XJERA’s video analytics algorithms are able to deliver an excellent > 95% accuracy for people detection, intrusion, and line crossing, and a > 85% accuracy for attribute detection.
Assuming a fixed target for accuracy, basic video analytics such as detection, intrusion, and line crossing, GPU-accelerated analytics delivers a significant 31X higher performance compared to the same algorithm run only on the CPU. This gap widens even further to a massive 111X when complex video analytics such as attribute detection is executed on the same video stream.
Find out who has been talking about us
The ease of scalability and reconfigurability of the Tesla P4, with the added benefit of NVIDIA’s GPU support of a multitude of Deep Learning frameworks, gives Xjera Labs the flexibility that we need to not only differentiate ourself from the competition, but also the flexibility and possibility to do more with our Intelligent Video Analytic A.I.
Video analytics is the perfect demonstration of the value of edge computing, as processing video near the camera eliminates the need to transfer large amounts of video data into the data center or cloud, reduces bandwidth costs, greatly accelerates reaction time, and lowers risk of corruption or espionage.
Huawei has signed individual MoUs with five enterprises, committing the parties to joint development of public safety solutions at Huawei’s Singapore OpenLab. In the area of video cloud, Huawei has established new partnerships with Agent Video Intelligence (Agent Vi), IPSOTEK, and Xjera Labs.
"If the police want to find someone, then they want a very fast response. With our system, we are constantly doing facial indexing in real-time on CCTV camera footage. The footage is uploaded to the cloud by our customers and we process the data," Xjera Labs' founder and CTO Ethan Chu told IBTimesUK at the Innovfest Unbound 2017 event in Singapore.