Computer Vision
Auto Added by WPeMatico
Greyparrot bags $2.2M seed to scale its AI for waste management
London-based Greyparrot, which uses computer vision AI to scale efficient processing of recycling, has bagged £1.825 million (~$2.2M) in seed funding, topping up the $1.2M in pre-seed funding it had raised previously. The latest round is led by early stage European industrial tech investor Speedinvest, with participation from UK-based early stage b2b investor, Force Over Mass.
The 2019 founded startup — and TechCrunch Disrupt SF battlefield alum — has trained a series of machine learning models to recognize different types of waste, such as glass, paper, cardboard, newspapers, cans and different types of plastics, in order to make sorting recycling more efficient, applying digitization and automation to the waste management industry.
Greyparrot points out that some 60% of the 2BN tonnes of solid waste produced globally each year ends up in open dumps and landfill, causing major environmental impact. While global recycling rates are just 14% — a consequence of inefficient recycling systems, rising labour costs, and strict quality requirements imposed on recycled material. Hence the major opportunity the team has lit on for applying waste recognition software to boost recycling efficiency, reduce impurities and support scalability.
By embedding their hardware agnostic software into industrial recycling processes Greyparrot says it can offer real-time analysis on all waste flows, thereby increasing efficiency while enabling a facility to provide quality guarantee to buyers, mitigating against risk.
Currently less than 1% of waste is monitored and audited, per the startup, given the expensive involved in doing those tasks manually. So this is an application of AI that’s not so much taking over a human job as doing something humans essentially don’t bother with, to the detriment of the environment and its resources.
Greyparrot’s first product is an Automated Waste Monitoring System which is currently deployed on moving conveyor belts in sorting facilities to measure large waste flows — automating the identification of different types of waste, as well as providing composition information and analytics to help facilities increase recycling rates.
It partnered with ACI, the largest recycling system integrator in South Korea, to work on early product-market fit. It says the new funding will be used to further develop its product and scale across global markets. It’s also collaborating with suppliers of next-gen systems such as smart bins and sorting robots to integrate its software.
“One of the key problems we are solving is the lack of data,” said Mikela Druckman, co-founder & CEO of Greyparrot in a statement. “We see increasing demand from consumers, brands, governments and waste managers for better insights to transition to a more circular economy. There is an urgent opportunity to optimise waste management with further digitisation and automation using deep learning.”
“Waste is not only a massive market — it builds up to a global crisis. With an increase in both world population and per capita consumption, waste management is critical to sustaining our way of living. Greyparrot’s solution has proven to bring down recycling costs and help plants recover more waste. Ultimately it unlocks the value of waste and creates a measurable impact for the environment,” added Marie-Hélène Ametsreiter, lead partner at Speedinvest Industry, in another statement.
Greyparrot is sitting pretty in another aspect — aligning with several strategic areas of focus for the European Union, which has made digitization of legacy industries, industrial data sharing, investment in AI, plus a green transition to a circular economy core planks of its policy plan for the next five+ years. Just yesterday the Commission announced a €750BN pan-EU support proposal to feed such transitions as part of a wider coronavirus recovery plan for the trading bloc.
Powered by WPeMatico
FortressIQ snags $30M Series B to streamline processes with AI-fueled data
As we move through life in the pandemic, companies are being forced to review and understand how workflows happen. How do you distribute laptops to your workforce? How do you make sure everyone has the correct tool set? FortressIQ, a startup that wants to help companies use data to understand and improve internal processes, announced a $30 million Series B investment today.
M12, Microsoft’s venture fund and Tiger Global Management led the round with help from previous investors Boldstart Ventures, Comcast Ventures, Eniac Ventures and Lightspeed Venture Partners. The company has now raised almost $65 million, according to Pitchbook data.
As the product has matured, founder and CEO Pankaj Chowdhry, says its focus has shifted a bit. Whereas before it was primarily about using computer vision to understand workflows, customers are now using that data to help drive their own internal transformations.
That used to require a high priced consulting team to pull off, but FortressIQ is trying to use software, data and artificial intelligence to replace the consultant and expose processes that could be improved.
