In addition to capturing superb quality images, the new feature-rich cameras from the Hanwha Techwin Premium range are equipped with deep learning video analytics which offer a high level of detection accuracy, whilst minimising false alarms.
Control room efficiency
The license-free deep learning video analytics simultaneously detects and classifies various object types, including people, vehicles, faces and license plates and is supported by Wisenet AI algorithms unique to Hanwha Techwin which are able to identify the attributes of objects or people, such as their age group, their gender or the colour of the clothing a person is wearing.
The attributes are saved as metadata alongside the images captured by the new Wisenet P AI cameras, enabling users to quickly search for specific objects or incidents. The algorithms are even able to recognise if a person is wearing glasses or is holding a bag.
To further increase operator efficiency, as well as minimise network bandwidth and data storage requirements, the new Wisenet P AI cameras have a BestShot feature which, as its name suggests, is able to select the best images which have been captured of a person or object, and only send these together with the associated metadata, to a storage server.
Operators are able to take advantage of VMS from leading software developers such as Milestone, as well as Wisenet WAVE and Wisenet SSM, to forensically search for specific objects or people, by filtering the recorded metadata.
False alarm reduction
The analytics can be configured to ignore video noise, waving trees, moving clouds and animals, all of which might normally be the cause of false alarms when standard motion detection technology or sensors are being used to detect activity. This ability to minimise time-wasting and costly false alarms means control room operators and security personnel are able to focus on responding to real incidents and emergencies.
People counting to help businesses to reopen
At some point in the future, when the number of people being tested positive for COVID-19 begins to reduce, thought will no doubt be given as to how businesses will be able to safely reopen. Inevitably, social distancing rules will have to remain in place, and this is likely to mean only a specified number of people will be allowed to be in a controlled area at any one time.
With this in mind, the Wisenet AI algorithms built into the new Wisenet P 4K AI cameras can be utilised to accurately count the number of people entering and leaving premises. The data can be displayed to provide managers with information on the number of people present.
The new Wisenet P AI cameras are likely to be of particular interest to the retail sector as they have been integrated with Wisenet Retail Insight (v2.0), which enables retailers to gain a greater understanding of customer behaviour and buying patterns.
The Wisenet Retail Insight business intelligence solution utilises people counting, heat mapping and queue management applications to display statistical analytics on a centralised dashboard, along with other practical information such as weather reports. With the help of Wisenet AI algorithms, Retail Insight is also able to display the age and gender of store visitors, allowing retailers to granularly analyse customer demographics.
Other key features of the new Wisenet P AI cameras include:
- Digital auto-tracking: The cameras are able to transmit two streams of video, providing the option for operators to see a camera’s full field of view, whilst at the same time using a digital PTZ auto-tracking feature while viewing Full HD images to track the movements of a person or vehicle.
- Wide Dynamic Range (WDR): which performs at up to 120dB to produce clear images from scenes containing a challenging mix of bright and dark areas which normally results in overexposed or underexposed images.
- DC output: A 12V DC power supply with maximum 50mA provides sufficient power to support external devices, including LEDs, PIR sensors and glass break detectors, eliminating the need to install separate power supplies for each of them.
- Alarm in/out ports: Connected devices such as LEDs can be activated when a camera detects and classifies an object or person.
- 2 SD card slots: allow video or data to be stored at the edge should there be disruption to the network. Video evidence, which might have been potentially lost, can be retrieved when the network connection has been restored.