Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras

TL;DR

Argus is a distributed smart camera system enabling efficient cross-camera collaboration for multi-target tracking, reducing redundant processing and latency without relying on cloud support.

Contribution

The paper introduces Argus, a novel distributed system that performs multi-camera, multi-target tracking with low latency and no cloud dependency, using object-wise spatio-temporal association.

Findings

Reduces object identification workload by up to 7.13x.

Lowers end-to-end latency by up to 2.19x.

Achieves comparable tracking quality to state-of-the-art methods.

Abstract

Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing visual analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13x and 2.19x (4.86x and 1.60x compared to the state-of-the-art), while achieving comparable tracking quality.