The 5 biggest computer vision trends in 2022 – Recycling Today
From retail to health and safety, computer vision will play a larger role in business efficiency.
Computer vision is one of the most exciting applications of artificial intelligence. Algorithms that can understand images—both still pictures and moving video—are a key technological foundation behind various innovations from autonomous, self-driving vehicles to smart industrial machinery and the filters on mobile phones that make the pictures uploaded to Instagram look pretty.
Along with language processing abilities, called natural language processing (NLP), it’s fundamental to AMCS’ efforts to build machines that are capable of understanding and learning about the world. It generally involves applications powered by deep learning and neural networks trained on thousands, millions or billions of images until they become experts at classifying what they can see.
The value of the market in computer vision technology is predicted to hit $48 billion by the end of 2022 and is likely to be a source of ongoing innovation and breakthroughs throughout the year. So, let’s take a look at some of the key trends involving this fascinating technology.
Data-centric computer vision
Data-centric artificial intelligence (AI) is based on the idea that equal focus should be given to the quality of data used to train algorithms as is given to developing the models and algorithms themselves. Championed by Andrew Ng, a renowned pioneer of deep learning, this newly emerging paradigm is relevant across AI disciplines, particularly in the field of computer vision.
Some of the first deep learning-based image recognition models were developed by Ng at Google for the purpose of training computers to recognize pictures of cats, and the models are particularly dependent on the quality of the data they are fed, rather than just the quantity.
This focus on iteratively improving the quality of labeling and using automated techniques of extracting and labeling data will enable developers to apply computer vision technology to problems where far less data is available, potentially lowering costs and opening new potential use cases.
Health and safety
A key use case for computer vision is spotting dangers and raising alarms when something goes wrong. Methods have been developed for allowing computers to detect unsafe behavior on construction sites, such as workers without hard hats or safety harnesses, and monitor environments where heavy machinery, such as forklift trucks, are working in proximity to humans, enabling vehicles to be automatically shut down if someone steps into their path. About 2.7 million injuries are caused due to workplace accidents every year, according to the US Bureau of Labor Statistics. This is an area where businesses are increasingly investing to reduce the human and financial costs caused by oversight or inattentiveness.
Of course, preventing the spread of illness caused by viruses also is an important cause these days, and computer vision technologies are increasingly being deployed to monitor compliance with social distancing requirements and mask mandates.
Computer vision algorithms also have been developed during the COVID-19 pandemic to assist with diagnosing infection by looking at chest X-ray images for evidence of infection and damage to the lungs.
Retail
Shopping and retail are other aspects of life where we are sure to notice the increasing prevalence of computer vision technology during 2022. Amazon has pioneered the concept of cashier-less stores with its Go grocery stores, which are equipped with cameras that recognize which items customers are taking from the shelves. More branches will open throughout 2022, and other retailers will jump on the bandwagon, including Tesco, which will open the United Kingdom’s first checkout-free supermarket.
In addition to relieving humans of the responsibility of scanning purchases, computer vision has several other uses in retail, including inventory management where cameras are used to check stock levels on shelves and in warehouses and automatically order more inventory when necessary. It’s also been used to monitor and understand the movement patterns of customers around stores to optimize the positioning of goods and in security systems to deter shoplifters.
Another increasingly popular use allows customers to get information on products by scanning barcodes using their mobile phones. In fashion retail, one application of computer vision is the “virtual fitting room,” which enables shoppers to try on items without touching them. Cameras in the mirror superimpose images of the clothing on the mirror’s reflection and can identify products customers are trying on and suggest matching accessories to go with them.
Connected and autonomous cars
Computer vision is an integral element of the connected systems in modern cars. Although our first thoughts might be of the upcoming autonomous vehicles, it has several other uses in the existing range of connected cars that already are on the roads. Systems have been developed that use cameras to track facial expressions to look for warning signs that we may be getting tired and risking falling asleep at the wheel. Since fatigue is said to be a factor in up to 25 percent of fatal and serious car crashes, it’s clear that measures like this could easily save lives.
This technology already is in use in commercial vehicles such as freight trucks, and in 2022 we could see it start to make its way into personal cars, too. Other proposed uses for computer vision in cars that could make it from drawing board to reality include monitoring whether seatbelts are being worn and even whether passengers are leaving keys and phones behind as they leave taxis and ride-sharing vehicles.
Of course, computer vision will play a big part in self-driving vehicles, too. Current thinking is that it will be the most important on-board element of autonomous navigation. Tesla announced this year that its cars will rely primarily on computer vision rather than lidar and radar, which use laser and radio waves, respectively, to build a model of the car’s environment.
At the edge
Edge computing describes systems where computation is carried out as close as possible to the data source. It’s a term used in contrast to the paradigm of cloud computing where data is collected via sensors and sent to centralized servers for storage and processing. In the domain of computer vision, it is an increasingly useful concept, as computer vision systems often do jobs where action needs to be taken immediately and there isn’t time for data to be sent to the cloud.
