Privacy-Preserving Object Counting in Lightweight Intelligent Transportation System
Top Cited Papers
- 1 November 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (11) , 13950-13962
Abstract
In Intelligent Transportation Systems (ITS), tiny machine learning enables resource-efficient on-device learning and deployment of AI models for critical tasks such as traffic flow prediction and pedestrian safety. However, existing object counting models typically consist of a large number of parameters, which require high computational costs that are unsuited for on-device learning. Moreover, these models are usually trained in a centralized manner, which raises data privacy concerns and relies on the unrealistic assumption of independent and identically distributed (IID) data across all vehicles and environments. To address these challenges, we propose a lightweight network, termed Privacy-aware Efficient Generalization Network (PEGNet), that preserves user privacy and improves cross-scenario generalization. Specifically, this network incorporates a Lightweight Adaptive Enhancement (LAE) module with deformable convolutions to efficiently capture multi-scale features under strict resource constraints. We further employ a federated learning framework to collaboratively train the model across distributed IoV nodes with limited local data, thereby significantly reducing per-node computation while safeguarding user data privacy. To enhance the robustness of non-IID data, we introduce a Moment Distance loss (MDloss) that prompts the model to adapt to diverse traffic scenes. Experiments on multiple vehicle and crowd counting benchmarks demonstrate that the proposed method achieves superior efficiency and accuracy.Keywords
Funding Information
- National Natural Science Foundation of China (62076078)
- Fundamental Research Funds for the Central Universities (3072024LJ0403)
- Chinese Association for Artificial Intelligence (CAAI)-Huawei MindSpore Open Fund (CAAIXSJLJJ-2020-033A)
This publication has 63 references indexed in Scilit:
- Object counting in remote sensing via selective spatial‐frequency pyramid networkSoftware: Practice and Experience, 2023
- Dense Attention Fusion Network for Object Counting in IoT SystemMobile Networks and Applications, 2023
- $\hbox {DA}^2$Net: a dual attention-aware network for robust crowd countingMultimedia Systems, 2022
- Efficient federated learning for fault diagnosis in industrial cloud-edge computingComputing, 2021
- Pixel-Wise Crowd Understanding via Synthetic DataInternational Journal of Computer Vision, 2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds2018
- Scale Aggregation Network for Accurate and Efficient Crowd Counting2018
- A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning2016
- Extremely Overlapping Vehicle Counting2015