Intel today announced the launch of OpenVINO or Open Visual Inference & Neural Network Optimization, a toolkit for the quick deployment of computer vision for edge computing in cameras and IoT devices.
OpenVINO will be compatible with popular open source frameworks like Caffe and TensorFlow and will work with Intel’s traditional CPUs, or chips specially made for AI inference — like the field programmable gate array (FPGA) chips and Movidius vision processing unit (VPU) that launched into production earlier this year.
The news comes a week after Microsoft announced plans to create a computer vision developer kit for edge computing with Qualcomm that uses Azure Machine Learning services, Qualcomm’s Vision Intelligence Platform, and Qualcomm’s AI Engine.
“Processing high-quality video requires the ability to rapidly analyze vast streams of data near the edge and respond in real time, moving only relevant insights to the cloud asynchronously,” Intel VP Tom Lantzsch said in a blog post. “The OpenVINO toolkit is designed to fast-track development of high-performance computer vision and deep learning inference applications at the edge.”
OpenVINO is being used by companies like GE Healthcare for medical imaging, Dahua for smart city solutions, and others like Amazon Web Services and Honeywell, according to Intel.
OpenVINO competes with a number of computer vision services from companies like AWS, Google, Microsoft, and Clarifai.
More AI news may be on the way from Intel as the company hosts a conference for developers using artificial intelligence later this month in San Francisco.