# A Scalable Platform for Distributed Object Tracking across a Many-camera Network

## TL;DR

This paper introduces Anveshak, a scalable, flexible platform for distributed object tracking across large camera networks, addressing limitations of existing systems by supporting dynamic, real-time, and resource-aware tracking applications.

## Contribution

The paper presents Anveshak, a novel runtime platform with a dataflow programming model that enables dynamic, scalable, and resource-efficient distributed object tracking across many cameras.

## Key findings

- Supports real-time tracking with 1000 camera feeds
- Demonstrates tunable scalability and performance trade-offs
- Effectively balances accuracy, speed, and resource utilization

## Abstract

Advances in deep neural networks (DNN) and computer vision (CV) algorithms have made it feasible to extract meaningful insights from large-scale deployments of urban cameras. Tracking an object of interest across the camera network in near real-time is a canonical problem. However, current tracking platforms have two key limitations: 1) They are monolithic, proprietary and lack the ability to rapidly incorporate sophisticated tracking models; and 2) They are less responsive to dynamism across wide-area computing resources that include edge, fog and cloud abstractions. We address these gaps using Anveshak, a runtime platform for composing and coordinating distributed tracking applications. It provides a domain-specific dataflow programming model to intuitively compose a tracking application, supporting contemporary CV advances like query fusion and re-identification, and enabling dynamic scoping of the camera network's search space to avoid wasted computation. We also offer tunable batching and data-dropping strategies for dataflow blocks deployed on distributed resources to respond to network and compute variability. These balance the tracking accuracy, its real-time performance and the active camera-set size. We illustrate the concise expressiveness of the programming model for $4$ tracking applications. Our detailed experiments for a network of 1000 camera-feeds on modest resources exhibit the tunable scalability, performance and quality trade-offs enabled by our dynamic tracking, batching and dropping strategies.