digital domino to fall if AI research indicates that the speed-accuracy tradeoff is about to end? The 3D laser scanning sector, which comprises 3D visualizations for applications in architecture, engineering, construction, operations, and maintenance, as well as public safety pre-incident planning, is ready to win this battle as well.
A World Waiting to be Scanned
As-built documentation professionals today are always looking for quicker, better, and simpler solutions to complete their work. Without compromising quality for speed or speed for quality, they want to simplify activities and streamline workflows.
Why are they seeking the “holy grail” of precision and speed? Because there is a lot of work to be done in the professional measurement services sector as a whole. And if BIM models are inaccurate or if image capture and processing rates are too slow, a lot of time, money, and human and technology resources are on the line. Globally, the industry is mapping and measuring industrial facilities like power plants, scanning the interior and exterior of large structures, helping law enforcement with pre-incident planning, assisting specialty and general contractors with engineering projects, and providing facility managers/owners with real-time facility management insights they need to monitor building operations and prevent disasters.
As may be expected, the two different approaches that were finally used to address the speed-accuracy tradeoff were mobile scanning products and static scanning tripod-mounted 3D laser scanners.
However, the invention only really served to create two realms of competing influence rather than actually putting a stop to the SAT “battle”. Studies have confirmed that while mobile scanning is quick, it is not as precise as a static scan. One such study was carried out by the University of Cambridge and presented at the 2021 European Conference on Computing in Construction on the Greek island of Rhodes.
A section of the paper’s conclusion reads:
“Our experiment demonstrated that mobile scanners outperform static mapping devices in this regard, as the density of the scanned targets measured in points per second drops exponentially along with the increasing distance to the target. When it comes to precision, the trend is the exact reverse. Compared to mobile equipment, the static scanner generates scans that are at least 20 times less noisy. While all devices almost entirely meet the accuracy requirements for use cases like measured building surveys, topographic surveys, and low accuracy setting out up to 40 meters, the more demanding use cases like engineering surveying could only be satisfied by the static scanner.
Hybrid Computing 2.0
If the 1960s at NASA were the era of “hybrid” technology (human “computers,” were hired to crunch critical launch and re-entry data in part because the space agency’s mainframe, the IBM 7090, while faster than humans, wasn’t as accurate as their genius), then the term “hybrid” for 3D reality capture is about to mean a union of two types of digital formats, uniting the best qualities of mobile scanning with the best qualities of static reality capture.
This merger will take the form of new technology and a word that is still subject to patent. This hybrid method augments a lower resolution 3D laser scan with data from a 360° camera by algorithmically combining the data from a panoramic image with a static 3D point cloud. As a result, accuracy and speed are no longer mutually exclusive for the first time.
The next phase in 3D scanning solutions is the hybridization of mobile scanning and static scanning with little sacrifice in accuracy and speed. Think about the effects of a system that can complete a laser scanning workflow up to 50% faster. Additionally, one that offers the most value for the money in terms of on-site productivity, dependable accuracy, and cutting-edge visual clarity.
The benefits of such a merging should be clear:
- A scan that is reduced in accuracy is designed to be significantly faster than traditional scans.
- 360° images that augment less dense data sets to ensure project completion with accelerated workflows
- The saving of entire days per week enabled the taking of additional scans that would likely not have been taken without the added speed and time savings, ensuring more complete and comprehensive projects.
- Colorized images allow users to see object edges and corners more clearly and identify defined geometries with greater ease, leading to better analysis and execution in other software.
The first laser scanning devices were created in the 1960s and used lights, cameras, and projectors to scan objects, but they were labor-intensive and prone to error. While technological advancements that brought the 3D laser scanning industry to where it is today are evolutionary in nature, a fusion of static scan data and mobile 360° images with no loss of speed or accuracy is revolutionary.
The large-scale scanning-dependent industries, such as architecture, engineering, construction, operations and maintenance, and public safety, now have a fast, accurate, and reliable way to take thousands of scans and use that data to drive business results or achieve situational results, such as the quick scanning of entrance and egress points to a building. Given that there are over 100 billion buildings in the globe, and that a sizable portion of those buildings is large-scale structures, there has never been a better time to speed up the transition of the physical world into the digital one.
It’s as if a NASA human computer had access to Frontier, the fastest computer in the world right now, knowing with certainty that every single one of its one quintillion floating point operations per second was accurate.
New Frontiers
What has been true since the first cities appeared in the Fertile Crescent of the Eastern Mediterranean thousands of years ago is still true today, whether it is the physical frontier, the biological frontier, the mechanical frontier, the computational/digital frontier, or any other frontier whose limits are pushed by today’s fastest computers and ever smarter algorithms. Large, complex constructions will continue to be created as long as there are people on this planet, necessitating quick, precise assembly and careful project management. And there will always be a need for public safety to prevent worst-case scenarios from happening.
These two realities guarantee that 3D laser scanning will keep developing. The equipment’s size, weight, and mass will continue to reduce while speed and accuracy also rise. While app-based LiDAR scanning is outside the purview of this study, the future eventually lies in breakthroughs in generalist technology that is no bigger than a smartphone or tablet.
The world’s first universal quantum computer with more than 1,000 qubits is scheduled for release by IBM later this year. When combined with the promise that quantum computing offers, the new frontier is anticipated to push well beyond the speed-accuracy tradeoff in the decades to come.
However, the technological advance that the 3D laser scanning sector is only now starting to profit from is hybrid reality capture. The speed-accuracy tradeoff is increasingly a problem in need of a solution that is going to be solved. It has long been a major source of suffering for many disciplines over time. One of the most famous quotes from renowned British science fiction author Arthur C. Clarke is that “Any sufficiently advanced technology is indistinguishable from magic.”
While accurate, Clarke’s statement says nothing about how thrilling magic maybe if you’re one of the visionaries who help make it happen.
Credits: FARO
Click on the following link Metrologically Speaking to read more such blogs about the Metrology Industry.
