EKO: Adaptive Sampling of Compressed Video Data

by   Jaeho Bang, et al.

Researchers have presented systems for efficiently analysing video data at scale using sampling algorithms. While these systems effectively leverage the temporal redundancy present in videos, they suffer from three limitations. First, they use traditional video storage formats are tailored for human consumption. Second, they load and decode the entire compressed video in memory before applying the sampling algorithm. Third, the sampling algorithms often require labeled training data obtained using a specific deep learning model. These limitations lead to lower accuracy, higher query execution time, and larger memory footprint. In this paper, we present EKO, a storage engine for efficiently managing video data. EKO relies on two optimizations. First, it uses a novel unsupervised, adaptive sampling algorithm for identifying the key frames in a given video. Second, it stores the identified key frames in a compressed representation that is optimized for machine consumption. We show that EKO improves F1-score by up to 9 state-of-the-art unsupervised, sampling algorithms by selecting more representative frames. It reduces query execution time by 3X and memory footprint by 10X in comparison to a widely-used, traditional video storage format.


Active Learning for Video Classification with Frame Level Queries

Deep learning algorithms have pushed the boundaries of computer vision r...

Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain

With the widespread use of installed cameras, video-based monitoring app...

Vignette: Perceptual Compression for Video Storage and Processing Systems

Compressed videos constitute 70 rates far outpace compute and storage im...

MorphStore: Analytical Query Engine with a Holistic Compression-Enabled Processing Model

In this paper, we present MorphStore, an open-source in-memory columnar ...

Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning

Detection and localization of actions in videos is an important problem ...

Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning

Over the last decade, the use of Deep Learning in many applications prod...

Please sign up or login with your details

Forgot password? Click here to reset