Authors: Adrian Boguszewski, AI Software Evangelist and Anisha Udayakumar, AI Software Evangelist
In today’s world, we want everything to be fast, but it seems like we cannot escape the bottleneck of retail store checkout lines. Whether you opt for self-checkout or rely on manual checkout lines, there always seems to be a wait — which can be frustrating when you are in a rush and trying to get in and out of the store. Even a few extra seconds of wait time can have a huge impact on customer satisfaction, which, in turn, impacts a store’s business and reputation. Customers will often abandon their items if they experience a long wait time or even consider frequenting a competing store where they experience less of a hassle.
But from the store’s perspective, it can be quite challenging to predict optimal staging levels, determine the appropriate quantities of food and supplies to order, and manage food waste. They need access to queue management data to effectively make changes, improve accuracy, save costs, and ensure a seamless customer experience.
Enter Intelligent Queue Management
Fortunately, recent advancements in artificial intelligence (AI) have opened doors to solutions that address this very situation. For instance, applying AI models on existing store cameras can provide real-time analytics into what’s happening throughout the store. This means you can identify a customer in need within seconds and immediately send store assistance or be alerted to any low stock items and efficiently restock in a timely manner.
Integrating AI into business operations is becoming more mainstream, with cutting-edge AI toolkits like the OpenVINO™ toolkit, giving developers the means to develop, deploy and scale AI solutions that meet business needs effectively.
Building a Scalable Queue Management System
Going even further, OpenVINO provides several resources and edge AI reference kits that can walk developers through building AI solutions capable of real-time detection and object location within images and video and more. Our intelligent queue management reference kit, for example, leverages the power of OpenVINO and the advanced object detection algorithm YOLOv8 to develop an AI solution that gives businesses real-time insight into their checkout lanes. And when you combine these AI workloads with Intel hardware, you get the performance, scalability, and efficiency required for these complex AI workloads.
Developers looking to build an intelligent queue management app can follow our step-by-step recipe. As an outcome, you will have developed an AI model that can be trained with a threshold limit so when there’s a certain number of customers within a store queue, store managers are quickly notified and can take actions accordingly.
This application was developed using OpenVINO 2023,0, allowing us to leverage the new quantitation feature, a core optimization technique that enhances model efficiency and deployment readiness. This is key to any business solution because it not only helps us gain faster performance results but also allows developers to scale their solution from a small retail store up to a big shopping mall. OpenVINO gives developers the tools to write code once and deploy it on different hardware such as CPUs and GPUs without having to re-create the entire solution.
The Next Era of Intelligent Retail
Queue management is just one example of what’s possible with AI in the retail space today. There are also opportunities to use AI to understand foot traffic within the store so you can improve aspects of operations like sale metrics and product placement or detect spills that need to be cleaned up quickly.
Going forward, AI is expected to provide even more solutions that improve customer satisfaction. Eventually, the entire supply chain from store to warehouse to transportation will easily be connected. We can even see the ability of being able to walk into a store, grab your goods, and instantly be charged when you walk out the door without ever having to go through a checkout process. In the past, this might have sounded like an impossible dream, but today AI is making it possible.
We encourage you to explore the potential of AI and learn about other opportunities available. Beyond retail, object detection can be used in industries like healthcare to safely monitor patients and medical devices or ensure worker safety in manufacturing settings.
You don’t have to do it alone either. If you have any questions or anything you would like to share your experience, join our discussion on GitHub. Since OpenVINO is part of the open-source community, it gives developers a place where they can not only get help but also be a part of the AI journey.
To learn more about developing with OpenVINO, check out the OpenVINO documentation. We look forward to seeing what you come up with next!
Notices & Disclaimers
Intel technologies may require enabled hardware, software, or service activation.
No product or component can be absolutely secure.
Your costs and results may vary.
Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.
Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.
No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.
© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.
