# Real-Time Crowd Counting for Embedded Systems with Lightweight Architecture

arXiv: https://arxiv.org/abs/2510.13250 · HTML: https://mlsanity.com/paper/2510.13250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 73 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 30 of 37)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Lite-HRNet: A Lightweight High-Resolution Network](https://mlsanity.com/paper/2104.06403/) (2021)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting](https://mlsanity.com/paper/1707.09605/) (2017)
- [Positive-incentive Noise](https://mlsanity.com/paper/2212.09541/) (2022)
- [Variational Positive-incentive Noise: How Noise Benefits Models](https://mlsanity.com/paper/2306.07651/) (2023)
- [Reconstructive Sequence-Graph Network for Video Summarization](https://mlsanity.com/paper/2105.04066/) (2021)
- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [PCC Net: Perspective Crowd Counting via Spatial Convolutional Network](https://mlsanity.com/paper/1905.10085/) (2019)
- [Spatiotemporal Modeling for Crowd Counting in Videos](https://mlsanity.com/paper/1707.07890/) (2017)
- [Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise](https://mlsanity.com/paper/2408.09929/) (2024)
- [C^3 Framework: An Open-source PyTorch Code for Crowd Counting](https://mlsanity.com/paper/1907.02724/) (2019)
- [DR.VIC: Decomposition and Reasoning for Video Individual Counting](https://mlsanity.com/paper/2203.12335/) (2022)
- [Learn Beneficial Noise as Graph Augmentation](https://mlsanity.com/paper/2505.19024/) (2025)
- [WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code](https://mlsanity.com/paper/2506.07818/) (2025)
- [Top-Down Feedback for Crowd Counting Convolutional Neural Network](https://mlsanity.com/paper/1807.08881/) (2018)
- [Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2509.16738/) (2025)
- [Efficient Crowd Counting via Structured Knowledge Transfer](https://mlsanity.com/paper/2003.10120/) (2020)
- [A Fixed-Point Approach to Unified Prompt-Based Counting](https://mlsanity.com/paper/2403.10236/) (2024)
- [Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators](https://mlsanity.com/paper/2307.05358/) (2023)
- [LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges](https://mlsanity.com/paper/2506.10022/) (2025)

## Abstract (arXiv)

Crowd counting is a task of estimating the number of the crowd through images, which is extremely valuable in the fields of intelligent security, urban planning, public safety management, and so on. However, the existing counting methods have some problems in practical application on embedded systems for these fields, such as excessive model parameters, abundant complex calculations, etc. The practical application of embedded systems requires the model to be real-time, which means that the model is fast enough. Considering the aforementioned problems, we design a super real-time model with a stem-encoder-decoder structure for crowd counting tasks, which achieves the fastest inference compared with state-of-the-arts. Firstly, large convolution kernels in the stem network are used to enlarge the receptive field, which effectively extracts detailed head information. Then, in the encoder part, we use conditional channel weighting and multi-branch local fusion block to merge multi-scale features with low computational consumption. This part is crucial to the super real-time performance of the model. Finally, the feature pyramid networks are added to the top of the encoder to alleviate its incomplete fusion problems. Experiments on three benchmarks show that our network is suitable for super real-time crowd counting on embedded systems, ensuring competitive accuracy. At the same time, the proposed network reasoning speed is the fastest. Specifically, the proposed network achieves 381.7 FPS on NVIDIA GTX 1080Ti and 71.9 FPS on NVIDIA Jetson TX1.