“We’re building this kind of cool computer vision to help with process discovery, mostly in the automation space to help you automate processes. But what we’ve seen is people leveraging our data to drive transformation strategies, of which automation ends up being a pretty small component,” Chowdry explained.
He said that this is helping define new ways of using the tool they hadn’t considered when they first started the company. “If you think about it, we can use analytics to drive better experiences, better training, all of that. We’ve seen how customers are driving overall improvement strategies by leveraging the data coming out of this system,” he said.
The company currently has 65 employees, but he couldn’t commit to a future number at this point because of the uncertainty that exists in the economy. He knows he wants to hire, but he’s not sure what that will look like. He said they used to revisit hiring every six months. Now it’s ever six weeks, and so they keep having to reevaluate based on an ever-shifting set of conditions.
Chowdry believes that companies will need to be more agile moving forward to react more quickly to changing circumstances beyond the current crisis, and he thinks that’s going to require solid business relationships to pull off.
“I think the idea is to be leveraging this time to build that relationship with your customers so as they do start looking at what are they going to do and where they need to be invested in the business, that we’ve got both the data and the infrastructure to help them do that.”
Powered by WPeMatico
Invisible AI uses computer vision to help (but hopefully not nag) assembly line workers
“Assembly” may sound like one of the simpler tests in the manufacturing process, but as anyone who’s ever put together a piece of flat-pack furniture knows, it can be surprisingly (and frustratingly) complex. Invisible AI is a startup that aims to monitor people doing assembly tasks using computer vision, helping maintain safety and efficiency — without succumbing to the obvious all-seeing-eye pitfalls. A $3.6 million seed round ought to help get them going.
The company makes self-contained camera-computer units that run highly optimized computer vision algorithms to track the movements of the people they see. By comparing those movements with a set of canonical ones (someone performing the task correctly), the system can watch for mistakes or identify other problems in the workflow — missing parts, injuries and so on.
Obviously, right at the outset, this sounds like the kind of thing that results in a pitiless computer overseer that punishes workers every time they fall below an artificial and constantly rising standard — and Amazon has probably already patented that. But co-founder and CEO Eric Danziger was eager to explain that this isn’t the idea at all.
“The most important parts of this product are for the operators themselves. This is skilled labor, and they have a lot of pride in their work,” he said. “They’re the ones in the trenches doing the work, and catching and correcting mistakes is a big part of it.”
“These assembly jobs are pretty athletic and fast-paced. You have to remember the 15 steps you have to do, then move on to the next one, and that might be a totally different variation. The challenge is keeping all that in your head,” he continued. “The goal is to be a part of that loop in real time. When they’re about to move on to the next piece we can provide a double check and say, ‘Hey, we think you missed step 8.’ That can save a huge amount of pain. It might be as simple as plugging in a cable, but catching it there is huge — if it’s after the vehicle has been assembled, you’d have to tear it down again.”
This kind of body tracking exists in various forms and for various reasons; Veo Robotics, for instance, uses depth sensors to track an operator and robot’s exact positions to dynamically prevent collisions.
But the challenge at the industrial scale is less “how do we track a person’s movements in the first place” than “how can we easily deploy and apply the results of tracking a person’s movements.” After all, it does no good if the system takes a month to install and days to reprogram. So Invisible AI focused on simplicity of installation and administration, with no code needed and entirely edge-based computer vision.
“The goal was to make it as easy to deploy as possible. You buy a camera from us, with compute and everything built in. You install it in your facility, you show it a few examples of the assembly process, then you annotate them. And that’s less complicated than it sounds,” Danziger explained. “Within something like an hour they can be up and running.”
Once the camera and machine learning system is set up, it’s really not such a difficult problem for it to be working on. Tracking human movements is a fairly straightforward task for a smart camera these days, and comparing those movements to an example set is comparatively easy, as well. There’s no “creativity” involved, like trying to guess what a person is doing or match it to some huge library of gestures, as you might find in an AI dedicated to captioning video or interpreting sign language (both still very much works in progress elsewhere in the research community).
As for privacy and the possibility of being unnerved by being on camera constantly, that’s something that has to be addressed by the companies using this technology. There’s a distinct possibility for good, but also for evil, like pretty much any new tech.
