Received:
2025-09-15 | Accepted:
2025-12-06 | Published:
2025-12-30
Title
An experimental analysis of artificial intelligence (AI) use for traffic monitoring in urban environments
Abstract
This article presents an experimental analysis of lightweight convolutional neural network (CNN) object detection models designed for on-device traffic monitoring in urban environments. The study investigates the performance of several mobile-oriented detectors, including EfficientDet, SSD MobileNet V2, and SSD MobileNet V2 FPNLite, with the goal of identifying an optimal balance between detection accuracy, inference speed, memory footprint, and energy efficiency on resource-constrained Android devices. To assess practical applicability, all models were evaluated under realistic operational conditions, including varying object distances, partial occlusions, and reduced illumination typical of urban monitoring scenarios. The comparative analysis shows that the recommended configuration – SSD MobileNet V2 FPNLite (640×640) accelerated with NNAPI – achieves the most favorable trade-off for real-time deployment, reaching approximately 40% mAP on the evaluation dataset while maintaining fast on-device inference and reduced power consumption. Experimental testing further demonstrates that the system achieves up to 94% recognition accuracy at close range and delivers stable performance at medium distances, surpassing several lightweight state-of-the-art detectors in practical real-time tests. Additionally, a modular Android application based on the Model-View-Controller architecture is presented, demonstrating seamless integration of the selected model into an end-to-end mobile processing pipeline. The results confirm that accurate and efficient on-device object detection for traffic monitoring can be achieved without reliance on high-end hardware or cloud-based computation, making the proposed solution well-suited for mobile, embedded, and edge-intelligent urban applications.
Keywords
detection, real-time system, convolutional neural networks (CNN)
JEL classifications
O33
, C55
, L86
, R41
URI
http://jssidoi.org/ird/article/232
DOI
Pages
231-250
Funding
The work was funded by the EU NextGenerationEU through the Recovery and Resilience Plan for Slovakia under the project No. 09I03-03-V01-00085
This is an open access issue and all published articles are licensed under a
Creative Commons Attribution 4.0 International License
References
Search via ReFindit
Ardito, L., Coppola, R., Malnati, G., & Torchiano, M. (2020). Effectiveness of Kotlin vs. Java in Android app development tasks. Information and Software Technology, 127, 106374. https://doi.org/10.1016/j.infsof.2020.106374
Search via ReFindit
Bursa, S. Ö., Durmaz İncel, Ö., & Işıklar Alptekin, G. (2023). Building lightweight deep-learning models with TensorFlow Lite for human activity recognition on mobile devices. Annales des Télécommunications, 78, 687-702. https://doi.org/10.1007/s12243-023-00962-x
Search via ReFindit
Daoudi, W., Shang, W., & Zou, Y. (2019). An exploratory study of MVC-based architectural patterns in Android apps. In Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing (SAC ’19) (pp. 1711-1720). https://doi.org/10.1145/3297280.3297447
Search via ReFindit
Datactics. (2024). The importance of data quality in machine learning. https://www.datactics.com/blog/the-importance-of-data-quality-in-machine-learning/
Search via ReFindit
David, R., Duke, J., Jain, A., Janapa Reddi, V., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., Regev, S., Rhodes, R., Wang, T., & Warden, P. (2020). TensorFlow Lite Micro: Embedded machine learning on TinyML systems. https://www.scribd.com/document/773516821/TensorFlow-Lite-Micro-Embedded-Machine-L
Search via ReFindit
Dusek, V. (2024). People-detector: Python app for people monitoring from UAV. GitHub. https://github.com/vdusek/people-detector
Search via ReFindit
Hirsch, M., Mateos, C., & Majchrzak, T. A. (2025). Exploring smartphone-based edge AI inferences using real testbeds. Sensors, 25(9), 2875. https://doi.org/10.3390/s25092875
Search via ReFindit
Hua, H., & Chen, J. (2024). Attention pyramid networks for object detection with semantic information fusion. International Journal on Semantic Web and Information Systems, 20(1). https://doi.org/10.4018/IJSWIS.359769
