Evaluation of Image Transmission Strategies on Edge Server-Based Centralized Object Detection Systems

Firmansyah Achmad  Adam; Bambang  Harjito; Fajar  Muslim

doi:10.52436/1.jutif.2026.7.3.5731

Authors

Firmansyah Achmad Adam Informatics Study Program, Sebelas Maret University. Indonesia
Bambang Harjito Informatics Study Program, Sebelas Maret University. Indonesia
Fajar Muslim Informatics Study Program, Sebelas Maret University. Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.3.5731

Keywords:

End-To-End Latency, HTTP POST Snapshot, MJPEG Streaming, Raspberry Pi, Server-Based Object Detection

Abstract

Urban waste management in smart city development requires efficient and stable visual monitoring systems. Utilization of edge devices such as Raspberry Pi is often constrained by limited computational power for complex computer vision models, making edge server architecture a relevant solution. This study evaluates the performance of image transmission from a Raspberry Pi to a centralized server for YOLOv8 object detection by comparing MJPEG streaming and HTTP POST-based periodic snapshot methods. Evaluation metrics included median latency (p50), jitter, and tail latency (p95 and p99). The results indicate that MJPEG streaming provides more stable latency compared to snapshots, particularly at tight transmission intervals. The transmission interval proved to have a significant effect on inference pipeline stability, while image resolution showed no observable impact on latency distribution under the evaluated conditions. This research recommends selecting appropriate transmission strategies to maintain the reliability of visual monitoring systems. These findings provide practical guidance for designing reliable centralized visual monitoring systems in resource-constrained edge environments.

Downloads

Download data is not yet available.

References

S. Wan et al., “Insights into the urban municipal solid waste generation during the COVID-19 pandemic from machine learning analysis,” Sustainable Cities and Society, vol. 100, Jan. 2024, doi: 10.1016/j.scs.2023.105044.

[2] A. A. Ravindran, “Edge Computing Systems for Streaming Video Analytics: Trail Behind and the Paths Ahead,” 2023, doi: 10.20944/preprints202308.0383.v1.

[3] X. R. Huang, S. S. Yang, W. S. Chen, Y. Q. Zhang, C. T. Lee, and L. B. Chen, “An IoT-Based Smart Trash Cans Monitoring System,” in 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), 2021, pp. 623–624, doi: 10.1109/GCCE53005.2021.9621358.

[4] G. Liu et al., “An adaptive DNN inference acceleration framework with end–edge–cloud collaborative computing,” Future Generation Computer Systems, vol. 140, pp. 422–435, Mar. 2023, doi: 10.1016/j.future.2022.10.033.

[5] H. Kim, J. S. Choi, J. Kim, and J. H. Ko, “A DNN partitioning framework with controlled lossy mechanisms for edge-cloud collaborative intelligence,” Future Generation Computer Systems, vol. 154, pp. 426–439, May 2024, doi: 10.1016/j.future.2024.01.006.

[6] G. Rong, Y. Xu, X. Tong, and H. Fan, “An edge-cloud collaborative computing platform for building AIoT applications efficiently,” Journal of Cloud Computing, vol. 10, no. 1, Dec. 2021, doi: 10.1186/s13677-021-00250-w.

[7] D. G. Lema, R. Usamentiaga, and D. F. García, “Quantitative comparison and performance evaluation of deep learning-based object detection models on edge computing devices,” Integration, vol. 95, Mar. 2024, doi: 10.1016/j.vlsi.2023.102127.

[8] Y. Wang, G. Zhong, Y. Duan, Y. Cheng, M. Yin, and R. Yang, “Efficient and privacy-preserving deep inference towards cloud–edge collaborative,” Applied Soft Computing, vol. 180, Aug. 2025, doi: 10.1016/j.asoc.2025.113381.

[9] Y. Ma, Y. Wang, and B. Tang, “Joint Optimization of Model Partitioning and Resource Allocation for Multi-Exit DNNs in Edge-Device Collaboration,” Electronics, vol. 14, no. 8, Apr. 2025, doi: 10.3390/electronics14081647.

