Deep learning analytics minimize false alarms and provide valuable new insight for security and operations
June 24, 2020 By SP&T Staff
Hanwha Techwin America announced a new line of 4K AI cameras on June 24. Part of the Wisenet P series, the new AI-based cameras capture images at up to 4K resolution while including in-camera deep learning algorithms for advanced object detection, classification and error-free analytics. Utilizing object recognition versus motion detection all but eliminates false alarms while also providing valuable business and operations insight.
“Our new AI cameras have solid performance in both analytics and deep learning applications,” said Ray Cooke, vice-president – products, solutions, and integration, Hanwha Techwin America, in a prepared statement. “The included, license-free analytics detect and classify a range of objects including people, vehicles, license plates, and faces. This technology will provide more reliable edge based intelligence, and open new opportunities in security as well as business and operations intelligence.”
Attributes of the objects are also stored as metadata alongside the video information including:
- Colours of clothes for both top and bottom
- Clothing length for both top and bottom
- Wearing of glasses or not
- Wearing or carrying a bag
- Age group
- Vehicle types
- Vehicle colors
This metadata can be read by a VMS server and used in post-event forensic search to significantly reduce time spent investigating specific events. Wisenet P series AI cameras offer integration with Wisenet WAVE and other popular VMSs from Milestone and Genetec using Hanwha’s plugin.
As businesses re-open with new policies regarding social distancing and occupancy limits, it’s never been more important to accurately count customers and employees as they enter and exit the premises. The Wisenet P series AI cameras help to deliver the highest accuracy with people counting based on the camera’s AI object detection algorithm.
Reducing Server Bandwidth for Analytics
Wisenet P series AI cameras are equipped with a ‘BestShot’ feature which ensures that the image of classified objects is sent to a backend server. The full video image can be up to 4K resolution to see details of objects, along with tagged attributes metadata. Users have the option to set the image resolution to less than 4K for full video streaming or use BestShot to minimize bandwidth and storage requirements for server-based analytics.
Additional key features include:
- Digital auto-tracking: provides two simultaneous streams of video, enabling operators to see the camera’s full field of view, whilst simultaneously viewing a Full HD digital PTZ auto-tracked image of a person or vehicle
- Upgraded Business Intelligence: integration with Wisenet Retail Insight providing gender and age group counting
- 12V DC power supply (50mA max): provides power for external sensors including LEDs, PIR sensors, and glass break detectors, eliminating the need for an additional power supply
The new Wisenet P series AI cameras are available in the following configurations:
- PND-A9081RV – 4K AI dome camera with built-in IR illumination
- PND-A9081RF – 4K AI flush-mount AI dome camera with built-in IR illumination
- PNV-A9081R – 4K AI vandal-resistant dome camera with built-in IR illumination
- PNO-A9081R – 4K AI bullet camera with built-in IR illumination
- PNB-A9001 – 4K AI box camera
Print this page