Sony Launches AI-Based Video Analytics Solution

Sony today announced its first Artificial Intelligence (AI) based Edge Analytics solution, the REA-C1000, which allows users to create video content in real time, without the need for specialized training, additional staff or equipment.

The REA-C1000 uses AI-based video analytics technology to analyze the input it receives from connected cameras and automatically extracts the object in focus to combine it with other images in real time on a GPU (Graphics Processor Unit). This unique technology using motion/face detection and color/shape recognition, effectively makes the REA-C1000 the powerful brain of any connected camera and AV setup, allowing education, government and corporate organizations to cost-effectively create professional content that keeps audiences engaged.

 

Still confused? Well watch this video and be blown away:

The REA-C1000, planned to be available in spring 2019, includes the following features:

  • Handwriting Extraction and Presenter Overlay: By optimizing parameters and processing the images received from the camera, the REA-C1000 can extract handwritten objects from black and white boards using Sony’s unique moving/unmoving object detection algorithm. This allows audiences to clearly see written content and diagrams, while simultaneously being able to see the gestures and expressions of the presenter. This function of the REA-C1000 is particularly well suited for lecture theaters or remote learning to keep students engaged, even if they aren’t physically in the same room as their teacher. Additionally, it helps all members of an audience to engage in a live presentation, in a large hall requiring sub-monitors.
  • Chroma Keyless CG Overlay: Based on Sony’s motion detection technology, the REA-C1000’s chroma keyless function can extract the presenter and overlay them onto any background without the need for a dedicated green screen or specialized training. This offers a simple, cost-effective chroma key solution to make content like corporate videos, interviews, webinars and e-learning materials much more appealing and engaging. This feature will be made available through a future software update later in 2019.
  • PTZ Auto Tracking: The REA-C1000 can accurately and smoothly track a presenter, ensuring they constantly stay in frame and in focus throughout their presentation. This feature offers users a cost-effective tracking solution in an education, corporate or conference setting, without having to invest in a camera operator.
  • Focus Area Cropping: Using this feature, an image from one camera can be simultaneously shown as two different output images. Users are able to get an overview image in 4K and a cropped image in HD. The cropped area is selectable to be static or dynamic to follow the speaker’s movement. This feature will be made available through a future software update later in 2019.
  • Close-up by Gesture: The REA-C1000 can detect and react to the gestures of audience members, showing both the whole image and zoomed image in real time. When an audience member stands up, the REA-C1000 can trigger the camera to electronically auto-zoom in on that person, which is particularly useful in educational environments to measure students’ reaction and incorporate presentation settings such as during a Q&A session.
See also  Sony Ships Edge Analytics AI Video Solution

Leveraging Sony’s expertise in image quality and their heritage in camera development, the REA-C1000 will support 4K/HD input and output, and will be able to connect directly to Sony’s PTZ cameras, including its range of XDCAM camcorders, which boast outstanding image quality and are widely used within the broadcast industry. Additionally, with HDMI network connection, the REA-C1000 can seamlessly integrate into various common AV setups involving either multiple displays, large screen projections with monitors or even live-streaming projects.

This will be on display at ISE 2019 in Sony’s stand 1.N20 and here are more details.

Check out video of the award winning Sony REA-C1000 Edge Analytics from ISE 2019 below: