17643822. FILTERED IMAGES FOR 3D BODY TRACKING simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
FILTERED IMAGES FOR 3D BODY TRACKING
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Yasunori Yamada of Kawaguchi-shi (JP)
Kaoru Shinkawa of Hachioji-shi (JP)
Masatomo Kobayashi of Tokyo (JP)
FILTERED IMAGES FOR 3D BODY TRACKING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17643822 titled 'FILTERED IMAGES FOR 3D BODY TRACKING
Simplified Explanation
The present disclosure is about a system that processes infrared (IR) images and depth maps to generate 2D and 3D poses of a subject. Here is a simplified explanation of the abstract:
- The system receives an IR image and a depth map associated with the image.
- It applies one or more filters to the IR image based on a set of parameters.
- Using the filtered IR image, it generates a 2D pose estimation for the subject.
- The system then correlates the 2D pose with the depth map to generate a 3D pose estimation.
Potential applications of this technology:
- Motion tracking and analysis in sports and fitness training.
- Gesture recognition for human-computer interaction.
- Biometric identification and security systems.
- Virtual reality and augmented reality applications.
- Healthcare and rehabilitation monitoring.
Problems solved by this technology:
- Accurate and real-time estimation of human poses in both 2D and 3D.
- Overcoming limitations of traditional RGB-based pose estimation methods.
- Handling occlusions and low-light conditions more effectively.
- Enabling more immersive and interactive experiences in various domains.
Benefits of this technology:
- Improved accuracy and reliability in pose estimation.
- Enhanced performance in challenging environments.
- Compatibility with existing IR imaging systems.
- Potential for real-time applications.
- Versatility in different industries and use cases.
Original Abstract Submitted
Aspects of the present disclosure relate to a system receiving an infrared (IR) image, receiving a depth map associated with the IR image, applying one or more filters to the IR image based on a set of parameters, generating a 2D pose for a subject based on the filtered IR image, and generating a 3D pose by correlating the 2D pose to the depth map.