This inventor holds 1 USPTO granted patent. Top assignee: Wuhan University. Active years: 2022.
Company Filing History:
Years Active: 2022
Title: Jiaming Wang - Innovator in Pedestrian Re-identification Technology.
Introduction
Jiaming Wang is a notable inventor based in Wuhan, China. He has made significant contributions to the field of pedestrian re-identification through his innovative methods and technologies. His work focuses on enhancing the accuracy and efficiency of identifying pedestrians in various environments.
Latest Patents
Jiaming Wang holds a patent for a "Pedestrian re-identification method based on spatio-temporal joint model of residual attention mechanism and device thereof." This patent outlines a method that includes performing feature extraction for an input pedestrian using a pre-trained ResNet-50 model. It constructs a residual attention mechanism network that incorporates several layers, including a feature sampling layer and a global average pooling layer. The method calculates a feature distance using cosine distance and models a spatio-temporal probability based on camera ID and frame number information. Ultimately, it calculates a final spatio-temporal joint probability to achieve pedestrian re-identification results.
Career Highlights
Jiaming Wang is affiliated with Wuhan University, where he continues to advance his research and development in the field of pedestrian identification technologies. His work has garnered attention for its innovative approach and practical applications in security and surveillance systems.
Collaborations
Jiaming Wang collaborates with Zhenfeng Shao, contributing to the development of advanced technologies in their field. Their partnership enhances the research output and innovation potential at Wuhan University.
Conclusion
Jiaming Wang's contributions to pedestrian re-identification technology exemplify the impact of innovative thinking in addressing real-world challenges. His work continues to influence the field and pave the way for future advancements.