Kayak image fusion sequence

Here we present part I of the multimodal Kayak image dataset consisting of two image sequences showing three approaching kayaks in a cluttered maritime background. The scenario was registered in the 3-5 mm (mid-wave infrared), and 8-12 mm (long wave infrared or thermal) frequency bands and in the visual range. Because of the variation in distance the targets (kayaks) vary from dim point targets to easily distinguishable objects. This dataset can be used to develop and test mulisensor image fusion schemes and dim target detection algorithms.

本文发布多模态皮划艇图像数据集的第一部分，该数据集包含两组图像序列，呈现了杂乱海洋背景下三艘正向镜头靠近的皮划艇。该数据集的场景覆盖3-5 mm（中波红外，mid-wave infrared）、8-12 mm（长波红外，long wave infrared，或称热红外）以及可见光三个频段，且各模态数据已完成配准。由于目标（皮划艇）与拍摄端的距离存在变化，其成像特征从微弱的点目标逐步转变为易于分辨的完整目标。本数据集可用于开发与测试多传感器图像融合方案以及弱目标检测算法。

搜集汇总

背景与挑战

背景概述

该数据集包含两个图像序列，展示了在杂乱海上背景中三个接近的皮划艇，记录了中波红外、长波红外和视觉范围内的场景，适用于多传感器图像融合方案和暗淡目标检测算法的开发与测试。