Edge computing in relation to computer vision has important implications for security, an important factor to consider as businesses face tighter scrutiny and regulation over the way video data is captured and used. With edge devices like computer vision-equipped security cameras, data can be analyzed on the fly and discarded if there is no reason for it to be kept, for example, if no suspicious activity is detected.
Bernard Marr is a technology consultant and contributing writer for AMCS and will be a guest speaker for the AMCS Inspire Series Executive webinar on ‘How to unlock the advantage of AI to transform your organization with automation and actionable insights’ on 14th June. Register to join the webinar: http://ow.ly/ZM6J50JlPR7
See how CP Group assisted Iowa's Metro Waste Authority in providing sustainable future for Des Moines, Iowa.
The new MRF processes 25 tons per hour of single-stream recycling from more than 100,000 residents in the Des Moines metro area.
To create a successful operation, MWA emphasized advanced technology, a commitment to education and strong industry partnerships.
CP Group was selected to provide the innovative sorting system: one that would capture more material, reduce contamination and provide safe working conditions.
MWA’s new, innovative system follows the design CP Group’s design principles for the successful recovery of commodities with lower operating costs.
CP has pioneered their newest machine, the Auger Screen, in a single-stream environment to eliminate presorting. This means MWA’s process requires no traditional presort.
This nonwrapping machine fractionates material, increasing sorter safety by removing small fraction, including contamination like needles and sharps.
MWA is the first residential facility with patented nonround augers, which agitate material and create clean OCC product, omitting the need for an OCC screen.
The overs of the OCC auger screen go to a combined postsort/OCC QC. This eliminates the need for multiple sorters and sort stations.
The unders of the 6” primary auger screen go to a glass breaker, which removes the fines. These discs are specialized, long-lasting cast-chromium steel discs.
This air drum separator for glass processing is very low maintenance and uses air to remove contaminants from glass.
By agitating materials with high amplitude disc screens, glass and dirt fines are liberated from the commodities and captured by the third cut on the CP Screen.
The unders fraction from the OCC auger screen go to a glass breaker deck to remove any fines, then go directly to a MSS Fibermax.
These high-volume optical sorters have belt speeds processing at 1,000 feet per minute with the capability of more than 1,000 picks per minute, the fastest in the industry.
Optical sorting separates and recovers polyethylene terephthalate, high-density polyethylene and mixed plastics with minimal manual sorting.
This system emphasizes low maintenance, utilizing nonwrapping cantilevered auger screens and antiwrapping disc screens to fractionate/liberate material and high-capacity optics to make yes or no decisions.
The system is performing exceptionally well, reducing contamination early in the sorting process, allowing MWA to produce great output for material sales.
The education center features an exhibit space that includes kiosks, infographics and a hands-on sorting activity where visitors of all ages can learn about recycling.
The center also boasts a vibrant mural designed by a local artist, an observation deck above the sorting floor and multipurpose space for community meetings.
The tip floor spans 27,600 square feet and is completely enclosed to prevent blowing litter and protect the material from rain and snow.
“This facility will improve recycling and benefit metro communities throughout the state for years to come,” says MWA Executive Director Michael McCoy.
CP Group
6795 Calle de Linea, San Diego, CA 92154
619-477-3175
https://www.cpgrp.com/
Suppliers Partnership for the Environment’s updated guidance includes information on the recyclability of 35 different packaging material types and designs used in the automotive industry.
The Washington-based Suppliers Partnership for the Environment (SP), an association of global automakers and their suppliers working to advance environmental sustainability through the automotive supply chain, has published an updated guidance document, “Sustainable Packaging Specification Recommendations for Automotive Manufacturing Operations.”
According to a news release from SP, the document provides straightforward industry-supported guidance to help automakers and their suppliers source sustainable packaging designs for use in automotive manufacturing operations based on best practices that have been implemented by industry environmental sustainability leaders. The document can be downloaded for free here.
Building on an earlier sustainable packaging guidance published by SP in 2020, this new document was produced through a collaborative process by SP’s Sustainable Materials Work Group Sustainable Packaging Sub-Team. Members of the work group include automotive original equipment manufacturers such as Ford Motor Co., General Motors Co., Honda Development & Manufacturing America, Stellantis, Toyota Motor North America and their suppliers. The process to review and update the guidance was co-chaired by Magna International and Toyota Motor North America.
“Toyota is working to reduce the use of packaging and wrapping materials in our operations as we work toward our long-term goal to support a recycling-based society, and we expect our suppliers to undertake similar activities,” says Matt Marshall, a supply chain sustainability consultant at Plano, Texas-based Toyota Motor North America. “Through this collaborative project, we are working to provide tools and resources to help the industry in its drive to minimize automotive packaging waste and continually improve sustainability.”
The latest version of the guidance document includes information on the recyclability of 35 different packaging material types and designs commonly used in the automotive industry in the United States. The guidance also provides new information on common packaging attachment methods that can be detrimental to recycling as well as information on alternative designs that have viable outlets for recycling in key automotive regions. SP says this information is intended to support consideration of opportunities to minimize automotive packaging waste and address barriers to recyclability in the design phase where possible.
