How AI and computer vision can help retailers to compete [Q&A]

The rise of online retail coupled with the pandemic have brought about some unprecedented changes to the retail landscape in recent years.

But as consumers now start to venture back into stores, how can retailers make use of technology to effectively compete with their online counterparts and with other brick-and-mortar businesses?

We spoke to Rohan Sanil, CEO and co-founder of Deep North to discuss how AI and computer vision can empower retailers to gain data-rich insights so they can best meet shoppers' needs and run their stores more efficiently.

BN: What is the difference between sensor analytics and AI and computer vision?

RS: Sensor analytics are based on the use of physical sensor devices in-store. These work by converting stimuli such as movement or sound into electrical signals which are converted to code and then processed by computers.

Computer vision is a field of artificial intelligence (AI) that focuses on replicating the capacities of human vision. As such, computer vision takes sensor analytics a step further, as anything one's eye can see can be analyzed. It trains computers to interpret and understand the visual world the same way humans do. For example, sensors may be able to pick up on whether a person has walked into a store and into an aisle. However, computer vision can pick up on that in addition to whether there's a dangerous spill in the aisle that could cause harm to a shopper.

BN: Which industries can benefit from AI and computer vision?

RS: AI and computer vision can empower businesses across a variety of industries to gain data-rich insights to better use their environments. For example, they can positively impact retail, quick service restaurants, shopping centers, transportation, commercial real estate, manufacturing and warehouses. AI and computer vision derive meaningful data from videos, digital images, and visual inputs to not only help the consumer have a memorable experience, but also to help the business maximize its profits.

BN: How can the technology be used in these industries?

RS: AI and computer vision enable organizations to digitize their physical environments. Businesses are facing extreme competitive pressures, and without proper data to understand behavior on their physical properties, they are left with very little visibility and limited information to make important decisions.

Across all of these industries, AI and computer vision can empower businesses to address a variety of challenges, including:

• Limited visibility into in-location and back-of-house operations
• Lack of insight into customer behavior and journey
• Inadequate data for labor planning and allocation
• Lack of real time insights for decision making

Specifically, AI and computer vision can enable businesses to understand things like:

1. Footfall analytics. With these technologies, organizations are able to determine metrics like the number of people walking into and out of a business and the total number of people in a business at a moment in time.
2. Customer demographics and repeat visitors. AI and computer vision can enable businesses to determine characteristics like customer age range, gender and the people who made more than one trip to the location on a single day.
3. Customer journey. With this functionality, businesses can understand heatmaps/the number of entrances into a zone. They can also determine the length of time spent in the business as well as length of time spent in a specific zone.
4. Queue management at checkout. AI and computer vision provide clarity on the number of people waiting in line for checkout and the average wait time spent in queue before reaching checkout.
5. On-site analytics. The technologies provide the ability for businesses to understand shelf engagement, including the number of touch gestures made towards shelved items. It also delivers POS transaction time and conversion details. In addition, they can provide businesses with insight into the dominant customer path, including zone-to-zone traffic patterns from entry to exit.

BN: Can AI and computer vision also be used to enhance security? If so, how?

RS: They can absolutely be used to bolster security efforts. They can enable businesses to create safer work environments, detect safety breaches, monitor compliance, and action real time safety and accident alerts. Humans have limitations and cannot monitor everything constantly 24/7; however, with the power of AI and computer vision it's possible. They can detect and prevent malicious behavior from occurring, which creates safety for customers, employees, and businesses. For example:

For airports and airlines: AI and computer vision can create safer work environments and traveler experiences by detecting safety breaches, monitoring compliance, identifying equipment failure, and actioning real time safety and accident alerts.

For commercial real estate: The technologies can create safer living and working environments for occupants and a business's teams by going beyond ineffective security camera monitoring to next stage technology by digitizing video from across properties, detecting behavior, and creating real time alerts that can be addressed quickly and effectively.

For manufacturing and warehouses: AI and computer vision create safer workplaces by identifying equipment failure, detecting safety breaches, monitoring compliance, and delivering real time incident alerts.

For retail: The technologies can reduce fraud at the checkout and enhance loss prevention.

BN: Is there any concern around data privacy when it comes to using these technologies?

RS: Speaking specifically about Deep North, we take privacy extremely seriously. Our business was developed to govern and preserve the integrity of every individual by the highest possible standards of anonymization. Deep North is GDPR and CCPA compliant, and the company does not store, save, or transfer any video images outside of the location (e.g. a store). All processing is done inside the location and purged.

Customers own 100 percent of their data when working with us. Data is processed and secured on site (during on-premises deployment) and in the cloud (during cloud deployments). Data is processed and securely sent as anonymized metadata to the cloud using industry accepted secure methods. Our business never has access to PII or stores customer data during this process and ensures that all data objects are securely stored and transferred.

Image credit: Sonpichit Salangsing / Shutterstock