Abstract: A multi-channel based noise and echo signal integrated cancellation device using deep neural network according to an embodiment comprises a plurality of microphone encoders that receive a plurality of microphone input signals including an echo signal, and a speaker's voice signal, convert the plurality of microphone input signals into a plurality of conversion information, and output the plurality of conversion information, a channel convert unit for compressing the plurality of pieces of conversion information and converting them into first input information having a size of a single channel and outputting the converted first input information, a far-end signal encoder that receives a far-end signal, converts the far-end signal into second input information, and outputs the converted second input information, an attention unit outputting weight information by applying an attention mechanism to the first input information and the second input information, a pre-learned first artificial neural network taking t
Type:
Application
Filed:
January 21, 2022
Publication date:
March 28, 2024
Applicant:
Industry-University Cooperation Foundation Hanyang Universtiy
Abstract: A radio frequency identification (RFID) tag is provided that prevents a recognition error of the RFID tag due to the occurrence of a shadow region. The RFID tag includes a first tag performing communication with an RFID reader and a second tag connected to the first tag and suitable for use with a different communication type from the first tag. Thus, when information stored in the first tag can not be read, the second tag is activated and externally transmits information and when information stored in the first tag can be read, the second tag is deactivated and does not externally transmit information. A communication method of an RFID system including an RFID reader communicating with an RFID tag is also provided.
Type:
Grant
Filed:
December 4, 2008
Date of Patent:
March 13, 2012
Assignees:
Samsung Techwin Co., Ltd., Industry-University Cooperation Foundation Hanyang Universtiy
Abstract: A parking area detecting method includes generating a top view image by capturing images of surroundings of a vehicle, detecting a first directional parking line from the top view image, detecting a second directional parking line having a direction different from a direction of the first directional parking line from the top view image, and detecting a parking area by combining the first directional parking line and the second directional parking line.
Type:
Grant
Filed:
December 30, 2016
Date of Patent:
August 6, 2019
Assignees:
Hyundai Motor Company, Kia Motors Corporation, Industry-University Cooperation Foundation Hanyang Universtiy
Inventors:
Seong Sook Ryu, Eu Gene Chang, Jae Seob Choi, Dae Joong Yoon, Jae Kyu Suhr, Ho Gi Jung