[time]
2022-08-02T05:41:05+02:00

[track]
4

[team_name]
PedestrianNav

[team_institution]
National University of Defense Technology

[logolink]


[team_members]


[reference_person]
Zheming Tu, Chaoqun Chu, Zongyang Chen

[reference_email]
tzm_nudt@163.com

[description_short]
Firstly, we carry out the magnetic calibration and determine the initial parameters according to the initial data, Then, we detect the zero-velocity interval, which is fused with the navigation trajectory solution model in EKF algorithm. To ensure the accuracy of zero-velocity detection, we used a novel detector based on contrastive learning method in the competition. This detector roughly eliminates the inertial data that must not be the zero-velocity event in advance, to reduce the computation cost. Then the detector uses the remaining inertial data to detect the zero-velocity event via a trained contrastive neural network. The contrastive neural network uses the triplet network and is trained by comparing with the anchor data which consists of the known static inertial data from the period of initial alignment. The classifier will finally determine whether the output of the triplet network is the zero-velocity event.

[description_long_link]
https://kdocs.cn/l/ccgzBcaI8EX9    (or    https://1drv.ms/w/s!And_W-_Ev2fBkG2RbnrKgd3eu1sh)

[publish_check_]
true

[results_check_]
true

[data_check_]
true

[pdf_check_]
true

[video_check_]
true