Feature
Computer vision is an in-demand artificial intelligence (AI) technology due to its many industrial applications, from manufacturing and retail floors to health care. Globally, the computer vision market is projected to nearly triple in size from $23.42 billion in 2025 to $63.48 billion in 2030, with a compound annual growth rate of 22.1%, according to a report by MarketsandMarkets. Here, we look at various use cases of computer vision technology.
Table of Contents
- Cashier-Less Shopping
- Retail Shrinkage
- Bin Picking
- Warehouse Picking
- Quality Inspections
- Welding
- Fall Detection
- Player Safety
Cashier-Less Shopping
Both consumers and retailers seek a frictionless and seamless shopping experience, not only online but also in physical stores. With the checkout line being a chokepoint at stores, computer vision can remove this bottleneck.
At Amazon Go stores, the Just Walk Out application uses cameras, weight sensors and a combination of AI technologies, including computer vision, to enable shoppers in stores to buy food, beverages and merchandise without having to wait in a checkout line or stop at a cashier, according to Amazon. The Just Walk Out technology uses generative AI and machine learning (ML) to figure out “who took what.”
The latest iteration of the technology offers increased accuracy in complex shopping scenarios with variables such as camera obstructions, lighting conditions and the behavior of other shoppers.
Retail Shrinkage
Shrinkage is the term that the retail industry uses to describe the difference between recorded inventory and actual stock. The shrinkage is due to a mix of employee theft, shoplifting and breakage.
To reduce shrinkage, retailers can employ computer vision systems to detect theft. For example, Everseen’s Visual AI system processes 300 years of video daily, using computer vision and AI to detect potential shrink-related issues at self-checkouts and staffed lanes and identify anomalies, such as unscanned items and product switching. The system then prompts shoppers and store workers to correct the issue.
Related Article: 5 AI Case Studies in Retail
Bin Picking
Robots are much more efficient than humans at bin picking, which is the process of identifying individual objects in a bin, picking up an item and placing the item on a conveyor belt or mobile cart to advance production.
The first bin-picking robots worked with items that were homogeneous. Now, smart bin picking uses 3D vision, AI and software to safely handle a large variety of object shapes, a wider range of light reflection and with the appropriate end-of-arm-tooling, objects constructed from more delicate materials.
The AI-based vision systems can also handle random bin picking — where the contents of each bin might vary widely from the contents of the previous bin.
Warehouse Picking
Picking robots in warehouses can take completed items and place them for packing.
For example, Pickommerce recently introduced PickoBot, which is designed for the apparel, retail, e-commerce, pharmaceutical, agricultural and spare parts industries.
The robot’s computer vision system powered by machine learning enables the intelligent packaging of objects of different sizes, weights and textures. PickoBot features multiple gripping methods in a single station, including vacuum, finger-based and patented adhesive-based end effectors. The robot also uses an AI-driven decision-making algorithm that selects the optimal gripper and grasp configuration for each item.
Related Article: 5 AI Case Studies in Robotics
Quality Inspections
Humans and machine vision systems are conducting many of the quality inspections today, and both systems are subject to human inaccuracies.
Computer vision, on the other hand, can be much more accurate and is a growing technology in the field. For instance, the AI quality inspection market, including vision technologies, is expected to grow at a compound annual growth rate of 20.53% from 2024 through 2029, increasing to $70.74 billion from $27.808 billion, according to a report by Research And Markets.
“AI-owned applications that make quality checks are becoming more common in the semiconductor industry as well as in medicine, clothing production, car-making industries and others because of their precision and ability to save time,” the report says.
Related Article: 5 AI Case Studies in Manufacturing
Welding
Faced with a welder shortage, manufacturers and companies in other industries have turned to robots to help fill the gap.
Computer vision can help improve the quality of automated welds. For example, Novarc recently introduced NovaAI, a real-time vision processing system that tries to improve welding based on data collection and model enhancement to fully automate the pipe welding process.
“We have developed the intelligence to fully automate the welding process,” said Soroush Karimzadeh, CEO of Novarc. “This is an accomplishment that has resulted from years of data collected through machine learning.”
Fall Detection
Baby Boomers are moving into their senior years, and one of the health challenges they can face is maintaining their balance due to weakening muscles and other aging-related issues.
To help prevent falls, Caregility launched a fall risk-detection capability in its iObserver solution, which uses proprietary AI and computer vision to analyze visual information, detect fall risks and alert caregivers. The Caregility platform enables AI technology to run entirely on telehealth edge devices in a patient’s room.
The platform is designed is designed to be open and adaptable to allow the company to develop “native AI capabilities when possible while also evaluating other third-party solutions to determine if they can add value to caregivers' workflows,” said Kedar Ganta, chief product and engineering officer, Caregility.
Related Article: 5 AI Case Studies in Health Care
Webinar
Nov
6
Fix the Content Bottleneck: Build a Better WebOps Strategy
Content stalled? Dev overloaded? You’re not the only one. Learn how streamlined WebOps bridges the publishing gap.
Register
Webinar
Nov
20
How to Build a Solid Knowledge Foundation for AI Success
See how leading brands keep their AI honest, compliant and actually helpful.
Register
Webinar
Dec
2
From Manual to Magical: How AI Transforms CX Teams
Learn how to replace manual support processes with automation that actually delivers.
Register
Webinar
On demand
Beyond Storage: Smarter Content, Bigger Impact with DAM + AI
Discover how the DAM + AI duo makes content smarter, stronger and more accessible.
Watch Now
Webinar
On demand
Agentic AI Playbook: Real-World Customer Service Use Cases You Can Deploy Now
Boost self-service by 30% and slash call volume by 63% with agentic AI.
Watch Now
Webinar
On demand
CMS Briefing: A Live Look at What’s Next in AI-Driven Platforms
Learn how leading organizations are using AI‑driven tools to publish faster, personalize smarter and stay secure.
Watch Now
Player Safety
To enhance player safety, the National Football League (NFL) uses the Digital Athlete platform, a joint effort between the NFL and Amazon’s AWS.
The Digital Athlete uses AI, computer vision and other technology to build a complete view of players' experiences to help NFL teams to understand what individual players need to stay healthy, recover quickly and perform their best. The technology is used by all teams to help prevent injuries.
Using ML techniques, the AI is taught to use computer vision to see visual information from game footage. For example, to help track head impacts, the Digital Athlete's AI was taught to identify helmets by the repeated ingestion of images of helmets from all angles.
