Logical Correction Enabled Collaborative Person Detection Inference in Edge Networks
- 31 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 4747-4761
Abstract
Person detection in videos is vital for area admission and public safety. Existing studies have made significant progress in improving the accuracy of this task on the cloud.Meanwhile, with people’s increasing awareness of privacy protection, there is a surging demand for privacy not being transmitted and processed by the cloud. Thus, providing services on edges becomes a promising solution. The dilemma is that edges are typically resource-constrained and cannot support the deployment of large models. However, tiny models that fit resource-constrained edges generally have unsatisfactory performance in accuracy and efficiency. To this end, we propose a Logical Correction Enabled Collaborative Person Detection Inference (LC-CPDI) framework for resource-constrained edges. First, we formulate the problem studied with a delay minimization objective. Second, we design a logical correction scheme to perceive abnormal predictions and perform corrections to improve accuracy. Third, a hybrid position prediction algorithm is proposed to replace time-consuming inference for simple scenarios. Finally, we design a collaborative inference scheme that enables frame outsourcing to idle edges to reduce the inference delay. We implemented LC-CPDI on a testbed designed with commercial edges. The experiments on real-world datasets show the effectiveness of LC-CPDI with up to 41.8% delay reduction on average and near 2% recall improvement.Keywords
Funding Information
- National Natural Science Foundation of China (U25A20436)
- National Natural Science Foundation of China (62372047)
- Ministry of Education Industry-University Cooperation Collaborative Education Project (240904497110437)
- Key Laboratory of Equipment Data Security and Guarantee Technology
- Ministry of Education, Libya (GDZB2024020100)
- Natural Science Foundation of Beijing Municipality (4232028)
- Natural Science Foundation of Guangdong Province (2024A1515011323)
- Joint Project of Production, Teaching and Research of Zhuhai (2220004002619)
- Joint Project of Production, Teaching and Research of Zhuhai (2220004002686)
- Joint Project of Production, Teaching and Research of Zhuhai (2320004002812)
- Science and Technology Projects of Social Development in Zhuhai (2320004000213)
- Supplemental Funds for Major Scientific Research Projects
- Beijing Normal University (ZHPT2023002)
- Fundamental Research Funds for the Central Universities
- Higher Education Research Topics of Guangdong Association of Higher Education in the 14th Five-Year Plan (24GYB207)
- Beijing Normal University Education Reform Project (jx2024139)
This publication has 42 references indexed in Scilit:
- YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information2024
- Lucas Kanade based Optical Flow for Vehicle Motion Tracking and Velocity Estimation2023
- Multi-level feature fusion for multimodal human activity recognition in Internet of Healthcare ThingsInformation Fusion, 2023
- A multitask joint framework for real-time person searchMultimedia Systems, 2022
- CHEX: CHannel EXploration for CNN Model Compression2022
- Edge computing-based person detection system for top view surveillance: Using CenterNet with transfer learningApplied Soft Computing, 2021
- A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillancePersonal and Ubiquitous Computing, 2021
- Generalizable Pedestrian Detection: The Elephant In The Room2021
- Multi-view People Tracking via Hierarchical Trajectory Composition2016
- Multispectral pedestrian detection: Benchmark dataset and baseline2015