Benchmark Analysis of YOLO Performance on Edge Intelligence Devices
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
In the 5G intelligent edge scenario, more and more accelerator-based single-board computers (SBCs) with low power consumption and high performance are being used as edge devices to run the inferencing part of the artificial intelligence (AI) model to deploy intelligent applications. In this paper, we investigate the inference workflow and performance of the You Only Look Once (YOLO) network, which is the most popular object detection model, in three different accelerator-based SBCs, which are NVIDIA Jetson Nano, NVIDIA Jetson Xavier NX and Raspberry Pi 4B (RPi) with Intel Neural Compute Stick2 (NCS2). Different video contents with different input resize windows are detected and benchmarked by using four different versions of the YOLO model across the above three SBCs. By comparing the inference performance of the three SBCs, the performance of RPi + NCS2 is more friendly to lightweight models. For example, the FPS of detected videos from RPi + NCS2 running YOLOv3-tiny is 7.6 times higher than that of YOLOv3. However, in terms of detection accuracy, we found that in the process of realizing edge intelligence, how to better adapt a AI model to run on RPi + NCS2 is much more complex than the process of Jetson devices. The analysis results indicate that Jetson Nano is a trade-off SBCs in terms of performance and cost; it achieves up to 15 FPSs of detected videos when running YOLOv4-tiny, and this result can be further increased by using TensorRT.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Specifically, previous works have not systematically identified the batch size regimes at which GPU memory pressure leads to inference engine failures or runtime instability.”
From Benchmarking YOLOv8 Variants for Object Detection Efficiency on Jetson Orin NX for Edge Computing Applications (2026) · cites this paper as [26]
Citations
Cites
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., & Zomaya, A. Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2984887 · Cited by 1,147
YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
Huang, R., Pedoeem, J., & Chen, C. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8621865 · Cited by 622
The ApolloScape Open Dataset for Autonomous Driving and Its Application
Huang, X., Wang, P., Cheng, X., Zhou, D., Geng, Q., & Yang, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2926463 · Cited by 615
The ApolloScape Open Dataset for Autonomous Driving and its Application
Huang, X., Wang, P., Cheng, X., Zhou, D., Geng, Q., & Yang, R. (2018) · arXiv · doi:10.48550/arxiv.1803.06184 · Cited by 615
YOLO v3-Tiny: Object Detection and Recognition using one stage improved model
Adarsh, P., Rathi, P., & Kumar, M. (2020) · 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs48705.2020.9074315 · Cited by 545
Edge-Computing-Enabled Smart Cities: A Comprehensive Survey
Khan, L. U., Yaqoob, I., Tran, N. H., Kazmi, S. M. A., Dang, T. N., & Hong, C. S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2987070 · Cited by 475
Zheng, Y.-Y., Kong, J.-L., Jin, X.-B., Wang, X.-Y., Su, T.-L., & Zuo, M. (2019) · Sensors · doi:10.3390/s19051058 · Cited by 462
Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
Li, E., Zhou, Z., & Chen, X. (2018) · Proceedings of the 2018 Workshop on Mobile Edge Communications · doi:10.1145/3229556.3229562 · Cited by 385
A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platform
Mittal, S. (2019) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.01.011 · Cited by 294
Benchmark Analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN
Suzen, A. A., Duman, B., & Sen, B. (2020) · 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA) · doi:10.1109/hora49412.2020.9152915 · Cited by 263
Deep learning for edge computing applications: A State-of-the-Art survey
Wang, F., Zhang, M., Wang, X., Ma, X., & Liu, J. (2020) · IEEE Access · doi:10.1109/access.2020.2982411 · Cited by 259
A Novel Framework for Mobile-Edge Computing by Optimizing Task Offloading
Naouri, A., Wu, H., Nouri, N. A., Dhelim, S., & Ning, H. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3064225 · Cited by 209
Towards Enabling Critical mMTC: A Review of URLLC Within mMTC
Pokhrel, S. R., Ding, J., Park, J., Park, O.-S., & Choi, J. (2020) · IEEE Access · doi:10.1109/access.2020.3010271 · Cited by 207
A survey of techniques for optimizing deep learning on gpus
Mittal, S., & Vaishay, S. (2019) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.101635 · Cited by 197
Deep Learning for Reliable Mobile Edge Analytics in Intelligent Transportation Systems: An Overview
Ferdowsi, A., Challita, U., & Saad, W. (2019) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2018.2883777 · Cited by 191
A deep-learning-based computer vision solution for construction vehicle detection
Arabi, S., Haghighat, A. K., & Sharma, A. (2020) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12530 · Cited by 189
The Smart Image Recognition Mechanism for Crop Harvesting System in Intelligent Agriculture
Horng, G.-J., Liu, M.-X., & Chen, C. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2954287 · Cited by 123
Wireless Network Intelligence at the Edge
Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2941458 · Cited by 92