One of Invisible’s early partners is Toyota, which has been both an early adopter and skeptic when it comes to AI and automation. Their philosophy, one that has been arrived at after some experimentation, is one of empowering expert workers. A tool like this is an opportunity to provide systematic improvement that’s based on what those workers already do.
It’s easy to imagine a version of this system where, like in Amazon’s warehouses, workers are pushed to meet nearly inhuman quotas through ruthless optimization. But Danziger said that a more likely outcome, based on anecdotes from companies he’s worked with already, is more about sourcing improvements from the workers themselves.
Having built a product day in and day out year after year, these are employees with deep and highly specific knowledge on how to do it right, and that knowledge can be difficult to pass on formally. “Hold the piece like this when you bolt it or your elbow will get in the way” is easy to say in training but not so easy to make standard practice. Invisible AI’s posture and position detection could help with that.
“We see less of a focus on cycle time for an individual, and more like, streamlining steps, avoiding repetitive stress, etc.,” Danziger said.
Importantly, this kind of capability can be offered with a code-free, compact device that requires no connection except to an intranet of some kind to send its results to. There’s no need to stream the video to the cloud for analysis; footage and metadata are both kept totally on-premise if desired.
Like any compelling new tech, the possibilities for abuse are there, but they are not — unlike an endeavor like Clearview AI — built for abuse.
“It’s a fine line. It definitely reflects the companies it’s deployed in,” Danziger said. “The companies we interact with really value their employees and want them to be as respected and engaged in the process as possible. This helps them with that.”
The $3.6 million seed round was led by 8VC, with participating investors including iRobot Corporation, K9 Ventures, Sierra Ventures and Slow Ventures.
Powered by WPeMatico
What happens if Magic Leap shuts down?
Since first uploading a YouTube teaser video of its tech five years ago, Magic Leap’s presence in the augmented reality industry has been controversial.
Some have lauded the team’s ambitions, while others I’ve talked to say the company’s posturing has dissuaded investors from taking chances on other AR hardware startups, which has hampered the industry’s advance.
Regardless of its impact, Magic Leap carries outsized weight, leading one to question what would happen to other AR companies if the company’s situation worsened.
The company announced layoffs today, with reports indicating that it is dismissing around 1,000 employees — about half of the company. Magic Leap’s added news of a major pivot to enterprise makes it seem like that wasn’t its primary strategy over the past year. From my perspective, the company looks like it is on a path to a fire sale and will be dependent on executing a dramatic turnaround, which grows tougher under current economic conditions.
Magic Leap has few users, so a theoretical shutdown would likely have a lesser impact than other unicorn flare-outs; still, losing a company on the forefront of a technology lauded by many as the next ubiquitous platform will certainly impact others that are striving to bring this tech to market.
The impact for startups moving forward would be nuanced. Without a substantial software suite of its own, Magic Leap relied heavily on developer partnerships, though in recent months many of those seemed to promote enterprise use cases. AR/VR startups are already in a rough position, and one less developer platform could force more companies to de-prioritize headset-based platforms and shift their focus to mobile.
Powered by WPeMatico
WorldGaze uses smartphone cameras to help voice AIs cut to the chase
If you find voice assistants frustratingly dumb, you’re hardly alone. The much-hyped promise of AI-driven vocal convenience very quickly falls through the cracks of robotic pedantry.
A smart AI that has to come back again (and sometimes again) to ask for extra input to execute your request can seem especially dumb — when, for example, it doesn’t get that the most likely repair shop you’re asking about is not any one of them but the one you’re parked outside of right now.
Researchers at the Human-Computer Interaction Institute at Carnegie Mellon University, working with Gierad Laput, a machine learning engineer at Apple, have devised a demo software add-on for voice assistants that lets smartphone users boost the savvy of an on-device AI by giving it a helping hand — or rather a helping head.
The prototype system makes simultaneous use of a smartphone’s front and rear cameras to be able to locate the user’s head in physical space, and more specifically within the immediate surroundings — which are parsed to identify objects in the vicinity using computer vision technology.
The user is then able to use their head as a pointer to direct their gaze at whatever they’re talking about — i.e. “that garage” — wordlessly filling in contextual gaps in the AI’s understanding in a way the researchers contend is more natural.
