International. Manufacturer Hanwha introduced WiseDetector, a machine-learning-based feature that can "train cameras" of video to identify objects, based on models defined by the end user.
This new feature provides customized solutions based on circumstantial requirements, allowing security teams to efficiently manage any unique security or safety needs.
Some examples of objects that can be trained to be detected are: boxes that could be a hazard on the store floor, cones that obstruct roads, or signs that block aisles.
The flexibility of machine learning-based detection can also create opportunities for security teams to strengthen other measures, such as access control. For example, WiseDetector can also be trained to recognize open or closed doors, offering a visual alert that improves access control.
WiseDetector is compatible with the P Series of AI-powered cameras and does not require a license.
How does it work?
Training is done using the Device Manager. Users don't need to have high technical knowledge to get started. This makes it relatively easy to set up and further expands the possibilities of video analytics.
Users simply collect images of a selected object for the machine learning model to recognize. When using WiseDetector, you can use your camera's existing video analytics applications to trigger live events.
"WiseDetector is another tool that expands the use of video analytics. We are committed to helping our customers use video analytics because of the many benefits it offers to safety, operations, and personal protection. WiseDetector is one of the ways we are achieving this together with our state-of-the-art AI devices and deep learning algorithms, which continue to evolve and advance", said Pread Um (Suk Bong), Chief Product and Marketing Officer at Hanwha Vision.
