Deep Learning Holds Promise for Better Video Analytics
Predicting that “deep learning” technology will cause a “revolution in video,” global research firm IHS Markit delves into deep learning video analytics in a new Security and Business Intelligence Report.
Deep learning goes far beyond previous video analytics technology in its capacity for accuracy and power. Deep learning algorithms improve accuracy to as high as 99.9 percent, according to IHS Markit, for better detection of security breaches. It can also reduce time spent looking for relevant video footage by processing and analyzing larger volumes of video data in shorter time frames than conventional technology.
Deep learning algorithms mean security monitoring benefits from more accurate detection. Security professionals can now identify faces in large crowds using upgraded facial recognition technology. In the case of a terrorist attack in a crowded area, this feature alone could allow “law enforcement to track suspects with far greater speed and efficiency,” according to IHS.
Hikvision’s new DeepInMind NVR uses deep learning technology algorithms to rapidly process data and to isolate human subjects. This reduces false alarms caused by non-human objects such as animals or moving vehicles. The DeepInMind NVR features H.265+ compressional technology, 12MP camera input, 4K HDMI output and capacity for up to 32 IP camera inputs. Visit ASIS booth #3703 to see Hikvision’s new DeepInMind NVR.