Skip to main content

Hikvision adds AI to DeepinView cameras

By Adam Hill July 22, 2020 Read time: 2 mins
In deep: users can change the algorithm as installation needs change (© Hikvision)

Hikvision has added to its DeepinView camera line with what it calls the Dedicated subseries.

The company says this loads a batch of artificial intelligence-powered deep learning algorithms into each unit, which are of use in two distinct categories.

The first is vehicle analysis, where cameras combine automatic number plate recognition with vehicle attribute recognition - including make, colour and direction of movement. 

Typical installations would be on city streets and at the entrances of car parks and buildings.  

Models in the second category have six switchable deep learning algorithms in one camera housing, including facial recognition, face counting and queue management. This means users can enable an algorithm manually for dedicated use, then later switch it as needed. 

“Embedding switchable algorithms is a significant step for Hikvision to take in its AI product development," says Frank Zhang, president of the International Product and Solution Centre at Hikvision. 

"In a world of ever-changing technologies and functionalities, this approach creates great value for end users to try new technologies to ensure security, as well as to implement business intelligence and other applications. The benefits of our new offerings are numerous including reduced costs, improved efficiency, and speedy and effective incident response.” 

Hikvision says the cameras offer HD clarity, day and night, as they are equipped with the manufacturer's DarkFighter and LightFighter technologies. 

In Smooth Streaming mode there is a "high-quality live feed", the firm insists.

The Dedicated DeepinView cameras are available in 2, 4, 8, and 12 MP resolutions.

For more information on companies in this article

Related Content

  • Adopting universal technology platforms for tolling
    July 16, 2012
    Dave Marples of Technolution argues that the continuing development of tolling-specific onboard equipment is leading us up a blind alley. We should, he says, be looking to realise universal platforms with universal application. The near-future automobile contains information systems of a sophistication to rival a jet airliner of only a few years ago, yet is 'piloted' by a considerably less well-trained individual of highly variable mental and physical capacity, and operated in a hostile, unpredictable and p
  • Intersection monitoring from video using 3D reconstruction
    March 9, 2016
    Researchers Yuting Yang, Camillo Taylor and Daniel Lee have developed a system to turn surveillance cameras into traffic counters. Traffic information can be collected from existing inexpensive roadside cameras but extracting it often entails manual work or costly commercial software. Against this background the Delaware Valley Regional Planning Commission (DVRPC) was looking for an efficient and user-friendly solution to extract traffic information from videos captured from road intersections.
  • Star Systems International flies high with Falcon
    May 6, 2025
    Dual-frequency transponder has UHF and NFC capabilities
  • Where is tolling tech taking us?
    September 25, 2019
    From DSRC and RFID to GNSS or smartphones – which technology is ‘best’ for tolls, charging and pricing schemes? In the first of two articles, Josef Czako examines the options