Nokia Introduces Real-time Visual Position And Object Detection

Nokia Introduces Real-time Visual Position And Object Detection To Enable AI Powered Applications For Worker Safety And Industrial Automation

  • Visual Position and Object Detection tracks industrial assets via camera video feeds, eliminating the need for tags.
  • Key for situational awareness, VPOD’s AI algorithms running on MX Grid’s micro-edges also identify object types, detects anomalies and run for example pose estimation, enabling worker safety use cases.
  • VPOD can leverage existing cameras making it highly scalable with limited bandwidth impact on connectivity as the video streams are processed near the camera.
Nokia announced Visual Position and Object Detection, a new MX Grid application that enhances industrial tracking and positioning and contextual awareness to enable Industry 4.0 applications and increase worker safety in industrial plants. Using Bell Labs’ patented technologies, VPOD traces industrial assets by using locally deployed AI algorithms that analyze real time camera feeds to deliver valuable insights into industrial operations to improve workplace conditions. Nokia also today announced MX Grid, enabling organizations to improve OT responsiveness and decision making by processing and analyzing data closest to the source.

Worker safety remains a high priority for industrial businesses. In 2021, the Eurostat revealed that there were 2.9 million non-fatal industrial accidents reported in the European Union, with 540,000 occurring in manufacturing and 260,000 in transportation and storage industries.

Engineered to detect and identify assets within defined spatial areas, VPOD improves worker safety and operational efficiency in industries including manufacturing, logistics, ports, and mining.

In complex industrial environments it is often difficult to equip machinery and tools with active tags and challenging for people to wear and maintain those units (e.g. battery change, faulty units, etc.). By using a real-time video data feed, VPOD eliminates the need to equip assets and people with powered devices, facilitating improved situational awareness.

VPOD provides another source of industrial contextual awareness data, which is made available through APIs, for example for use by third-party applications running on the MXIE on-premise edge compute platform. VPOD’s real-time output will also be utilized by Nokia MX Workmate, a gen-AI LLM based worker assistant, to enrich the contextual information it provides to workers.

For example, the solution’s AI based object, anomaly detection, and workers’ pose estimation, enables VPOD to detect a fallen worker. The information from the fall and the precise coordinate can then be leveraged by MX Workmate, to assist in organizing the response and rescue activities to improve worker safety.

Nokia VPOD complements other Nokia Tracking and Positioning solutions such as Bluetooth based HAIP, and third-party tracking and positioning solutions running on MXIE, such as HERE HD GNSS or Nordic ID. All video data is processed in real-time and image content analyzed within the customer’s closed network, ensuring compliance with privacy and security regulations. Facial recognition software is not used within the Nokia VPOD solution.

Stephan Litjens, Vice President of Enterprise Solutions at Nokia, said: “Real-time tracking and positioning technologies play a critical role in enhancing situational awareness, needed for powering an array of intelligent applications ranging from worker safety to improved asset utilization. Nokia Visual Position and Object Detection running on MX Grid is the first solution to make this possible at scale through patented algorithms and full lifecycle management, enabling the solution to be updated as new capabilities emerge. Privacy and security are key concerns for customers and with data confined and processed at the MX Grid micro and MXIE edge, Visual Position and Object Detection also ensures data privacy can be always maintained.”

Source: Nokia media announcement

Latest Updates

Subscribe to our YouTube Channel