Title: Dual-scale dual-rate video compressive sensing for edge surveillance devices

Authors: Yue Lu; Xiang Zhang; Chengsheng Yuan

Addresses: Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, 210044, China ' Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, 210044, China ' Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, 210044, China

Abstract: Classic video compression method suffers from long encode time and requires large memories, making it hard to deploy on edge devices, thus video compressive sensing which requires less resources during encoding is getting more attention. We propose a dual-scale dual-rate video compressive sensing algorithm for surveillance video compression. Proposed method extracts and compresses foreground area and reference frame separately using dual-scale compressive sampling, then using reversible neural network to reconstruct original frames. Finally we test compressive sampling and region of interest (ROI) extraction network in proposed method on edge device and reconstruction network on server. The experiments show that proposed method can fast compresses frame and extracts foreground area on edge computing devices, achieves higher reconstruction quality.

Keywords: video compressive sensing; reversible neural network; surveillance video; Siamese network; edge computing; neural processing unit; RK3399 Pro.

DOI: 10.1504/IJAACS.2025.147723

International Journal of Autonomous and Adaptive Communications Systems, 2025 Vol.18 No.3, pp.258 - 277

Received: 23 Feb 2024
Accepted: 23 Apr 2024
Published online: 28 Jul 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article