ODinMJ: <i>A red, green, blue-thermal dataset for mountain jungle object detection</i>
Qingwang Wang, Xin Qu, Pengcheng Jin, Liyao Zhou, Junlin Ouyang, Haochen Song, Bei Cheng, Tao Shen, Yanfeng Gu
Abstract
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Mountain jungle</i> is one of the important types of land cover on Earth’s surface and a crucial component of terrestrial ecosystems. According to statistics, mountains occupy approximately 24% of the global land area, while jungles cover about 31% of the terrestrial surface <xref ref-type="bibr" rid="ref1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[1]</xref>. This complex ecosystem nurtures a diverse array of rare and precious plant and animal species, making remarkable contributions to the maintenance and protection of Earth’s biodiversity. Additionally, mountain jungles serve as a habitat that many humans depend on for survival, supplying more than half of the world’s freshwater resources. Therefore, mountain jungles are of great research significance.