“When considering materials to create a packaging design it is important to think about not only the quality and performance but also the sustainability and recyclability of those material choices,” says Bridget Grewal, director of packaging continuous improvement at Ontario-based Magna International. “We brought in packaging and sustainability experts from across the value chain and developed a list of common packaging designs that can create a challenge for recycling as well as a list of alternative designs that tend to be more viably recyclable. We rely on our packaging engineers to design packaging that minimizes environmental impacts, and these new guidelines are a strong step forward in providing consistent information to help the industry source more sustainable packaging.”
The SP Sustainable Materials Work Group is recommending that the sustainable packaging strategies outlined in the guidance document be entered into automotive companies’ product sourcing considerations, where appropriate, and distributed widely across the automotive supply chain as best practice guidance.
Representatives from across the automotive value chain provide their input and review in the document, including companies such as Action Wood 360, AI Trading, Arplank Direct, Avangard Innovative, Denso Corp., Doug Brown Packaging Products, Ford Motor Co., General Motors Co., Green Processing Co., Honda Development & Manufacturing America, JSP, Lear Corp, Magna International, Mustang Innovation, Primex Design & Fabrication, Real Quality Services, Stellantis, Toyota Motor North America, Toyota Tsusho America and UGN.
“This was an outstanding collaborative effort bringing together automakers, tiered suppliers, packaging vendors and recyclers to work toward a shared goal of minimizing packaging waste,” says Kellen Mahoney, director at SP. “Going forward, SP intends to build on learnings from this process to promote further alignment on sustainable packaging practices across the automotive supply chain and pursue targeted opportunities to further improve packaging sustainability in support of industry sustainability goals.”
The facility in Tinley Park, Illinois, aims to support battery electric vehicle training and provide dealers and customers with easier access to training in the central U.S.
Mack Trucks, headquartered in Greensboro, North Carolina, has announced its Mack Academy opened a facility in Tinley Park, Illinois, to support battery electric vehicle (BEV) training and provide dealers and customers with easier access to training in the central United States.
The Mack Academy signed a seven-year lease (with an option to renew) for a 14,865-square-foot facility in Tinley Park, located in a manufacturing park outside Chicago. The company says the new location is “newer, larger and more modern” than its previous site in Joliet, Illinois.
“The Tinley Park Mack Academy is located in a central location so that dealers and customers needing training can easily travel to the facility,” Mack Academy Senior Manager of Operations Scott Behe says. “It is in close proximity to both O’Hare and Midway airports, and the facility is about 5,500 square feet bigger than our previous location, so it fulfills our need for more space for BEV-specific training.”
Mack says BEV coursework at Tinley Park is focused on BEV safety training, operation, repair and sales, with other courses including diesel training such as engine overhaul, transmission design and function and parts sales and warranty fundamentals. The facility has two full-time trainers and offers technical training sessions up to four times per day, and features meeting spaces so classes are not disrupted by technician training.
The Mack Trucks Academy has six training locations throughout the U.S. and Canada, including Allentown, Pennsylvania; Atlanta; Grand Prairie, Texas; and Toronto.
Mack’s first fully electric Class 8 vehicle, the Mack LR Electric, is available for order and the company says it’s supported by dealers and training facilities in various locations across the U.S. According to the company, it features 42 percent more energy and a standard 376 kWh total battery capacity, offering increased range compared with the first generation LR Electric.
The latest version also has twin electric motors and offers 448 continuous horsepower and 4,051 pound per foot of peak output torque from zero RPM. It has a two-speed Mack Powershift transmission, Mack mRide suspension and its proprietary s462R 46,000-pound rear axles.
Mack recently announced the sale of four LR Electric collection trucks to three different cities: Ocala, Florida, purchased two vehicles; Miami-Dade County purchased one; and Santa Cruz, California purchased one for its sanitation fleet.
The LR Electric is produced at the Mack Lehigh Valley Operations facility in Pennsylvania, where the company says all Mack Class 8 models for North America and export are assembled.
Mass production of the Doosan DD100 will begin in June and will launch in North America in the third quarter.
Hyundai Doosan Infracore (HDI), which has a North American office in Suwanee, Georgia, has shipped the first Doosan dozer model DD100, a 9-metric-ton dozer targeted at the North American market.
HDI also produced two additional pilot machines and shipped them to North America for various performance tests, sales, marketing and service training.
The mass production of the Doosan DD100 will begin in June and will launch in North America in the third quarter, according to the company. With the launch of the dozer, HDI hopes to create synergies with its existing excavator and wheel loader models.
“This is the next significant milestone in the development of the new Doosan dozers,” says Edward Song, CEO of Doosan Infracore North America. “Our North American dealers and their customers are eager for the arrival of the new Doosan dozers. We look forward to launching the new line of construction equipment later this year.”
The company says the dozer model was the first to be produced through the collaboration of various departments at HDI, including development analysis, market research, competitive benchmarking, validation and pilot vehicle assembly. In addition, purchasing and quality teams investigated parts supply while production teams completed the first production dozer model.
HDI also says it set plans for its 13-metric-ton dozer, the Doosan DD130, and will be shipping a pilot machine later this year. The company plans to start production as early as February 2023.