计算机科学
像素
人工智能
计算机视觉
冗余(工程)
帧速率
红外线的
帧(网络)
比例(比率)
遥感
光学
地质学
电信
物理
量子力学
操作系统
作者
Ming Zhao,Meijing Zhao,Fan Yang,Houde Wu,Wenhai Xu
摘要
Abstract This paper presents an infrared single‐pixel video imaging to surveille sea surface. Based on the temporal redundancy of the surveillance video, a two‐step scheme, including low‐scale detection and high‐scale detection, is proposed. For each frame, low‐scale detection performs low‐resolution single‐pixel imaging to obtain a “preview” image of the scene, where the moving target can be located. These targets are further refined in the high‐scale detection where the high‐resolution single‐pixel imagings focusing on these targets are used. The frame is reconstructed by merging these two‐level images. The simulated experiments show that for a video with 128 × 128 pixels and 150 frames, the sampling rate of our scheme is about 17.8%, and the reconstructed video presents a good visual quality.
科研通智能强力驱动
Strongly Powered by AbleSci AI