pmmw_data.rar

Citation Author(s):: Lei Pang

Yang Chen
Submitted by:: Pang Lei
Date Created:: Thu, 12/19/2019 - 15:53
Last updated:: Thu, 12/19/2019 - 15:53
DOI:: 10.21227/8261-ek35

375 views

Categories:

Machine Learning

Keywords:

PMMW

CITE

AI-Powered Dataset Intelligence is available for this dataset exclusively to institutional subscribers.

Learn More

Abstract

The PMMW real-time imager, SAIR-U, is developed by Microwave Laboratory of Beihang University, China.It could be (or has been) used in non-contact, non-cooperative (i.e. no need for a fixed posture) security, especially in the environment of large passenger flow. This is the dataset used in the experiment in paper"Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on YOLOv3 Algorithm"

Instructions:

This is a dataset about Passive Millimeter Wave(PMMW) data. It includes 1624 *2 files, divided into two parts, the original images and the annotation data. The relative system parameters are as following:

(a) The working band is Ka band, at 34Ghz.

(b) The imaging field of view is designed to be 40°×22°.

(c) The minimum imaging distance of the system is set according to the imaging field of view, and the imaging distance range is set to 2.5~5m.

(d) The spatial resolution of the design is determined to be centimeter, considering the application requirements, cost, hardware facilities, and the size of the contraband that the human body may carry. In the case of ensuring the number of system channels, the resolution of the human body at a distance of 3 meters from the system is about 6 to 7 cm.

(e) The sensitivity to temperature is 1~2K.

Provided in the experiments in the paper“Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on YOLOv3 Algorithm”.

2019-12-19