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

arXiv: https://arxiv.org/abs/2401.14132 · HTML: https://mlsanity.com/paper/2401.14132/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 93 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors](https://mlsanity.com/paper/2008.07043/) (2020)
- [Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers](https://mlsanity.com/paper/2012.10557/) (2020)
- [Focus: Querying Large Video Datasets with Low Latency and Low Cost](https://mlsanity.com/paper/1801.03493/) (2018)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [The 5th AI City Challenge](https://mlsanity.com/paper/2104.12233/) (2021)
- [DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device](https://mlsanity.com/paper/2104.09949/) (2021)
- [City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones](https://mlsanity.com/paper/2105.06623/) (2021)
- [Pose-Assisted Multi-Camera Collaboration for Active Object Tracking](https://mlsanity.com/paper/2001.05161/) (2020)
- [Wireless Software Synchronization of Multiple Distributed Cameras](https://mlsanity.com/paper/1812.09366/) (2018)
- [Scaling Video Analytics Systems to Large Camera Deployments](https://mlsanity.com/paper/1809.02318/) (2018)
- [CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale](https://mlsanity.com/paper/2105.06524/) (2021)
- [Privid: Practical, Privacy-Preserving Video Analytics Queries](https://mlsanity.com/paper/2106.12083/) (2021)
- [SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices](https://mlsanity.com/paper/2109.03947/) (2021)
- [MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations](https://mlsanity.com/paper/2304.02101/) (2023)
- [Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking](https://mlsanity.com/paper/1607.06408/) (2016)
- [Image Segmentation in Video Sequences: A Probabilistic Approach](https://mlsanity.com/paper/1302.1539/) (2013)
- [Video Analytics with Zero-streaming Cameras](https://mlsanity.com/paper/1904.12342/) (2019)
- [An Empirical Study of Vehicle Re-Identification on the AI City Challenge](https://mlsanity.com/paper/2105.09701/) (2021)

## Built on by (most cited first, 1 of 1)

- [Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey](https://mlsanity.com/paper/2510.09731/) (2025)

## Abstract (arXiv)

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.