Visible-Infrared Artificial Camouflage Dataset

To promote the development of camouflaged object detection technology, an visible-infrared artificial camouflage dataset (VIAC) is constructed. To simulate and replicate real-world scenarios, we customize and procure a set of metal models and camouflage materials to construct artificial camouflage environments. Utilizing DJI drones equipped with a dual-mode (visible and infrared) imaging system, we conduct coordinated aerial photography in complex outdoor settings, thereby comprehensively acquiring 1,500 pairs of high-quality visible and infrared images. After data alignment and professional annotation, the VIAC dataset is formed. This dataset contains 9 challenges, namely big camouflaged object (BCO), small camouflaged object (SCO), multiple camouflaged objects (MCO), center bias (CB), out-of-view (OV), occlusions(OC), thermal crossover (TC), image clutter (IC), and low illumination (LI).

为推动伪装目标检测技术的发展，本研究构建了可见光-红外人工伪装数据集（visible-infrared artificial camouflage dataset, VIAC）。为模拟并复现真实应用场景，我们定制并采购了一批金属模型与伪装材料，以搭建人工伪装环境。借助搭载双模态（可见光与红外）成像系统的大疆（DJI）无人机，我们在复杂户外场景中开展协同航空拍摄，由此全面采集得到1500对高质量可见光与红外图像对。经数据对齐与专业标注后，最终形成该VIAC数据集。该数据集涵盖九类挑战场景，分别为大型伪装目标（big camouflaged object, BCO）、小型伪装目标（small camouflaged object, SCO）、多伪装目标（multiple camouflaged objects, MCO）、中心偏置（center bias, CB）、视野外（out-of-view, OV）、遮挡（occlusions, OC）、热交叉（thermal crossover, TC）、图像杂波（image clutter, IC）以及低照度（low illumination, LI）。

搜集汇总

背景与挑战

背景概述

Visible-Infrared Artificial Camouflage Dataset是一个包含1500对可见光和红外图像的数据集，旨在促进伪装目标检测技术的发展。数据集通过无人机在复杂户外环境中拍摄，并包含9种不同的挑战场景，如大伪装物体、小伪装物体和多伪装物体等。