So, instead of needing to talk like a robot in order to tap the utility of a voice AI, you can sound a bit more, well, human. Asking stuff like “‘Siri, when does that Starbucks close?” Or — in a retail setting — “are there other color options for that sofa?” Or asking for an instant price comparison between “this chair and that one.” Or for a lamp to be added to your wish-list.
In a home/office scenario, the system could also let the user remotely control a variety of devices within their field of vision — without needing to be hyper-specific about it. Instead they could just look toward the smart TV or thermostat and speak the required volume/temperature adjustment.
The team has put together a demo video (below) showing the prototype — which they’ve called WorldGaze — in action. “We use the iPhone’s front-facing camera to track the head in 3D, including its direction vector. Because the geometry of the front and back cameras are known, we can raycast the head vector into the world as seen by the rear-facing camera,” they explain in the video.
“This allows the user to intuitively define an object or region of interest using the head gaze. Voice assistants can then use this contextual information to make enquiries that are more precise and natural.”
In a research paper presenting the prototype they also suggest it could be used to “help to socialize mobile AR experiences, currently typified by people walking down the street looking down at their devices.”
Asked to expand on this, CMU researcher Chris Harrison told TechCrunch: “People are always walking and looking down at their phones, which isn’t very social. They aren’t engaging with other people, or even looking at the beautiful world around them. With something like WorldGaze, people can look out into the world, but still ask questions to their smartphone. If I’m walking down the street, I can inquire and listen about restaurant reviews or add things to my shopping list without having to look down at my phone. But the phone still has all the smarts. I don’t have to buy something extra or special.”
In the paper they note there is a long body of research related to tracking users’ gaze for interactive purposes — but a key aim of their work here was to develop “a functional, real-time prototype, constraining ourselves to hardware found on commodity smartphones.” (Although the rear camera’s field of view is one potential limitation they discuss, including suggesting a partial workaround for any hardware that falls short.)
“Although WorldGaze could be launched as a standalone application, we believe it is more likely for WorldGaze to be integrated as a background service that wakes upon a voice assistant trigger (e.g., ‘Hey Siri’),” they also write. “Although opening both cameras and performing computer vision processing is energy consumptive, the duty cycle would be so low as to not significantly impact battery life of today’s smartphones. It may even be that only a single frame is needed from both cameras, after which they can turn back off (WorldGaze startup time is 7 sec). Using bench equipment, we estimated power consumption at ~0.1 mWh per inquiry.”
Of course there’s still something a bit awkward about a human holding a screen up in front of their face and talking to it — but Harrison confirms the software could work just as easily hands-free on a pair of smart spectacles.
“Both are possible,” he told us. “We choose to focus on smartphones simply because everyone has one (and WorldGaze could literally be a software update), while almost no one has AR glasses (yet). But the premise of using where you are looking to supercharge voice assistants applies to both.”
“Increasingly, AR glasses include sensors to track gaze location (e.g., Magic Leap, which uses it for focusing reasons), so in that case, one only needs outwards facing cameras,” he added.
Taking a further leap it’s possible to imagine such a system being combined with facial recognition technology — to allow a smart spec-wearer to quietly tip their head and ask “who’s that?” — assuming the necessary facial data was legally available in the AI’s memory banks.
Features such as “add to contacts” or “when did we last meet” could then be unlocked to augment a networking or socializing experience. Although, at this point, the privacy implications of unleashing such a system into the real world look rather more challenging than stitching together the engineering. (See, for example, Apple banning Clearview AI’s app for violating its rules.)
“There would have to be a level of security and permissions to go along with this, and it’s not something we are contemplating right now, but it’s an interesting (and potentially scary idea),” agrees Harrison when we ask about such a possibility.
The team was due to present the research at ACM CHI — but the conference was canceled due to the coronavirus.
Powered by WPeMatico
Activity-monitoring startup Zensors repurposes its tech to help coronavirus response
Computer vision techniques used for commercial purposes are turning out to be valuable tools for monitoring people’s behavior during the present pandemic. Zensors, a startup that uses machine learning to track things like restaurant occupancy, lines and so on, is making its platform available for free to airports and other places desperate to take systematic measures against infection.
