The problem Smart Automation. solves

AI-Powered Video Analytics
The power of computer vision on the edge brings a whole new dimension to video analytics. Shopping malls, convenience stores, restaurants, and brick-and-mortar stores can leverage object detection applications to detect people and store items. This helps them better understand shopper behavior and improve operations.
Contactless Checkout
Completely frictionless checkout systems are made possible with object detection. Through sensors and cameras powered by computer vision, shoppers simply pick items off the shelf and a 'virtual' shopping cart is created for that person with AI.
Foot Traffic Analysis
Object detection is a powerful tool for tracking activity inside and outside a store. CV applications that utilize tracking and counting can monitor and tally how many people enter and exit a store.
Productivity Improvement
Computer vision can boost productivity and efficiency, improving the bottom line. Object detection monitors workers in factories, warehouses, production facilities, and construction sites, providing valuable data on their work activities.

Challenges we ran into

The ultimate purpose of object detection is to locate important items, draw rectangular bounding boxes around them, and determine the class of each item discovered. Applications of object detection arise in many different fields including detecting pedestrians for self-driving cars, monitoring agricultural crops, and even real-time ball tracking for sports. Researchers have dedicated a substantial amount of work towards this goal over the years: from Viola and Jones’s facial detection algorithm published in 2001 to RetinaNet, a fast, highly accurate one-state detection framework released in 2017. The introduction of CNNs marks a pivotal moment in object detection history, as nearly all modern systems use CNNs in some form. That said, the remainder of this post will focus on deep learning solutions for object detection, though similar challenges confront other approaches as well.

1. Dual priorities: object classification and localization
2. Speed for real-time detection
3. Multiple spatial scales and aspect ratios
4. Limited data