Dual-Spectrum Vehicle-mounted Scenario Database

With the constant development of the autonomous driving industry and relevant technologies, the need for vehicle-mounted scenario data is also increasing. The natural advantages of infrared night vision bring more extensive attention to the application of infrared detectors on night-time autonomous driving. The primary database of the autonomous driving industry is mostly based on single visible-light images or infrared images only. Therefore, we have created a new vehicle-mounted scenario database, which includes the dual-spectrum vehicle-mounted scenario data of visible light and infrared for data training of autonomous all-time driving and vehicle-mounted applications. We hope that our database can be a valuable resource for research groups to build better dual-spectrum models of infrared and visible light in vehicle-mounted scenarios, producing positive effects on all-weather autonomous driving.

Our researches aim to create a database based on the infrared and visible light dual-spectrum vehicle-mounted scenario to train and generate dual-spectrum deep learning models, which are used for pedestrian and vehicle detection in vehicle-mounted scenarios. The used infrared detectors are our self-developed products. The effective resolution is 1440×1080 for collected infrared images, and the resolution is 1920×1080 for visible-light images. The dual-spectrum images are in relatively large resolution and are captured in various scenarios. Pay attention to the following: 1) There is black edging on some infrared images, and you can remove the black edging when using the images; 2) Some visible-light images are taken at the depression angle, and you can exclude them if the images are used for special applications; 3) Motion blur occurs during visible-light and infrared data collection; 4) There are some blurs on the edge of visible-light and infrared images, which may cause targets such as people and vehicles to display in fewer pixels and have blurred appearance. When you use the database, the targets can be classified into the following: 1) person; 2) cyclist; 3) car; 4) truck; 5) bus. You can also adjust the classification according to your applications. We sincerely hope that the database can help in your work. 

Researchers

Researchers in this research:

LI Gangqiang (gqli@iraytek.com)

WANG Jiansheng (jiansheng.wang@iraytek.com)

WANG Shuigen (shuigen.wang@iraytek.com) 

Copyright Statement

-----------Copyright Statement Start------------

All rights reserved (c) 2021 IRay Technology Co., Ltd.

All rights reserved.

Hereby granted without any written permission, this permission contains no permission fee or permission loyalties. You can use, copy, modify, and distribute the data and documents for any legitimate purpose. However, you must comply with the following requirements: Its complete content must be in all copies of this database, and the original source of the database is IRay Technology Co., Ltd., which is clearly indicated in any publications of research results with this database used. IRay Technology Co., Ltd. does not bear responsibilities of any direct, indirect, special, accidental, or secondary damages caused by the usage of this database and documents in any circumstance, even though you have consulted IRay Technology Co., Ltd. before use. If you use this database, we will assume that you are familiar with this copyright statement.

IRay Technology Co., Ltd. does not make any promises, including but not limited to implied promises for marketability and applicability of special purposes. The database is provided "as is", and IRay has no obligations in forcible maintenance, support, update, enhancement, or modification.

-----------Copyright Statement End------------

Download

We are offering the infrared security database scenario to the public free of charge. If you have used this database in researches, please thank our company for conducting researches:

IRay Technology Co., Ltd.

You can provide information here to submit the application form for this database (if your institution is a domestic university or college, please fill in the name of your institution as announced by the Ministry of Education of the People's Republic of China). After the application is approved, the link for downloading the database will be sent to your e-mail box.

If you have any questions when downloading, viewing, or using the data set, please contact the maintenance personnel of this website: GUAN Chunlei (E-mail address: chunlei.guan@iraytek.com)