The company, founded two years ago but covered by TechCrunch in 2016, was among the early adopters of computer vision as a means to extract value from things like security camera feeds. It may seem obvious now that cameras covering a restaurant can and should count open tables and track that data over time, but a few years ago it wasn’t so easy to come up with or accomplish that.
Since then Zensors has built a suite of tools tailored to specific businesses and spaces, like airports, offices and retail environments. They can count open and occupied seats, spot trash, estimate lines and all that kind of thing. Coincidentally, this is exactly the kind of data that managers of these spaces are now very interested in watching closely given the present social distancing measures.
Zensors co-founder Anuraag Jain told Carnegie Mellon University — which the company was spun out of — that it had received a number of inquiries from the likes of airports regarding applying the technology to public health considerations.
Software that counts how many people are in line can be easily adapted to, for example, estimate how close people are standing and send an alert if too many people are congregating or passing through a small space.
“Rather than profiting off them, we thought we would give our help for free,” said Jain. And so, for the next two months at least, Zensors is providing its platform for free to “selected entities who are on the forefront of responding to this crisis, including our airport clients.”
The system has already been augmented to answer COVID-19-specific questions, like whether there are too many people in a given area, when a surface was last cleaned and whether cleaning should be expedited, and how many of a given group are wearing face masks.
Airports surely track some of this information already, but perhaps in a much less structured way. Using a system like this could be helpful for maintaining cleanliness and reducing risk, and no doubt Zensors hopes that having had a taste via what amounts to a free trial, some of these users will become paying clients. Interested parties should get in touch with Zensors via its usual contact page.
Powered by WPeMatico
Glisten uses computer vision to break down product photos to their most important parts
It’s amazing that in this day and age, the best way to search for new clothes is to click a few check boxes and then scroll through endless pictures. Why can’t you search for “green patterned scoop neck dress” and see one? Glisten is a new startup enabling just that by using computer vision to understand and list the most important aspects of the products in any photo.
Now, you may think this already exists. In a way, it does — but not a way that’s helpful. Co-founder Sarah Wooders encountered this while working on a fashion search project of her own while going to MIT.
“I was procrastinating by shopping online, and I searched for v-neck crop shirt, and only like two things came up. But when I scrolled through there were 20 or so,” she said. “I realized things were tagged in very inconsistent ways — and if the data is that gross when consumers see it, it’s probably even worse in the backend.”
As it turns out, computer vision systems have been trained to identify, really quite effectively, features of all kinds of images, from identifying dog breeds to recognizing facial expressions. When it comes to fashion and other relatively complex products, they do the same sort of thing: Look at the image and generate a list of features with corresponding confidence levels.
So for a given image, it would produce a sort of tag list, like this:
As you can imagine, that’s actually pretty useful. But it also leaves a lot to be desired. The system doesn’t really understand what “maroon” and “sleeve” really mean, except that they’re present in this image. If you asked the system what color the shirt is, it would be stumped unless you manually sorted through the list and said, these two things are colors, these are styles, these are variations of styles, and so on.
That’s not hard to do for one image, but a clothing retailer might have thousands of products, each with a dozen pictures, and new ones coming in weekly. Do you want to be the intern assigned to copying and pasting tags into sorted fields? No, and neither does anyone else. That’s the problem Glisten solves, by making the computer vision engine considerably more context-aware and its outputs much more useful.
Here’s the same image as it might be processed by Glisten’s system:
Better, right?
“Our API response will be actually, the neckline is this, the color is this, the pattern is this,” Wooders said.
That kind of structured data can be plugged far more easily into a database and queried with confidence. Users (not necessarily consumers, as Wooders explained later) can mix and match, knowing that when they say “long sleeves” the system has actually looked at the sleeves of the garment and determined that they are long.
The system was trained on a growing library of around 11 million product images and corresponding descriptions, which the system parses using natural language processing to figure out what’s referring to what. That gives important contextual clues that prevent the model from thinking “formal” is a color or “cute” is an occasion. But you’d be right in thinking that it’s not quite as easy as just plugging in the data and letting the network figure it out.
