Marcel Germann

Title: Innovations by Marcel Germann

Introduction

Marcel Germann is a notable inventor based in Zurich, Switzerland. He has made significant contributions to the field of pose estimation through his innovative patents. With a total of three patents to his name, Germann's work focuses on enhancing the accuracy and efficiency of computer-based models for articulated objects.

Latest Patents

One of Germann's latest patents is titled "Silhouette-based pose estimation." This invention involves estimating the pose of an articulated object model by utilizing a sequence of source images. The process includes obtaining corresponding source image segments, matching these segments with reference silhouettes, and determining the best match. The method also involves retrieving reference poses associated with the selected reference silhouettes and computing an estimate of the pose from these retrieved poses. This initial pose estimate can be further refined for maintaining local and global consistency across frames. Another patent by Germann outlines a computer-implemented method for estimating the pose of an articulated object model observed by one or more source cameras. This method includes processing source images, comparing them to a database of reference silhouettes, and selecting the most accurate matches to compute the pose estimate.

Career Highlights

Throughout his career, Marcel Germann has worked with prominent companies such as Liberovision AG and Mitsubishi Electric Research Laboratories, Inc. His experience in these organizations has contributed to his expertise in the field of computer vision and pose estimation.

Collaborations

Germann has collaborated with notable individuals in his field, including Richard Keiser and Remo Ziegler. These collaborations have likely enriched his work and led to further advancements in his research.

Conclusion

Marcel Germann's innovative contributions to pose estimation demonstrate his expertise and commitment to advancing technology in this area. His patents reflect a deep understanding of computer vision and its applications in real-world scenarios.