Compressive Sensing Video Dataset Using Pixel-Wise Coded Exposure
收藏arXiv2019-07-09 更新2024-08-06 收录
下载链接：
http://arxiv.org/abs/1905.10054v2
下载链接
链接失效反馈官方服务：
资源简介：
本数据集名为Compressive Sensing Video Dataset Using Pixel-Wise Coded Exposure，由印度科学理工学院电子与系统工程系创建，旨在通过像素级编码曝光技术压缩视频数据，解决存储和计算资源限制问题。数据集包含284个汽车视频片段和91个人物视频片段，总计约90分钟，涵盖多种运动和环境变化。创建过程中，视频通过13倍压缩率处理，使用随机感知矩阵以增强通用性。该数据集主要应用于视频监控领域，通过压缩感知技术提高视频处理的效率和隐私保护。
This dataset, named Compressive Sensing Video Dataset Using Pixel-Wise Coded Exposure, was developed by the Department of Electronics and Systems Engineering, Indian Institute of Science. It aims to compress video data via pixel-wise coded exposure technology to address the limitations of storage and computing resources. The dataset consists of 284 automotive video clips and 91 human video clips, totaling approximately 90 minutes, covering various motions and environmental changes. During its construction, the videos were processed at a 13-fold compression ratio using random sensing matrices to enhance generalizability. This dataset is primarily applied in the field of video surveillance, where compressive sensing technology is utilized to improve the efficiency of video processing and strengthen privacy protection.
提供机构：
印度科学理工学院电子与系统工程系
创建时间：
2019-05-24
