20/20 Vision Hack

Manufacturers leverage powerful, real-time data from the IoT to increase uptime, perform preventative maintenance, enhance productivity, improve mobile accessibility, and a host of other benefits. It’s clear that manufacturers need to embrace IoT and utilise vision as a sensor. Vision as a sensor can remove some of the barriers of adoption due to the minimal requirement of existing system integration. Sensors and industrial cameras have opened up new perspectives in the automation of the production process. Based on your experience and understanding of challenges in manufacturing, what can you see as a vision solution?

For example, but not limited to:

• Measurement - measuring/testing specific product dimensions
• Product verification - checking the correct position of all parts on the assembly
• Product identification - barcode and 2D code reading, product type determination based on shape, size, and other characteristics
• Product sorting - sorting packages by color, etc.
• Product component and assembly - cap closure/seal, position, label placement, print quality, more
• Navigation system - determining the position of the product on the assembly line and using its coordinates for IoT devices
• Quality control - ensuring that faults are identified and noted to create an action/reaction
• Anomaly detection - scan object details and send a signal if something is amiss

Please refer to the details to be submitted in the Submission Guidelines Tab.

Distribution businesses have requirements for asset management, business process efficiencies and new business models. Existing problems, like congestion in cargo yards, perishable cargo not being properly tended to or vital machinery performing sub-optimally, can be identified and alleviated before they escalate. How do you see vision AI play a key part in mitigating supply chain disruptions?

For example, but not limited to:

• Warehouse management – track and trace assets in real-time
• Inventory check – ensure package contents are correct prior to distribution
• Security and transparency - monitor asset movement within and around the facility to prevent theft or misplaced goods
• Congestion on cargo yards - provide visual guidance for drop-off and placement of cargo to ensure smooth traffic flow and prevent bottlenecks
• Perishable cargo risks - identify and monitor specific types of cargo to ensure quick processing and prevent spoilage
• Machinery performance - monitor machine health for proactive maintenance and downtime prevention

Please refer to the details to be submitted in the Submission Guidelines Tab.

Thousands of workers die in industrial accidents each year in the U.S., and more than 100,000 suffer from non-fatal work-related injuries. Workers, employers and insurance companies collectively face billions of dollars of direct and indirect costs due to industrial accidents, and individuals suffer unnecessarily. How do you see vision AI helping to minimise these risks?

For example, but not limited to:

• Fall detection - enable identification and notification system when workers experience injury or equipment is damaged
• Proximity warnings - provide visual and audio alerts when workers enter a hazardous area
• Safety zones – enable instant alarm and system reaction when people are identified in the wrong place at the wrong time
• Personal protective Equipment (PPE) detection – ensure people are wearing the correct equipment for hazardous environments
• Security – automated premise surveillance

Please refer to the details to be submitted in the Submission Guidelines Tab.

AI is powering the fourth industrial revolution and is increasingly being incorporated into key strategies to protect work forces and drive efficiencies. And AI is also being used to help solve some of the greatest challenges of our time, including climate change and pollution. The energy sector is adopting the use of computer vision to enable smarter, automated and more effective sensor data collection - data that is actionable and available where and when it needs to.

For example, but not limited to:

• Wind energy producers — identifying maintenance needs such as dirt accumulated on wind turbines, dead insects and cracks in foundation or tower
• Mines — automatic detection of anomalies in mines (e.g., leaks, fires, smoke) or production blocks
• Production — automatic machine inspection and anomaly detection
• Transport equipment managers — identify parts needing repair to shorten time that vehicle is out of service
• Network service providers — automatically detect the need for network maintenance

Please refer to the details to be submitted in the Submission Guidelines Tab.