arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.04435cs.CVeess.IV
收藏

HSTR-Net:用于广域监控的高时空分辨率视频生成

HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area Surveillance

Ozyegin University(奥兹耶金大学);Istanbul Medipol University(伊斯坦布尔梅迪波尔大学)

H. Umut Suluhan, Hasan F. Ates, Bahadir K. Gunturk

摘要:

广域监控有着广泛的应用,而目标跟踪是一项重要的任务,通常需要高时空分辨率(HSTR)的视频来提高精度。本文提出了使用多个视频源生成HSTR视频作为基于参考的超分辨率(RefSR)的扩展。一个馈入以低帧速率(HSLF)以高空间分辨率俘获视频,而另一馈入同时针对同一场景俘获低空间分辨率及高帧速率(LSHF)视频。主要目的是从HSLF和LSHF视频的融合中创建HSTR视频。在本文中,我们提出了一种端到端的可训练深度网络,该网络通过组合来自两个视频源的输入来执行光流估计和帧重建。所提出的架构提供了显着改善现有的视频帧插值和RefSR技术的客观PSNR和SSIM指标。

英文摘要:

Wide area surveillance has many applications and tracking of objects under observation is an important task, which often needs high spatio-temporal resolution (HSTR) video for better precision. This paper presents the usage of multiple video feeds for the generation of HSTR video as an extension of reference based super resolution (RefSR). One feed captures video at high spatial resolution with low frame rate (HSLF) while the other captures low spatial resolution and high frame rate (LSHF) video simultaneously for the same scene. The main purpose is to create an HSTR video from the fusion of HSLF and LSHF videos. In this paper we propose an end-to-end trainable deep network that performs optical flow estimation and frame reconstruction by combining inputs from both video feeds. The proposed architecture provides significant improvement over existing video frame interpolation and RefSR techniques in terms of objective PSNR and SSIM metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