Wal-Mart Also Testing Cashier-less Model

Another indication that cashier-less models that use image recognition of product are on their way.  Recall we tested this idea in the early 90s in our labs.  Reported on it here.

Walmart-owned Sam’s Club is opening a cashier-less store in Texas in TheVerge

Just like Amazon’s automated Amazon Go stores
By Chaim Gartenberg  @cgartenberg  .... 

Going Cashier-Free

Recall we reported here a test of BlueEyes technology to test vision based interaction with product in physical retail in our store laboratory.  Our survey showed people liked the idea, once it was fully integrated.  Now a more generalized version has emerged for 'any store'.    Cost and maintenance required?  Issue with implied surveillance?

Will all retailers soon go cashier-less?     by Tom Ryan in Retailwire

After reportedly five years in development, the first Amazon Go opened in January, raising speculation over the practicality and adoption rate in the industry of cashier-less stores. Last week, a start-up said it is getting ready to deliver the “first scalable checkout-free solution” suitable for mega-retailers and affordable for mom and pops.

Describing itself as a “computer vision technology,” AiFi’s founders previously worked for Google and Apple on projects like 3D Touch and Google Glass.

Using AI (artificial intelligence) algorithms, sensors and camera networks, AiFi’s checkout-free technology will track shoppers as they move through the store, recognize shoppers as individuals and secure payment through a companion app, much like the tech used at Amazon Go.  .... " 

Also in TechCrunch and Engadget

Autonomous Shopping: No Checkouts

So called autonomous, 'checkout-free' experience.     Like that being done with Amazon Go.  Note how other behavioral information can be derived from such interactions.  In Mashable.

 We experimented and provided support to IBM's research work in this area, called BlueEyes, in around 2005.   See tag below.

"  .... A startup is showing how its AI-powered store will change our shopping habits ... A startup called Standard Cognition is experimenting with using machine learning and cameras to create an automated checkout experience.   ... "

See also the demo video at Standard Cognition, which has a more detailed demonstration of the system in action.

(Update) It comes to mind that I have observed my local Kroger getting crowded with workers assembling pickup orders. Could this process be improved by robotics and order interaction with image recognition?  Likely.

AmazonGo Tests Effort-less Buying

In the isle, without checkouts.   But tracking I am sure.   So this can detect aspects of movement and context that take us to purchase.  What are the patterns that make us buy?  We tested similar approaches which modeled all activity in a physical store.   See the BlueEyes tab below.



Amazon Go lets you trade your privacy for a cashier-less lunch buying experience

 Amazon has launched a shop that will make you feel like a shoplifter but will actually be tracking your every move. 

Amazon Go arrives in the form of an 1800-square-foot retail space located in the company's hometown of Seattle and is described by the firm as a "new kind of store" without checkouts. 

Instead of making small talk with cashiers or battling a self-service checkout that refuses to recognise your shopping in the bagging area, Amazon Go lets you waltz in, pick up a sandwich, and walk straight out. 

Naturally, that doesn't mean you're getting a free BLT on Amazon. Not only will you be charged once you've left the shop courtesy of the Amazon Go app that you'll need to install on your smartphone, you'll also have sacrificed your privacy for a speedy sandwich shopping experience. 

"Our checkout-free shopping experience is made possible by the same types of technologies used in self-driving cars: computer vision, sensor fusion, and deep learning," Amazon explains.

"Our Just Walk Out technology automatically detects when products are taken from or returned to the shelves and keeps track of them in a virtual cart. When you’re done shopping, you can just leave the store. Shortly after, we’ll charge your Amazon account and send you a receipt."  .... " 

What does Amazongo Mean to retail?  Discussion in Retailwire.  Redefining convenience?

Webcams and Maps

My writing about the famous coffee pot Webcam, and its internet of things implications, reminded me of work we did looking at the output of public webcams as data sources for shopping traffic and activity.  Different than the gathering of data in our lab, linked to work with IBM,  but still a source of public data to combine with private.  In 2009 Google announced a layer of public webcam to be added to maps.   Regrettably later this effort was removed and added to a separate map effort.  There are still many directories of Webcams still online.

Advanced Pedestrian Detection/Analysis

Detecting and counting pedestrians is not new, has been done since the 90s, but advanced analysis of real time video is rapidly changing.   Called VCA, or Video content analysis.  Interesting that Google is involved.  Likely for driver less car applications.  But possible for other retail applications, which we also examined.  Consider also how such methods can be connected with digital signage.

" ... Google Research has quietly made a breakthrough in the emerging area of image recognition and rapid video analysis — a breakthrough that has significant implications for pedestrian detection. Pedestrian detection refers to the analysis of statistics of pedestrian scale, occlusion and location. It gives detection systems a base of knowledge under which to operate ......  As an experiment [PDF], Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga and George Toderici — researchers from the University of Maryland at College Park, the University of Texas at Austin and Google — applied several deep neural network architectures to analyze a dataset of videos over longer time periods than previously attempted. ... " 

See a long ago item on project BlueEyes we participated in.

Billboards Looking Back

The basic idea has been tried a number of times. I know of no cases where it is permanently installed. The technology is there but still imperfect. The behavioral data would be useful. See also Videomining. In Slashdot and GoodGearGuide:

... "At a Tokyo railway station above a flat-panel display hawking DVDs and books sits a small camera hooked up to some image processing software. When trials begin in January the camera will scan travelers to see how many of them are taking note of the panel, in part of a technology test being run by NTT Communications. It doesn't seek to identify individuals, but it will attempt to figure out how many of the people standing in front of an advertisement are actually looking at it. A second camera, which wasn't fitted at the station but will be when tests begin next month, will take care of estimating how many people are in front of the ad, whether they are looking at it or not." ... '

Also see this previous post, which describes something similar, not sure it is the same thing. Above picture, a very advanced system from IBM, called BlueEyes, tracks shoppers in a supermarket aisle, painting them in color.