Here’s a sort of idealized version of how it looks:
“There’s a lot of ambiguity in fashion terms and that’s definitely a problem,” Wooders admitted, but far from an insurmountable one. “When we provide the output for our customers we sort of give each attribute a score. So if it’s ambiguous, whether it’s a crew neck or a scoop neck, if the algorithm is working correctly it’ll put a lot of weight on both. If it’s not sure, it’ll give a lower confidence score. Our models are trained on the aggregate of how people labeled things, so you get an average of what people’s opinion is.”
The model was initially aimed at fashion and clothing in general, but with the right training data it can apply to plenty of other categories as well — the same algorithms could find the defining characteristics of cars, beauty products and so on. Here’s how it might look for a shampoo bottle — instead of sleeves, cut and occasion you have volume, hair type and paraben content.
Although shoppers will likely see the benefits of Glisten’s tech in time, the company has found that its customers are actually two steps removed from the point of sale.
“What we realized over time was that the right customer is the customer who feels the pain point of having messy unreliable product data,” Wooders explained. “That’s mainly tech companies that work with retailers. Our first customer was actually a pricing optimization company, another was a digital marketing company. Those are pretty outside what we thought the applications would be.”
It makes sense if you think about it. The more you know about the product, the more data you have to correlate with consumer behaviors, trends and such. Knowing summer dresses are coming back, but knowing blue and green floral designs with 3/4 sleeves are coming back is better.
Glisten co-founders Sarah Wooders (left) and Alice Deng
Competition is mainly internal tagging teams (the manual review we established none of us would like to do) and general-purpose computer vision algorithms, which don’t produce the kind of structured data Glisten does.
Even ahead of Y Combinator’s demo day next week the company is already seeing five figures of monthly recurring revenue, with their sales process limited to individual outreach to people they thought would find it useful. “There’s been a crazy amount of sales these past few weeks,” Wooders said.
Soon Glisten may be powering many a product search engine online, though ideally you won’t even notice — with luck you’ll just find what you’re looking for that much easier.
(This article originally had Alice Deng quoted throughout when in fact it was Wooders the whole time — a mistake in my notes. It has also been updated to better reflect that the system is applicable to products beyond fashion.)
Powered by WPeMatico
Deep North raises $25.7M for AI that uses CCTV to build retail analytics
Amazon and others have raised awareness of how the in-store shopping experience can be sped up (and into the future) using computer vision to let a person pay for and take away items without ever interacting with a cashier, human or otherwise. Today, a startup is announcing funding for its own take on how to use AI-based video detection get more insights out of the retail experience. Deep North, which has built an analytics platform that builds insights for retailers based on the the videos from the CCTV and other cameras that those retailers already use, is today announcing that it has raised $25.7 million in funding, a Series A round that it plans to use to continue expanding its platform.
Deep North’s AI currently measures such parameters as daily entries and exits; occupancy; queue times; conversions and heat maps — a list and product roadmap that it’s planning to continue growing with this latest investment. It says that using cameras to build its insights is more accurate and scalable than current solutions that include devices like beacons, RFID tags, mobile networks, smartphone tracking and shopping data. A typical installation takes a weekend to do.
The funding is being led by London VC Celeres Investments (backer of self-driving startup Phantom AI, among others), with participation also from Engage, AI List Capital and others. The startup is not disclosing its valuation, and previously Deep North has not disclosed how much it has raised.
Previously known as VMAXX, the Bay Area-based startup, according to CEO and co-founder Rohan Sanil, currently is in use by customers in the US and Europe. It does not disclose customer names, but Sanil said the list includes shopping centers, retailers, commercial real estate businesses and transportation hubs.
There are a number of retail analytics plays on the market today, but up to now the vast majority of them have been based on using other kinds of non-visual (and non-video) data to build their pictures of how a business is working, including logs of sales, card payments, in-store beacons, in-store WiFi and smartphone usage.
This list is, indeed, extensive and already provides a startling amount of data on the average shopper, but it has its drawbacks. Some people don’t use in-store WiFi; beacons are not as ubiquitous as CCTV; certain shopping data is a false positive, in the sense that if you don’t buy anything, it’s harder to track why not and where everything went wrong in getting you to shop; and perhaps, most importantly, you can’t see how shoppers are behaving, where they are looking and walking.