Resource Characterisation of Personal-Scale Sensing Models on Edge Accelerators
Antonini, M., Vu, T. H., Min, C., Montanari, A., Mathur, A., & Kawsar, F. (2019) · International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT) · doi:10.1145/3363347.3363363 · Cited by 63
Embedded Low-Power Processor for Personalized Stress Detection
Attaran, N., Puranik, A., Brooks, J., & Mohsenin, T. (2018) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2018.2799821 · Cited by 56
Design of a Scalable and Fast YOLO for Edge-Computing Devices
Han, B.-G., Lee, J.-G., Lim, K.-T., & Choi, D.-H. (2020) · Sensors · doi:10.3390/s20236779 · Cited by 52
Benchmarking GPU-Accelerated Edge Devices
Jo, J., Jeong, S., & Kang, P. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-89 · Cited by 51
Basulto-Lantsova, A., Padilla-Medina, J. A., Pérez-Pinal, F. J., & Gutiérrez, A. I. B. (2020) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc47524.2020.9031166 · Cited by 43
5G PPP Architecture Working Group - View on 5G Architecture, Version 3.0
Redana, S., Bulakçı, Ö., Mannweiler, C., Gallo, L., Κουσαρίδας, Α., Navratil, D., Tzanakaki, A., Gutiérrez, J., Karl, H., Hasselmeyer, P., et al. (2019) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3265030 · Cited by 38
Sahu, P., Yu, D., & Qin, H. (2018) · SPIE Medical Imaging: Imaging Informatics for Healthcare, Research, and Applications · doi:10.1117/12.2293350 · Cited by 36
Developing an AI IoT application with open software on a RISC-V SoC
Torres-Sanchez, E., Alastruey-Benedé, J., & Moreno, E. F. T. (2020) · Conference on Design of Circuits and Integrated Systems · doi:10.1109/dcis51330.2020.9268645 · Cited by 34
A Taste of Scientific Computing on the GPU-Accelerated Edge Device
Kang, P., & Lim, S. (2020) · IEEE Access · doi:10.1109/access.2020.3038714 · Cited by 19
Multi-Camera-Based Person Recognition System for Autonomous Tractors
Jung, T.-H., Cates, B., Choi, I.-K., Lee, S., & Choi, J. (2020) · Designs · doi:10.3390/designs4040054 · Cited by 17
Deep Learning Algorithms for Emotion Recognition on Low Power Single Board Computers
Srinivasan, V., Meudt, S., & Schwenker, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20984-1_6 · Cited by 11
Edge computing for 5G networks - white paper
Guillen, D. A., Sayadi, B., Bisson, P., et al. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3698117 · Cited by 11
Edge computing for 5G networks - white paper
Guillen, D. A., Sayadi, B., Bisson, P., Wary, J. P., Lønsethagen, H., Antón, C., de la Oliva, A., Kaloxylos, A., & Frascolla, V. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3698116 · Cited by 11
Face recognition systems based on Neural Compute Stick 2, CPU, GPU comparison
Aleksandrova, O., & Bashkov, Y. (2020) · IEEE International Conference on Advanced Trends in Information Theory (ATIT) · doi:10.1109/atit50783.2020.9349313 · Cited by 9
GPU acceleration design method for driver's seatbelt detection
Jing, Y., TS(吴天舒), W., Li, J., ZJ(张志佳), Z., & Gao, C. (2019) · Cited by 1
Research works printed but not linked: 3
- Nair, D., Pakdaman, A., and Plöger, P. (2020). Performance Evaluation of Low-Cost Machine Vision Cameras for Image-Based Grasp Verification. arXiv.
- Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
- Bochkovskiy, A., Wang, C., and Liao, H.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
Cited by
Edge deep learning in computer vision and medical diagnostics: a comprehensive survey
Xu, Y., Khan, T. M., Song, Y., & Meijering, E. H. W. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11033-5 · Cited by 236
Kamath, V. P., & Renuka, A. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.006 · Cited by 128
Disclosing Edge Intelligence: A Systematic Meta-Survey
Barbuto, V., Savaglio, C., Chen, M., & Fortino, G. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7010044 · Cited by 80
Chan, C. C., Alvi, S. A., Zhou, X., Durrani, S., Wilson, N., & Yebra, M. (2024) · IEEE Access · doi:10.1109/access.2024.3501336 · Cited by 77
Bartoň, M., Budjač, R., Tanuška, P., Gašpar, G., & Schreiber, P. P. (2022) · Applied Sciences · doi:10.3390/app12115672 · Cited by 70
Metadata
- Authors
- Feng, H., Mu, G., Zhong, S., Zhang, P., & Yuan, T.
- Affiliations
- Shenzhen University (CN)
- Corresponding author
- Zhong, Shida
- Venue
- Cryptography
- Publisher
- MDPI AG
- Published
- 2022-04-01
- Volume
- 6
- Issue
- 2
- Pages
- 16
- ISSN
- 2410-387X (ISSN-L)
- OpenAlex
- W4225714398
- Cited by
- 100
- References
- 33
- Citations by year
- 2026: 21 · 2025: 28 · 2024: 20 · 2023: 25 · 2022: 6
- FWCI
- 6.46
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Cryptography (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Guangdong Provincial Department of Science and Technology (No.2020B1212030002)
- Shenzhen Science and Technology Innovation Commission (No.KQTD20180412181337494 and No.JSGG20201103095805016)
- National Key Research and Development Program (No.2019YFF0216602)
- Key Area Project of Department of Education of Guangdong Province, China (No.2021ZDZX4008)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Keywords
- YOLO, object detection, edge computing, single-board computer, Jetson Nano, Jetson Xavier NX, Raspberry Pi 4B, YOLOv3-tiny, YOLOv4-tiny, TensorRT, lightweight models, detection accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.