Deepak Sridhar

Title: Innovations by Deepak Sridhar

Introduction

Deepak Sridhar is an accomplished inventor based in Richmond Hill, Canada. He has made significant contributions to the field of computer vision and machine learning, holding a total of five patents. His work focuses on enhancing keypoint estimation and gesture detection technologies.

Latest Patents

One of Deepak's latest patents is titled "Methods, devices, and computer readable media for training a keypoint estimation network using cGAN-based data augmentation." This patent describes a method where synthetic images are generated by a generator during each training iteration. Each synthetic image is assigned respective keypoints, and a prior iteration of the keypoint estimation network is used to obtain predicted keypoints. Poor quality synthetic images are discarded based on an error score, and the remaining images, along with real-world images, are utilized to train an updated keypoint estimation network until convergence criteria are met.

Another notable patent is "Devices and methods for single or multi-user gesture detection using computer vision." This invention outlines methods for detecting gestures through computer vision. It involves extracting locations of keypoints from a detected hand and normalizing these features. A trained decision tree ensemble processes the normalized features to generate a probability of a valid gesture, which is then classified as valid or invalid based on a defined decision threshold.

Career Highlights

Deepak Sridhar is currently employed at Huawei Technologies Co., Limited, where he continues to innovate in the field of technology. His work has contributed to advancements in machine learning and computer vision applications.

Collaborations

Deepak has collaborated with notable colleagues, including Juwei Lu and Peng Dai, to further enhance the impact of his inventions.

Conclusion

Deepak Sridhar's innovative work in keypoint estimation and gesture detection showcases his expertise and commitment to advancing technology. His contributions are paving the way for future developments in computer vision.