[10] Z. Cao, Y. Cheng, Z. Zhou, Y. Chen, Y. Hu, A. Lu, J. Liu, and Z. Li, “Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator,” IEEE Transactions on Mobile Computing, 2024, doi: 10.1109/TMC.2024.3474743.

[11] A. Ghotbou and M. Khansari, “VE-CoAP: A constrained application layer protocol for IoT video transmission,” Journal of Network and Computer Applications, vol. 173, Jan. 2021, doi: 10.1016/j.jnca.2020.102855.

[12] A. Ghotbou and M. Khansari, “Comparing application layer protocols for video transmission in IoT low power lossy networks: an analytic comparison,” Wireless Networks, vol. 27, no. 1, pp. 269–283, Jan. 2021, doi: 10.1007/s11276-020-02453-6.

[13] Y. Jiang, P. Zhao, C. Zhao, and J. Lin, “Towards bandwidth efficient edge–cloud collaborative deep learning with Data Importance driven Compression,” Neurocomputing, vol. 650, Oct. 2025, doi: 10.1016/j.neucom.2025.130835.

[14] B. Diallo, A. Ouamri, and M. Keche, “A Hybrid Approach for WebRTC Video Streaming on Resource-Constrained Devices,” Electronics, vol. 12, no. 18, Sep. 2023, doi: 10.3390/electronics12183775.

[15] J. Nakazato, K. Nakagawa, K. Itoh, R. Fontugne, M. Tsukada, and H. Esaki, “WebRTC over 5G: A Study of Remote Collaboration QoS in Mobile Environment,” Journal of Network and Systems Management, vol. 32, no. 1, Mar. 2024, doi: 10.1007/s10922-023-09778-5.

[16] J. Ma, B. Shang, H. Song, Y. Huang, and P. Fan, “Reliability Versus Latency in IIoT Visual Applications: A Scalable Task Offloading Framework,” IEEE Internet of Things Journal, vol. 9, no. 17, pp. 16726–16735, Sep. 2022, doi: 10.1109/JIOT.2022.3148115.

[17] Y. Bandung et al., “Performance Evaluation of CoAP Communication Method Extensions in Internet of Video Things,” Journal of Advances in Information Technology, vol. 16, no. 7, pp. 1017–1029, 2025, doi: 10.12720/jait.16.7.1017-1029.

[18] L. Lu, Z. Chen, R. Wang, L. Liu, and H. Chi, “Yolo-inspection: defect detection method for power transmission lines based on enhanced YOLOv5s,” Journal of Real-Time Image Processing, vol. 20, no. 5, Oct. 2023, doi: 10.1007/s11554-023-01360-1.

[19] Z. Lei, Y. Zhang, J. Wang, and M. Zhou, “Cloud-Edge Collaborative Defect Detection Based on Efficient Yolo Networks and Incremental Learning,” Sensors, vol. 24, no. 18, Sep. 2024, doi: 10.3390/s24185921.

S. Nazir and M. Kaleem, “Object classification and visualization with edge artificial intelligence for a customized camera trap platform,” Ecological Informatics, vol. 79, Mar. 2024, doi: 10.1016/j.ecoinf.2023.102453.

N. Saha, P. Paul, K. Ji, and R. Harik, “Performance evaluation framework of MQTT client libraries for IoT applications in manufacturing,” Manufacturing Letters, vol. 41, pp. 1237–1245, 2024.

C. Caiazza, V. Luconi, and A. Vecchio, “Energy consumption of smartphones and IoT devices when using different versions of the HTTP protocol,” Pervasive Mob. Comput., vol. 97, Jan. 2024, doi: 10.1016/j.pmcj.2023.101871.

M. Naseri et al., “Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability, Throughput, and Latency,” arXiv:2411.10650, 2024.

X. Yang, Z. Wang, Z. Qin, and X. Tao, “Timeliness-Aware Joint Source and Channel Coding for Adaptive Image Transmission,” arXiv:2509.19754, 2025.

G. Ma, H. Tong, N. Yang, and C. Yin, “Attention-based UNet enabled Lightweight Image Semantic Communication System over Internet of Things,” arXiv:2401.07329, 2024.