Kinect-based motion capture is a process of using a Kinect sensor and complementary software to record movement. The Kinect technology was originally used for the mainstream game-playing market but is now used widely for the movie, sports therapy, robotic, and research industries. Kinect is powered by both hardware and Window’s Software Development Kit.
Capturing and displaying pictures and videos of human motion requires a high-end computer to work properly. All of the footage captured produces a large amount of data that has to be stored securely. Displaying visual information and 3D representations in real-time is demanding on the computer’s processor. To see Kinetisense’s recommended computer specifications click here.
The Kinect sensor is made up of three elements that work together to recognize and quantify human motion.
RGB video camera – This video camera aids in facial recognition and other detection features by identifying three color components: red, green and blue. Microsoft calls this an “RGB camera” referring to the color components it detects.
Depth sensor – An infrared projector and a monochrome CMOS (complementary metal-oxide semiconductor) sensor work together to “see” the person in 3D. This allows the user to capture rotation with precision.
Multi-array microphone – The microphone consists of an array of 4 microphone capsules. Each of the four channels processes sound in 16 bit audio and at a rate of 48 KHz.
The Windows Software Development Kit (SDK) is what makes the Kinect a cutting-edge device. The SDK includes the following features:
Sensor streams – The video and depth sensor cameras have a 1080-pixel resolution and run at 30 FPS (frames per second).
Skeletal tracking – The ability to detect and track 48 locations per person within the Kinect field of view, makes it the ideal tool for biomechanical analysis applications.
Advanced audio capabilities – Including: Audio processing capabilities include sophisticated acoustic noise suppression and echo cancellation, beam formation to identify the current sound source, and integration with the Windows speech recognition API.
© 2017 Kinetisense, Inc.