Company Filing History:
Years Active: 2022-2025
Title: Innovations of Shangping Liu in Object Detection and Image Segmentation
Introduction
Shangping Liu is a prominent inventor based in Hong Kong, CN. He has made significant contributions to the fields of object detection and image segmentation through his innovative methods and systems. With a total of 2 patents, Liu's work showcases the application of convolutional neural networks (CNN) in enhancing video analysis and image processing.
Latest Patents
Liu's latest patents include a method, device, and system for detecting and tracking objects in captured video using convolutional neural networks. This method involves inputting image data into a detecting model to generate detection results, which are then enhanced through a series of operations. The process includes matching enhanced detection results with tracking results and selectively updating tracking models based on reliability estimations.
Another notable patent is his method for image segmentation using CNN. This innovation employs an encoder-decoder structure that aggregates multi-scale contexts to improve segmentation accuracy. By utilizing a channel-wise feature selection module, Liu's method effectively reduces computation while preserving high-activation channels, thereby enhancing the quality of the merged feature map.
Career Highlights
Shangping Liu is affiliated with the Hong Kong Applied Science and Technology Research Institute Company Limited. His work at this institution has allowed him to explore advanced technologies and contribute to the development of cutting-edge solutions in his field.
Collaborations
Liu has collaborated with notable colleagues, including Lu Wang and Pingping Zhang. These partnerships have fostered a collaborative environment that encourages innovation and the sharing of ideas.
Conclusion
Shangping Liu's contributions to the fields of object detection and image segmentation highlight his expertise and innovative spirit. His patents reflect a commitment to advancing technology through the application of convolutional neural networks. Liu's work continues to influence the landscape of video analysis and image processing, paving the way for future advancements.