# Optimizing video analytics inference pipelines: a case study

arXiv: https://arxiv.org/abs/2512.07009 · HTML: https://mlsanity.com/paper/2512.07009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [UNeXt: MLP-based Rapid Medical Image Segmentation Network](https://mlsanity.com/paper/2203.04967/) (2022)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022)
- [Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines](https://mlsanity.com/paper/2102.01887/) (2021)
- [Turbo: Opportunistic Enhancement for Edge Video Analytics](https://mlsanity.com/paper/2207.00172/) (2022)
- [AgriSORT: A Simple Online Real-time Tracking-by-Detection framework for robotics in precision agriculture](https://mlsanity.com/paper/2309.13393/) (2023)
- [VidCEP: Complex Event Processing Framework to Detect Spatiotemporal Patterns in Video Streams](https://mlsanity.com/paper/2007.07817/) (2020)
- [OCTOPINF: Workload-Aware Inference Serving for Edge Video Analytics](https://mlsanity.com/paper/2502.01277/) (2025)

## Abstract (arXiv)

Cost-effective and scalable video analytics are essential for precision livestock monitoring, where high-resolution footage and near-real-time monitoring needs from commercial farms generates substantial computational workloads. This paper presents a comprehensive case study on optimizing a poultry welfare monitoring system through system-level improvements across detection, tracking, clustering, and behavioral analysis modules. We introduce a set of optimizations, including multi-level parallelization, Optimizing code with substituting CPU code with GPU-accelerated code, vectorized clustering, and memory-efficient post-processing. Evaluated on real-world farm video footage, these changes deliver up to a 2x speedup across pipelines without compromising model accuracy. Our findings highlight practical strategies for building high-throughput, low-latency video inference systems that reduce infrastructure demands in agricultural and smart sensing deployments as well as other large-scale video analytics applications.