“The data collected [by these other means] is only 30-60% accurate and then extrapolated,” Sanil notes in a blog post. And that is not the only challenge. “The other is the enormous cost of the technology along with the software – which requires a team of programmers to get anything beyond stock analysis – plus being locked into a single vendor.”
Video systems “make a lot more sense,” he adds, and so does using those that are already installed in retailers’ locations. “The customers we see have no interest in deploying and paying for additional infrastructure, when the average store has several cameras already, and a typical big box store has dozens. Making our vision work means quantifying what a camera can see – and seeing through the cameras already in use.” The company typically integrates with 60-70% of a company’s installed cameras to run its analytics.
It’s that differentiation that has attracted investors. “Deep North’s platform allows retailers to gain real time insights on data points that were previously unattainable in the physical world. By leveraging existing video footage to understand activity and behavior, operators can now make informed decisions with the help of their prescriptive analytics engine,” said Azhaan Merchant of Celeres Investments, in a statement.
CCTV has had a problematic profile in the world of data privacy, where people pinpoint it as enemy number one in our rapidly expanding surveillance economy, and have ironically pointed out that it rarely is fit for the purpose it was originally set out to serve, which is deterring and identifying shoplifters. It’s notable to me that Deep North doesn’t actually ever use the term CCTV. (“Customers use a variety of terms for their cameras including CCTV, camera networks and loss prevention cameras so we’ve chosen to use a broader term that encompasses them,” a spokesperson said.)
Whatever you choose to call them, if a retailer has already made the leap into having these cameras installed, using them for analytics gives that business another way of getting a better return on investment. Sanil says that in any case, its platform is respectful of privacy.
“Deep North is not able to ascertain the identity of any individual captured via in-store footage,” he said. “We have no capability to link the metadata to any single individual. Further, Deep North does not capture personally identifiable information (PII) and was developed to govern and preserve the integrity of each and every individual by the highest possible standards of anonymization. Deep North does not retain any PII whatsoever, and only stores derived metadata that produces metrics such as number of entries, number of exits, etc. Deep North strives to stay compliant with all existing privacy policies including GDPR and the California Consumer Privacy Act.” (It has operations in Europe where it would need to comply with GDPR.)
Still, Deep North’s combination of computer vision with retail technology is a signal of a bigger trend. Many providers of security cameras have started to incorporate retail analytics into their wider offerings, and those that are concentrating on check out, like Amazon but also startups like Trigo, are likely also to consider this area too. Longer term, as retailers, but also their IT providers, look to get more intelligence about how their businesses are working in a bid for better margins, we’re likely to see even more players in this space.
For Deep North, that might mean also expanding into a wider set of products that not only are able to generate insights into how people shop, but then to use to those to build recommendations into how stores are laid out, or prompts to shoppers for what they might consider next as they browse.
Powered by WPeMatico
Visual One smartens up home security cameras with object and action recognition
“Smart” cameras are to be found in millions of homes, but the truth is they’re not all that smart. Facial recognition and motion detection are their main tricks… but what if you want to know if the dog jumped on the couch, or if your toddler is playing with the stove? Visual One equips cameras with the intellect to understand a bit more of the world and give you more granular — and important — information.
Founder Mohammad Rafiee said that the idea came to him after he got a puppy (Zula) and was dissatisfied with the options he had for monitoring her activities while he was away. Here she is doing what dogs do best:
There are no bad dogs, but chairs are for people
“There were specific things I wanted to know were happening, like I wanted to check if the dog got picked up by the dog walker. The cameras’ motion detection is useless — she’s always moving,” he lamented. “In fact, with a lot of these cameras, just a change in the lighting or wind or rain can trigger the motion alert, so it’s completely impractical.”
“My background is in machine learning. I was thinking about it, and realized we’re at a stage where this problem is starting to become solvable,” he continued.
Some tasks in computer vision, indeed, are as good as solved — detecting faces and common objects such as cars and bikes can be done quickly and efficiently. But that’s not always useful — what’s the point of knowing someone rode their bike past your house? In order for this to have value, the objects need to be understood as part of a greater context, and that’s what Rafiee and Visual One are undertaking.
