Other Data Paper Zone II Versions ZH5 Vol 5 (3) 2020
A dataset for infrared detection and tracking of dim-small aircraft targets under ground / air background
Dataset URL >>
: 2019 - 10 - 28
: 2020 - 02 - 18
: 2019 - 11 - 22
: 2020 - 08 - 17
17330 572 1
Abstract & Keywords
Abstract: Infrared detection and tracking of dim-small targets has been a major content of military application studies concerning, for example, long-range precision strike, aerospace defense confrontation, battlefield intelligence and reconnaissance. However, among the means of infrared target detection and recognition, there has been either a lack of authenticity in simulated infrared data or the insufficient sample volume of measured data. To tackle this predicament, we build this dataset by focusing on the detection and tracking of low altitude flying dim-small targets, through outfield recording and subsequent data processing. It can be used in algorithm testing related to the detection of one or multiple fixed-wing UAV targets. This dataset captures varied scenarios under the background of both sky and ground. It includes 22 image sequences, 30 trajectories and 16177 frames in relation to 16944 targets. Each target corresponds to a label location in the image, and each image sequence corresponds to a label file. This dataset provides statistical bases for researches concerning infrared target characteristics, dim-small object detection and precision guidance.
Keywords: infrared dim-small target; fixed wing target; target detection; target tracking; infrared image sequence
Dataset Profile
TitleA dataset for infrared detection and tracking of dim-small aircraft targets under ground / air background
Data corresponding authorFan Hongqi (fanhongqi@nudt.edu.cn)
Data authorsHui Bingwei, Song Zhiyong, Fan Hongqi, Zhong Ping, Hu Weidong, Zhang Xiaofeng, Ling Jianguo, Su Hongyan, Jin Wei, Zhang Yongjie, Bai Yaxi
Time range2017–2019
Geographical scopeChina
Spatial resolution10–100 m
Data volume870 MB
Data format*.bmp, *.txt
Data service system<http://www.dx.doi.org/10.11922/sciencedb.902>
Source of fundingATR Lab. Key Project “Multi-Source Data Set Construction for Target Detection, Tracking and Recognition” under Equipment Pre-Research Fund(2018).
Dataset compositionThe dataset consists of 22 subsets. The subsets are named in the format of data1.zip, data2.zip, …data11.zip. Each subset comprises two parts: (1) data[N].zip stores the infrared image sequences of all aircraft targets in Segment N; (2) data_label.txt stores the corresponding label files for data[N].zip. The label information includes the name of subset name, the number of image frames, the number of target trajectories, and the number, index and coordinate location of targets in each frame image.
Article and author information
Hui Bingwei
Song Zhiyong
Fan Hongqi
Zhong Ping
Hu Weidong
Zhang Xiaofeng
Ling Jianguo
Su Hongyan
Jin Wei
Zhang Yongjie
Bai Yaxi
Publication records
Released: Nov. 22, 2019 ( VersionsZH1
Published: Aug. 17, 2020 ( VersionsZH3
Updated: Aug. 17, 2020 ( VersionsZH5