Content uploaded by Neha Umesh Mishra
Author content
All content in this area was uploaded by Neha Umesh Mishra on Apr 27, 2017
Content may be subject to copyright.
JUST WALK OUT TECHNOLOGY
Abstract
In today’s world, technology plays a
vital role, without technology it is hard to imagine our
day to day life. Everyday an innovation is taking place
in some part of the world. ‘Just walk out technology’
is such an example of innovation and sheer brilliance
that will take the world by storm. Currently this
technology is been used by self-driving cars and
major online shopping giant ‘Amazon’. Amazon have
launched it as ‘Amazon go’. But this technology has
vast applications in various fields and will play lives
changing role in near future.
... As a general overview, amazon said that they had implemented this technology using computer vision, deep learning, and sensor fusion algorithms, and they named the technology by the name "just walk out technology". However, amazon didn't reveal any further details, so this led to the appearance of several journals that tried to explain how the technologies used in this system were combined, while the number of works which tried to implement the system were few, in this paper, we will use a modified idea of the suggested implementation in [5] to build our algorithm. The reference idea implementation can be illustrated on Fig. 1, the computer vision part can be represented by the cameras above the shelf, which can be used for two purposes; detect any removed or returned objects, in addition to track and recognize customers; i.e. face recognition, while the sensor fusion part can be represented by some embedded sensors in the shelves to sense different product characteristics, for example, it may be weight sensors to sense the weight of the added or removed items, then the output of both machine vision and sensor fusion are feeding a main Artificial Intelligence (AI) system which is constructed based on different deep learning algorithms, to detect which product had been removed or added, and for which customer. ...
The shopping experiment made by amazon go in USA is one of the most interesting applications of computer vision recently. They allow you to shop and automatically charge your virtual card for whatever goods you purchased using cameras and wireless systems, so no checkouts or waiting lines are required. However, amazon didn’t reveal yet the details of how their system components are implemented. In this paper, we introduce a complete system for computer vision based automated shopping. The proposed system contains barcode scanning of objects, data registration, image capturing for offline training stage, motion (change) detection, CNN and SVM for object classification and charging/discharging customers. Our system can be integrated with the wireless data transmission to do the whole shopping process. First, the proposed method extracts the objects’ barcodes to register their details, and take sample images of objects for classifier training. We employ a pre-trained CNN (i.e. ResNet50) for feature extraction and a multi-class SVM for training. After training our classifier, we have a real-time operation stage (i.e. test stage). We assume that a camera is embedded above products on each shelf to capture videos of the products. We employ a change detector to understand any added or removed items. If the item is removed from or added to the shelve, the moving object is input to CNN feature extractor, and then SVM classifier for identification and pricing. Results show that the proposed system is fast and effective.
ResearchGate has not been able to resolve any references for this publication.