AIoT-based Smart Cart System

• Published in: 2022 International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN) pp. 1 - 6
• Main Authors: S, Sakthivel, K, Akash Ram R., Sai B, Sidarth, M, Vijaya Kesavan K., Kumar C, Ganesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 25.03.2022
• Subjects: Automation; Cameras; Feature extraction; Neural networks; Object detection; Object recognition; RFID; Security; Smart Shopping Cart; Super market; YOLO neural network
• DOI: 10.1109/ICSTSN53084.2022.9761346

A supermarket is a place where customers go to purchase and pay for their daily necessities. As a result, calculating the number of things sold and generating a bill for the consumer is required. Generally shopping in a mall is very tedious where the right items needed are difficult to find. After that, standing in line to bill all of the things are exhausting. For this, the developed model here would be a solution which is a smart shopping cart system that would keep track of purchased products, as well as bill payment, is done using RFID (Radio Frequency Identification). In this paper, the automation of invoicing and payment is done using image processing, RFID scanners, and tags for consumers' convenience. In this case, RFID cards are being used, which are similar to the smart wallet systems that are popular in malls these days. Since assigning RFID tags to every item is a tiresome process, instead, they will only be assigned to a group of the same products, and the number of items chosen from each group will be determined by object detection and identification using the YOLO (You only look once) neural network technique. The proposed technique can be easily developed and tested on a commercial scale in a real-world situation in the future. As a result, the proposed model outperforms the alternatives.