Unfortunately, it’s far from easy — or else everyone would be doing it already. Identifying a cat is simple, and identifying a table is simple, but identifying a cat on a table is surprisingly hard.
“It’s a very difficult problem. So we’re breaking it down to things we can solve right now, then building on that,” Rafiee explained. “With deep learning techniques we can identify different objects, and we build models on top of those to specify different interactions, or specific objects being in specific locations. Like a car in the wrong spot, or a dog getting on a couch. We can recognize that with high accuracy right now — we have a list of supported objects and models that we’re expanding.”
In case you’re not convinced that the capabilities are that much advanced from the usual “activity in the living room” or “Kendra is at the front door” notifications, here are a few situations that Visual One is set up to detect:
- Kid playing with the stove
- Toddler climbing furniture
- Kid holding a knife
- Baby left alone for too long
- Raccoon getting into garbage
- Elderly person taking her medications
- Elderly person in bed for too long
- Car parked in the wrong spot
- Garage door left open
- Dog chewing on a shoe
- Cat scratching the furniture
The process for creating these triggers is pretty straightforward
If one of those doesn’t make you think “actually… that would be really good to know,” then perhaps a basic security camera is enough for your purposes after all. Not everyone has a knife-curious toddler. But those of you who do are probably scrolling furiously past this paragraph looking for where to buy one of these things.
Unfortunately Visual One isn’t something you can just install on any old existing system — with the prominent exception of Nest, into which it can plug. Camera workflows are generally too locked down for security and privacy purposes to allow for third-party apps and services to be slipped in. But the company isn’t trying to bankrupt everyone with an ultra-luxury offering. It’s using off-the-shelf cameras from Wyze and loading them with its own software stack.
Rafiee said he pictures Visual One as a mid-tier option for people who want to have more than a basic camera setup but aren’t convinced by the more expensive plays. That way the company avoids going head-on with commodity hardware’s race to the bottom or the brand warfare taking place between Google and Amazon’s Nest and Ring. Cameras cost $30-$40, and the service is $7 per month currently.
Ultimately the low-end companies may want to license from Visual One, while the high-end companies will be developing their own full stack at great cost, making it difficult for them to go downmarket. “Hardware is hard, and AI is specialized — unless you’re a giant company it’s hard to do both. I think we can fill the gap in the market for mid-market companies without those resources,” he said.
Of course privacy is paramount as well, and Rafiee said that because of the way their system works, although the AI lives in the cloud and therefore requires the cameras to be online (like most others), no important user data needs to be or will be stored on Visual One servers. “We do inference in the cloud so we can be hardware agnostic, but we don’t need to store any data. So we don’t add any risk,” he said.
Visual One is launching today (after a stint in YC’s latest cohort) with an initial set of objects and interactions, and will continue developing more as it observes which use cases prove popular and effective.
Powered by WPeMatico
Facebook brings its 3D photos feature to users with single-camera phones
Facebook first showed off its 3D photos back in 2018, and shared the technical details behind it a month later. But unless you had one of a handful of phones with dual cameras back then (when they weren’t so common), you couldn’t make your own. Today an update brings 3D photos to those of us still rocking a single camera.
In case you don’t remember or haven’t seen one lately, the 3D photos work by analyzing a 2D picture and slicing it into a ton of layers that move separately when you tilt the phone or scroll. I’m not a big fan of 3D anything, and I don’t even use Facebook, but the simple fact is this feature is pretty cool.
The problem is it used the dual-camera feature to help the system determine distance, which informed how the picture should be sliced. That meant I, with my beautiful iPhone SE, was out of the running — along with about a billion other people who hadn’t bought into the dual-camera thing yet.
But over the last few years the computer vision team over at Facebook has been working on making it possible to do this without dual-camera input. At last they succeeded, and this blog post explains, in terms technical enough that I’m not even going to attempt to summarize them here, just how they did it.
The advances mean that many — though not all — relatively modern single-camera phones should be able to use the feature. Google’s Pixel series is now supported, and single-camera iPhones from the 7 forward. The huge diversity of Android devices makes it hard to say which will and won’t be supported — it depends on a few things not usually listed on the spec sheet — but you’ll be able to tell once your Facebook app updates and you take a picture.
Powered by WPeMatico