Towards Automatic Model Specialization for Edge Video Analytics

TL;DR

This paper introduces COVA, a framework that automatically specializes lightweight models for edge video analytics, significantly improving accuracy while maintaining constant computational costs, especially for static camera scenarios.

Contribution

COVA provides an automated method to tailor lightweight models to specific contexts, enhancing accuracy without increasing computational complexity.

Findings

COVA improves model accuracy by an average of 21%.

State-of-the-art models can be effectively adapted for specific environments.

The approach simplifies model specialization by leveraging static camera assumptions.

Abstract

Judging by popular and generic computer vision challenges, such as the ImageNet or PASCAL VOC, neural networks have proven to be exceptionally accurate in recognition tasks. However, state-of-the-art accuracy often comes at a high computational price, requiring hardware acceleration to achieve real-time performance, while use cases, such as smart cities, require images from fixed cameras to be analyzed in real-time. Due to the amount of network bandwidth these streams would generate, we cannot rely on offloading compute to a centralized cloud. Thus, a distributed edge cloud is expected to process images locally. However, the edge is, by nature, resource-constrained, which puts a limit on the computational complexity that can execute. Yet, there is a need for a meeting point between the edge and accurate real-time video analytics. Specializing lightweight models on a per-camera basis may help but it quickly becomes unfeasible as the number of cameras grows unless the process is automated. In this paper, we present and evaluate COVA (Contextually Optimized Video Analytics), a framework to assist in the automatic specialization of models for video analytics in edge cameras. COVA automatically improves the accuracy of lightweight models through their specialization. Moreover, we discuss and review each step involved in the process to understand the different trade-offs that each one entails. Additionally, we show how the sole assumption of static cameras allows us to make a series of considerations that greatly simplify the scope of the problem. Finally, experiments show that state-of-the-art models, i.e., able to generalize to unseen environments, can be effectively used as teachers to tailor smaller networks to a specific context, boosting accuracy at a constant computational cost. Results show that our COVA can automatically improve accuracy of pre-trained models by an average of 21%.