Hanwha Techwin introduces 4K Wisenet P Artificial Intelligence cameras
21 May 2020
IN ADDITION to capturing "superb quality" images, the new feature-rich Wisenet P ultra-HD 4K Artificial Intelligence (AI) cameras from Hanwha Techwin are equipped with deep learning video analytics which offer a high level of detection accuracy, while also minimising false alarms.
The license-free deep learning video analytics simultaneously detect and classify various object types, including people, vehicles, faces and license plates. This 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 Wisenet P AI cameras, enabling end users to quickly search for specific objects or incidents. The algorithms are even able to recognise if an individual is wearing glasses or holding a bag.
To further increase operator efficiency, as well as minimise network bandwidth and data storage requirements, the Wisenet P AI cameras have a BestShot feature which, as its name suggests, is able to select the best images captured of a person or object, and only send these together with the associated metadata to a designated storage server.
Operators are able to take advantage of VMS from software developers such as Genetec and Milestone, as well as Wisenet WAVE and Wisenet SSM, in order to forensically search for specific objects or people by filtering the recorded metadata.
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-laden and costly false alarms means that Control Room operators and security personnel are able to focus on responding to real incidents and emergencies.
People counting: helping businesses to re-open
At some point in the future, when the number of people being tested positive for COVID-19 begins to reduce sufficiently, thought will no doubt be given as to how businesses will be able to safely re-open. Inevitably, social distancing rules will have to remain in place, and this is likely to mean that only a specified number of individuals will be allowed to be in a controlled area at any one time.
With this in mind, the Wisenet AI algorithms built into the Wisenet P 4K AI cameras can be used to accurately count the number of people entering and leaving a given premises. The data can be displayed to provide managers with information on the number of people present.
The 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 uses 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, thereby allowing retailers to granularly analyse customer demographics.
Additional key features
*Digital auto-tracking: The cameras are able to transmit two streams of video, allowing operators to see a camera’s full field of view, while 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 which performs at up to 120 dB to produce clear images from scenes containing a challenging mix of bright and dark areas and which normally results in overexposed or underexposed images
*DC output: A 12 V DC power supply with maximum 50 mA provides sufficient power to support external devices, including LEDs, PIR sensors and glass break detectors, thus 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
*Two 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.
*Wisenet PNB-A9001: 4K AI box camera
*Wisenet PNO-A9081R: 4K AI bullet camera
*Wisenet PNV-A9081R: 4K AI vandal-resistant dome camera with built-in IR illumination
*Wisenet PND-A9081RF: 4K AI flush-mount dome camera with built-in IR illumination.
*Wisenet PND-A9081RV: 4K AI dome camera with built-in IR illumination.
With the exception of the Wisenet PNB-A9001, all models are supplied with a motorised varifocal lens which facilitates auto-tracking and allows operators to zoom into a camera’s field of view to see close up detail of any activity and functionality.
The dome cameras have a four-part magnetic modular design which makes them extremely easy to install. The ability to prefigure IP network settings without the need to remove the camera modules from their packaging also reduces the time an engineer has to spend on site and/or cause disruption.
“We are proud of all the new innovative products and solutions we have launched over recent months, but this new camera range is a particularly good example of how Hanwha Techwin is continuing its 30-year journey of innovation and adding real value to video surveillance solutions,” enthused Uri Guterman, head of product and marketing for Hanwha Techwin Europe. “By harnessing the power of Deep Learning AI, we are providing security personnel with a powerful and accurate tool to help them stay one step ahead of intruders. We are also able to provide businesses with key information which could help them to be more productive.”