Qualcomm Bows Edge Computing IoT Platform to Make Connected Video Devices Smarter

Qualcomm wants to make the connected home more intelligent and efficient and has a new platform based on edge computing designed to make that happen, it blogged Wednesday. The chipmaker announced the first in a family of SoCs for the development of IoT smart devices. A home security camera that notifies a user every time it senses motion -- it gave as an example a Great Dane jumping on a sofa -- might be an entertaining use of a connected camera today but not very useful. More compelling is a camera pointed to the front door that’s able to differentiate between a son or daughter who has been locked out and a burglar, it said. In Qualcomm’s vision of the future, the camera could communicate with the door’s smart lock to allow entry to the child or notify the police if it senses a burglar. “This level of home security is possible, but it won’t happen overnight,” said Qualcomm. For such a camera to be truly effective, “it needs to be connected and intelligent enough to be able to process and analyze data in real time locally on the device, so it can recognize the things that matter and take immediate action,” it said. The new platform, anchored by the Qualcomm QCS605 and QCS603 SoCs, include advanced camera processing software, machine learning, computer vision software development kits and “proven connectivity and security technologies” designed for next-generation IoT devices, it said. Qualcomm’s Vision Intelligence Platform, combining powerful processing with AI and superior imaging, is applicable to products ranging from ovens to robotic vacuum cleaners and drones -- “any device that relies heavily on information that comes from a camera,” said the company. Rather than processing information in the cloud, which takes network resources and time, the camera has intelligence to respond based on “what it knows” vs. waiting for video data to be sent to the cloud for analysis and sent back, it said. The advantages of edge computing include faster processing, local control, better security and privacy -- and the use of less network bandwidth. Integrating this technology will “push the IoT ecosystem forward, as developers move away from the cloud and focus on the capabilities of the device,” Qualcomm said.