Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception
Keywords:
Object detection, motion consistency, velocity-constrained filtering, intelligent transportation systems, GPS-based velocity estimation, temporal stabilityAbstract
Conventional object detection systems in Intelligent Transportation Systems (ITS) commonly operate in a frame-wise manner, leading to temporally inconsistent predictions under dynamic conditions. This paper proposes a motion-consistent object detection framework that integrates velocity-constrained filtering to enforce physical plausibility across consecutive frames. The main contribution of this work lies in explicitly formulating detection validation as a deterministic velocity-bounded constraint problem, enabling direct integration of motion dynamics into the perception pipeline rather than treating motion as auxiliary information. The system employs a lightweight YOLO11s-based detector for visual perception and GPS-based motion estimation to provide real-world velocity constraints. Experiments are conducted on a traffic infrastructure dataset comprising 52,135 images across 33 classes and evaluated on an Intel NUC 13 Pro edge computing platform. Results demonstrate that the proposed method improves temporal stability compared to conventional frame-wise detection while maintaining strong detection performance, achieving an mAP@0.5 of 0.945 at 20 FPS. The findings indicate that incorporating explicit motion constraints enhances detection reliability without introducing significant computational overhead. However, performance may degrade under low-speed GPS noise and challenging visual conditions such as occlusion, highlighting limitations for future improvement.
References
[1] F. Chu, H. Li, L. Xie, & J. Zhao, "A survey of transformer architectures for autonomous driving," Expert Systems with Applications, vol. 280, p. 127273, June 2025.
[2] Q. Han, X. Liu, & J. Zhang, "SCL-YOLO: A Lightweight Model Based on Improved YOLOv11n and Its Application in Blood Cell Object Detection," SSRN Electronic Journal, 2025.
[3] A. Ghasemi, A. Keshavarzi, A. M. Abdelmoniem, O. R. Nejati, & T. Derikvand, "Edge intelligence for intelligent transport systems: Approaches, challenges, and future directions," Expert Systems with Applications, vol. 280, p. 127273, June 2025.
[4] W. Yu, Y. Cheng, X. Fang, X. Zhai, Y. Wang, & H. Jing, "Modeling and Risk Analysis of Cooperative Adaptive Cruise Control Systems Based on Petri Nets and Distributed Edge Intelligence," IEEE Internet of Things Journal, 2025.
[5] W. Ren, B. Yu, Y. Chen, S. Bao, K. Gao, & Y. Kong, "Self-explaining analysis of facility environments on 2-lane rural roads with an improved lightweight CNN considering drivers' visual perception," International Journal of Transportation Science and Technology, vol. 19, pp. 99–113, 2025.
[6] J. Guo & L. He, "DEL-YOLO: Low-illumination lightweight object detection for conveyor belts in coal mines," Journal of Electronic Measurement and Instrumentation, vol. 39, no. 12, pp. 289–299, 2025.
[7] X. Ma, C. Huang, X. Huang, & W. Wu, "Mamba-DQN: Adaptively Tunes Visual SLAM Parameters Based on Historical Observation DQN," Applied Sciences, vol. 15, no. 6, 2025.
[8] Y. Ma, W. Liang, J. Guo, B. Li, Y. Zang, & G. Yin, "Augmented Intelligence in Smart Intersections: Local Digital Twins-Assisted Hybrid Autonomous Driving," IEEE Transactions on Intelligent Vehicles, Early Access, pp. 1–15, October 2024.
[9] N. N. et al., "Enhanced CNN based approach for IoT edge enabled smart car driving system for improving real time control and navigation," Scientific Reports, vol. 15, p. 33932, September 2025.
[10] Z. Yang, Y. Li, C. Liu, H. Zhao, & J. Wang, "Edge-Assisted Relevance-Aware Perception Dissemination in Vehicular Networks," in Proc. IEEE International Conference on Computer Communications (INFOCOM) Workshop, Jersey City, NJ, USA, July 2024.
[11] M. A. Khan, H. Park, & J. Kim, "NanoCNN: A Parameters Efficient Network for Traffic Sign Recognition," in Proc. IEEE International Conference on Advanced Communication Technologies (ICACT), Islamabad, Pakistan, May 2024.
[12] T. Gao, D. Zou, C. P. Chen, X. Wu, & H. Hu, "Online lane mapping based on multi-sensor SLAM and Catmull–Rom splines," Measurement Science and Technology, vol. 36, no. 2, p. 026318, January 2025.
[13] D. Hu, X. Yuan, & C. Zhao, "Active layered topology mapping driven by road intersection," Knowledge-Based Systems, p. 113305, March 2025.
[14] T. Xiao, C. Wang, & Y. Sun, "EATNet: Efficient Axial Transformer Network for End-to-end Autonomous Driving," in Proc. IEEE International Conference on Intelligent Transportation Systems (ITSC), Edmonton, AB, Canada, September 2024.
[15] M. Zhang, Y. Li, & H. Wang, "Hierarchical Transformers for Motion Forecasting Based on Inverse Reinforcement Learning," IEEE Transactions on Vehicular Technology, vol. 74, no. 3, pp. 3751–3764, March 2025.
[16] Ultralytics, "Ultralytics YOLOv11," GitHub repository, 2025. [Online]. https://github.com/ultralytics/ultralytics
[17] Y. Peng, Z. Wang, F. Chen, & L. Zhang, "TriLight-YOLO: Stern Target Detection Algorithm Based on Lightweight YOLO," in Proc. IEEE International Conference on Automation Science and Engineering (CASE), Hangzhou, China, June 2025.
[18] Q. Zhao, Y. Liu, J. Sun, & M. Tan, "ISDC-YOLO: A Lightweight Small Object Detection Algorithm Based on Inverted Bottleneck and Semantic Detail Fusion Network for UAV Aerial Image," IEEE Access, vol. 13, pp. 147874–147891, August 2025.
[19] S. Li, K. Yang, H. Wang, & B. Cheng, "Hybrid Attention-based Multi-task Vehicle Motion Prediction Using Non-Autoregressive Transformer and Mixture of Experts," IEEE Transactions on Intelligent Vehicles, Early Access, pp. 1–9, December 2024.
[20] A. Basit, G. Kaddoum, & A. Mourad, "Learning Resilient Distributed Channel Access Policies in V2I Networks Under Intelligent Jamming," IEEE Internet of Things Journal, 2025.
[21] H. Zhao, R. Wang, & L. Zhang, "A Knowledge Distillation-Driven Lightweight CNN Model for Traffic Sign Recognition in Edge Computing Environments," in Proc. IEEE International Conference on Communications (ICC), Yokohama, Japan, June–July 2024.
[22] M. Huang, X. Chen, & S. Liu, "Multi-Sensor Fusion and Kalman Filtering for Robust Vehicle State Estimation in Autonomous Driving Systems," IEEE Sensors Journal, vol. 24, no. 10, pp. 15678–15692, May 2024.
[23] A. Kumar, R. Singh, & P. Sharma, "Deep Learning-Based Robust Traffic Scene Understanding Under Adverse Conditions," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 8, pp. 10234–10250, August 2024.
[24] H. Wang, J. Chen, & L. Zhang, "Multi-Sensor Fusion for Real-Time Autonomous Driving: A Review of Current Trends and Future Directions," IEEE Transactions on Intelligent Vehicles, vol. 9, no. 4, pp. 2345–2362, April 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Gusty Anugrah, Dedid Cahya Happyanto, Eru Puspita (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