Search via ReFindit
Kantarcı, S. B. (2024). Android-App-for-Object-Detection. GitHub. https://github.com/kantarcise/Android-App-for-Object-Detection
Search via ReFindit
Khadka, R., Hassanzade, A., & Heilman, M. (2025). DREAMS: A Python-based framework for deep learning model card generation. SoftwareX, 22. https://doi.org/10.48550/arXiv.2409.17815
Search via ReFindit
Kühlechner, R., Zschech, P., Funk, A., Linden, M., & Krcmar, H. (2025). Object Detection Survey for Industrial Applications with Focus on Quality Control. TechRxiv. August 26, 2025. https://doi.org/10.36227/techrxiv.175616901.10303345/v1
Search via ReFindit
Lin, T.-Y., et al. (2025). MS COCO dataset. Papers With Code. https://paperswithcode.com/dataset/coco
Search via ReFindit
Mazuera-Rozo, C., Escobar-Velásquez, C., Espitia-Acero, J., Vega-Guzmán, D., Trubiani, C., Linares-Vásquez, M., & Bavota, G. (2022). Taxonomy of security weaknesses in Java and Kotlin Android apps. Journal of Systems and Software, 187, 111233. https://doi.org/10.1016/j.jss.2022.111233
Search via ReFindit
Mehra, S., Rajput, S., & Paul, J. (2022). Determinants of adoption of latest version smartphones: Theory and evidence. Technological Forecasting and Social Change, 175, 121410. https://doi.org/10.1016/j.techfore.2021.121410
Search via ReFindit
Mohammed, A., Goitia, D., Ahmad, S. A., & Ramlal, C. (2025). Revealing resilience: AI anomaly detection driven design considerations for Cyber Physical Systems supporting critical infrastructures in Small Island Developing States. Insights into Regional Development, 7(3), 148-169. https://doi.org/10.70132/p6489444663
Search via ReFindit
Mumuni, A., & Mumuni, F. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16, 100258. https://doi.org/10.1016/j.array.2022.100258
Search via ReFindit
Pulgarín-Ospina, M., Pineda-Rodriguez, P., & Castaño-Guerrero, J. (2024). Optimizing deep learning models for edge computing in mobile environments. Procedia Computer Science, 246, 2549–2557. https://doi.org/10.1016/j.procs.2024.09.443
Search via ReFindit
Qiao, L., Li, Y., Song, Y., Zhang, C., Dong, W., & Xu, C. (2021). DeFRCN: Decoupled Faster R-CNN for few-shot object detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). https://openaccess.thecvf.com/content/ICCV2021/papers/Qiao_DeFRCN_Decoupled_Faster_R-CNN_for_Few-Shot_Object_Detection_ICCV_2021_paper.pdf
Search via ReFindit
Reis, D., Neto, J. C., Haddad, D. B., & de Medeiros, M. F. (2023). Real-time flying object detection with YOLOv8. https://doi.org/10.48550/arXiv.2305.09972
Search via ReFindit
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510-4520). https://doi.org/10.48550/arXiv.1801.04381
Search via ReFindit
Singhal, K., et al. (2024). Object-Detection-In-Urban-Environment. GitHub. https://github.com/kksinghal/Object-Detection-In-Urban-Environment
Search via ReFindit
St-Hilaire, M.-O., & Carpentier-Roy, J. (2024). Urban-detection. GitHub. https://github.com/VilledeMontreal/urban-detection
Search via ReFindit
Tan, M., Pang, R., & Le, Q. (2019). EfficientDet: Scalable and efficient object detection. https://doi.org/10.48550/arXiv.1911.09070
Search via ReFindit
TensorFlow. (2024). Post-training quantization. https://www.tensorflow.org/lite/performance/post_training_quantization
Search via ReFindit
Ultralytics. VisDrone. Ultralytics YOLO Documentation. https://docs.ultralytics.com/datasets/detect/visdrone/
Search via ReFindit
V7. (2024). Mean average precision (mAP) explained: Everything you need to know. https://www.v7labs.com/blog/mean-average-precision
Search via ReFindit
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. https://doi.org/10.48550/arXiv.2207.02696
Search via ReFindit
Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. https://doi.org/10.48550/arXiv.2402.13616
Search via ReFindit
Wang, X., Tang, Z., Guo, J., Meng, T., Wang, C., Wang, T., & Jia, W. (2025). Empowering edge intelligence: A comprehensive survey on on-device AI models. ACM Computing Surveys, 1(1). https://doi.org/10.48550/arXiv.2503.06027
Search via ReFindit
Wang, Y., Wang, J., Zhang, W., Zhan, Y., Guo, S., Zheng, Q., & Wang, X. (2022). A survey on deploying mobile deep learning applications: A systemic and technical perspective. Digital Communications and Networks, 8(1), 1-17. https://doi.org/10.1016/j.dcan.2021.06.001
Search via ReFindit
RSS 1.0