Memorize, Then Recall: A Generative Framework for Low Bit-rate Surveillance Video Compression

12/30/2019
by   Yaojun Wu, et al.
7

Surveillance video applications grow dramatically in public safety and daily life, which often detect and recognize moving objects inside video signals. Existing surveillance video compression schemes are still based on traditional hybrid coding frameworks handling temporal redundancy by block-wise motion compensation mechanism, lacking the extraction and utilization of inherent structure information. In this paper, we alleviate this issue by decomposing surveillance video signals into the structure of a global spatio-temporal feature (memory) and skeleton for each frame (clue). The memory is abstracted by a recurrent neural network across Group of Pictures (GoP) inside one video sequence, representing appearance for elements that appeared inside GoP. While the skeleton is obtained by the specific pose estimator, it served as a clue for recalling memory. In addition, we introduce an attention mechanism to learn the relationships between appearance and skeletons. And we reconstruct each frame with an adversarial training process. Experimental results demonstrate that our approach can effectively generate realistic frames from appearance and skeleton accordingly. Compared with the latest video compression standard H.265, it shows much higher compression performance on surveillance video.

READ FULL TEXT

page 1

page 2

page 4

research
08/13/2022

A new way of video compression via forward-referencing using deep learning

To exploit high temporal correlations in video frames of the same scene,...
research
03/08/2023

Scene Matters: Model-based Deep Video Compression

Video compression has always been a popular research area, where many tr...
research
09/23/2022

Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network

Existing methods for video-based person re-identification (ReID) mainly ...
research
05/06/2019

A multimodal lossless coding method for skeletons in videos

Nowadays, skeleton information in videos plays an important role in huma...
research
01/18/2020

A Foreground-background Parallel Compression with Residual Encoding for Surveillance Video

The data storage has been one of the bottlenecks in surveillance systems...
research
04/04/2023

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

Video compression plays a significant role in IoT devices for the effici...
research
02/02/2015

Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance

In order to track the moving objects in long range against occlusion, in...

Please sign up or login with your details

Forgot password? Click here to reset