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

TL;DR

This paper introduces a deep learning method to generate high spatio-temporal resolution videos for wide area surveillance by fusing high spatial low frame rate and low spatial high frame rate videos.

Contribution

It presents an end-to-end trainable network that combines dual video feeds for improved video super-resolution and frame interpolation in surveillance applications.

Findings

Significant improvement in PSNR and SSIM over existing methods.

Effective fusion of dual video feeds enhances resolution and temporal accuracy.

End-to-end training simplifies the process and improves performance.

Abstract

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.