Company Filing History:
Years Active: 2025
Title: Innovations by Canjun Yang
Introduction
Canjun Yang is a notable inventor based in Hangzhou, China. He has made significant contributions to the field of robotics and human posture estimation, holding a total of 3 patents. His work focuses on enhancing the accuracy and efficiency of motion estimation and robotic systems.
Latest Patents
One of Canjun Yang's latest patents is titled "Joint motion estimation based method for estimating continuous human postures." This invention discloses a key joint motion estimation method that utilizes a motion estimation block matching algorithm for human key joint tracking. The method aims to provide continuous human posture results, which are further refined using a deep neural network-based human posture estimator. This innovative approach allows for the estimation of human postures in video streams, represented as coordinate positions of human joints in each frame. Compared to traditional methods relying solely on deep neural networks, Yang's method offers advantages such as high frame rates, low hardware requirements, and improved continuity in recognition results. Additionally, it corrects cumulative errors that may arise in motion estimation algorithms, thereby enhancing estimation accuracy.
Another significant patent by Yang is the "Multi-modal robot system capable of realizing autonomous submarine docking and reconstruction." This system includes a non-contact charging platform, various functional modules, and a docking robot. The design features a coil on the charging platform that facilitates energy and signal transmission between the coil and functional modules. Each functional module serves a specific purpose, including propulsion, energy management, observation, and navigation. The docking robot is capable of reconstructing a multi-modal underwater robot by docking specific functional modules based on task instructions. This innovative system allows for the flexible reconstruction of the underwater robot's operational modes, enabling it to perform horizontal cruising, fixed-point operations, and vertical profiling while reducing costs.
Career Highlights
Canjun Yang is affiliated with Zhejiang University, where he continues to advance his research and development in robotics and human motion estimation. His work has garnered attention for its practical applications and innovative approaches to complex problems in these fields.
Collaborations
Yang collaborates with several colleagues, including Mingwei Lin and Ri Lin, who contribute to his research endeavors and projects.
Conclusion
Canjun Yang's contributions to the fields of robotics and human posture estimation demonstrate his innovative spirit and commitment to advancing technology. His patents reflect a deep understanding of both theoretical and practical aspects of his work,