Pedestrians with IMU (Ped-IMU)

Citation Author(s):: Jia-Yan Li (National Yang Ming Chiao Tung University)

Jaden Chao-Ho Lin (MediaTek Inc.)

Kun-Ru Wu (National Yang Ming Chiao Tung University)

Yu-Chee Tseng (National Yang Ming Chiao Tung University)
Submitted by:: KUN-RU WU
Last updated:: Thu, 03/16/2023 - 15:54
DOI:: 10.21227/fk1e-gx83
Data Format:: *.jpg; *.json
Research Article Link:: SensePred: Guiding Video Prediction by Wearable Sensors

354 views

Categories:

Artificial Intelligence

Keywords:

GAN; Video Prediction; Wearable Device; Mobile Computing; Deep Learning

ACCESS DATASET CITE

Abstract

The dataset, Pedestrians with IMU (Ped-IMU), contains pedestrians moving in different behaviors while carrying a wearable sensor. We use a smartphone mounted on a subject's waist as a wearable device and record the smartphone's accelerometer, gyroscope, and magnetometer readings. We invite ten subjects of ages 22-35 to perform walking around with 4 trajectories: Left-Turn Back (L-TB), Left-Go Straight (L-GS), Right-Turn Back (R-TB), and Right-Go Straight (R-GS). A camera is set with screen ratio 16:9, resolution 1920*1080 pixels, and 12 fps. Each video clip length is 5 second including 30 IMU samples.