Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
INERTIAL SENSOR-BASED GAIT FEATURE EXTRACTION AND GAIT RECOGNITION METHOD
Document Type and Number:
WIPO Patent Application WO/2021/115066
Kind Code:
A1
Abstract:
An inertial sensor-based gait feature extraction and gait recognition method. The method specifically comprises the following steps: step 1, preprocessing a gait signal; step 2, performing gait key point detection on the gait signal that is processed in step 1; step 3, extracting a gait cycle feature vector according to a detection result in step 2; step 4, performing PCA-CCA feature fusion on the gait cycle feature vector that is extracted in step 3; and step 5, performing gait recognition and classification modeling on the feature vector that is fused in step 4. According to the method, inertial sensors are placed in the middle parts of the left and right shanks of the lower limbs of a human body so as to better capture gait information, a gain cycle is accurately divided by means of a gait key point detection method based on an observation window, so that corresponding acceleration and angular velocity gait features are extracted, and an angular velocity feature and an acceleration feature are fused by means of a PCA-CCA feature fusion method, thereby improving the accuracy of gait recognition.

Inventors:
HUANG HAOHUA (CN)
SUN FANGMIN (CN)
LI YE (CN)
Application Number:
PCT/CN2020/129527
Publication Date:
June 17, 2021
Filing Date:
November 17, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SHENZHEN INST OF ADV TECH CAS (CN)
International Classes:
G06K9/00; A61B5/11
Foreign References:
CN111178155A2020-05-19
CN104729507A2015-06-24
CN102824177A2012-12-19
CN109540133A2019-03-29
CN108836346A2018-11-20
US20180220935A12018-08-09
Other References:
SUN, FANGMIN ET AL.: "Accelerometer-Based Speed-Adaptive Gait Authentication Method for Wearable IoT Devices", IEEE INTERNET OF THINGS JOURNAL, vol. 6, no. 1, 28 February 2019 (2019-02-28), XP011711641, DOI: 10.1109/JIOT.2018.2860592
Attorney, Agent or Firm:
BEIJING ZHONG XUN TONG DA INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: