{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:34:15Z","timestamp":1781076855196,"version":"3.54.1"},"reference-count":31,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T00:00:00Z","timestamp":1681516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute for Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["2020-0-00959"],"award-info":[{"award-number":["2020-0-00959"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents a benchmark analysis of NVIDIA Jetson platforms when operating deep learning-based 3D object detection frameworks. Three-dimensional (3D) object detection could be highly beneficial for the autonomous navigation of robotic platforms, such as autonomous vehicles, robots, and drones. Since the function provides one-shot inference that extracts 3D positions with depth information and the heading direction of neighboring objects, robots can generate a reliable path to navigate without collision. To enable the smooth functioning of 3D object detection, several approaches have been developed to build detectors using deep learning for fast and accurate inference. In this paper, we investigate 3D object detectors and analyze their performance on the NVIDIA Jetson series that contain an onboard graphical processing unit (GPU) for deep learning computation. Since robotic platforms often require real-time control to avoid dynamic obstacles, onboard processing with a built-in computer is an emerging trend. The Jetson series satisfies such requirements with a compact board size and suitable computational performance for autonomous navigation. However, a proper benchmark that analyzes the Jetson for a computationally expensive task, such as point cloud processing, has not yet been extensively studied. In order to examine the Jetson series for such expensive tasks, we tested the performance of all commercially available boards (i.e., Nano, TX2, NX, and AGX) with state-of-the-art 3D object detectors. We also evaluated the effect of the TensorRT library to optimize a deep learning model for faster inference and lower resource utilization on the Jetson platforms. We present benchmark results in terms of three metrics, including detection accuracy, frame per second (FPS), and resource usage with power consumption. From the experiments, we observe that all Jetson boards, on average, consume over 80% of GPU resources. Moreover, TensorRT could remarkably increase inference speed (i.e., four times faster) and reduce the central processing unit (CPU) and memory consumption in half. By analyzing such metrics in detail, we establish research foundations on edge device-based 3D object detection for the efficient operation of various robotic applications.<\/jats:p>","DOI":"10.3390\/s23084005","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T02:02:59Z","timestamp":1681696979000},"page":"4005","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis"],"prefix":"10.3390","volume":"23","author":[{"given":"Chungjae","family":"Choe","sequence":"first","affiliation":[{"name":"Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjae","family":"Choe","sequence":"additional","affiliation":[{"name":"Caterpillar Inc., Peoria, IL 61629, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1313-1347","authenticated-orcid":false,"given":"Sungwook","family":"Jung","sequence":"additional","affiliation":[{"name":"Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","article-title":"A survey on 3D object detection methods for autonomous driving applications","volume":"20","author":"Arnold","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.sysarc.2019.01.011","article-title":"A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platform","volume":"97","author":"Mittal","year":"2019","journal-title":"J. Syst. Archit."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., and Li, H. (2019, January 15\u201320). PointRCNN: 3D object proposal generation and detection from point cloud. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., and Li, H. (2020, January 13\u201319). PV-RCNN: Point-voxel feature set abstraction for 3D object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref_5","first-page":"2647","article-title":"From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network","volume":"43","author":"Shi","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Simony, M., Milzy, S., Amendey, K., and Gross, H.M. (2018, January 8\u201314). Complex-YOLO: An euler-region-proposal for real-time 3D object detection on point clouds. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Munich, Germany.","DOI":"10.1007\/978-3-030-11009-3_11"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., and Li, B. (2018). Second: Sparsely embedded convolutional detection. Sensors, 18.","DOI":"10.3390\/s18103337"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Tuzel, O. (2018, January 18\u201323). Voxelnet: End-to-end learning for Point Cloud based 3D object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., and Fu, C.W. (2020). CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud. arXiv.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., and Fu, C.W. (2021, January 20\u201325). SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"S\u00fczen, A.A., Duman, B., and \u015een, B. (2020, January 26\u201327). Benchmark analysis of Jetson TX2, Jetson Nano and Raspberry Pi using Deep-CNN. Proceedings of the 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey.","DOI":"10.1109\/HORA49412.2020.9152915"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jo, J., Jeong, S., and Kang, P. (2020, January 19\u201322). Benchmarking GPU-accelerated edge devices. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Republic of Korea.","DOI":"10.1109\/BigComp48618.2020.00-89"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ullah, S., and Kim, D.H. (2020, January 19\u201322). Benchmarking Jetson platform for 3D point-cloud and hyper-spectral image classification. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Republic of Korea.","DOI":"10.1109\/BigComp48618.2020.00-21"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16\u201321). Are we ready for autonomous driving? the KITTI vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref_15","unstructured":"Han, V. (2016, January 4\u20137). inference with tensorrt. Proceedings of the GPU Technology Conference, San Jose, CA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, S., Deng, X., Li, C., Liu, Y., and Jiang, H. (2022). Recognition-oriented image compressive sensing with deep learning. IEEE Trans. Multimed., Early Access.","DOI":"10.1109\/TMM.2022.3142952"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103776","DOI":"10.1016\/j.jvcir.2023.103776","article-title":"FFTI: Image inpainting algorithm via features fusion and two-steps inpainting","volume":"91","author":"Chen","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_18","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., and Kr\u00e4henb\u00fchl, P. (2021, January 20\u201325). Center-based 3D Object Detection and Tracking. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref_20","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., and Beijbom, O. (2019, January 15\u201320). PointPillars: Fast encoders for object detection from point clouds. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bokovoy, A., Muravyev, K., and Yakovlev, K. (September, January 31). Real-time vision-based depth reconstruction with nvidia jetson. Proceedings of the 2019 European Conference on Mobile Robots (ECMR), Bonn, Germany.","DOI":"10.1109\/ECMR.2019.8870936"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"62056","DOI":"10.1109\/ACCESS.2022.3181989","article-title":"TVENet: Transformer-based Visual Exploration Network for Mobile Robot in Unseen Environment","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107941","DOI":"10.1016\/j.knosys.2021.107941","article-title":"Deep embedded hybrid CNN\u2013LSTM network for lane detection on NVIDIA Jetson Xavier NX","volume":"240","author":"Kortli","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5332","DOI":"10.1109\/LRA.2021.3075141","article-title":"Run your visual\u2013inertial odometry on NVIDIA Jetson: Benchmark tests on a micro aerial vehicle","volume":"6","author":"Jeon","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_26","unstructured":"Dzung, N.M. (2021, September 13). Complex YOLOv4. Available online: https:\/\/github.com\/maudzung\/Complex-YOLOv4-Pytorch."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., and Beijbom, O. (2020, January 13\u201319). nuScenes: A multimodal dataset for autonomous driving. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref_28","unstructured":"CarkusL (2021, September 13). CenterPoint-PonintPillars Pytroch Model Convert to ONNX and TensorRT. Available online: https:\/\/github.com\/CarkusL\/CenterPoint."},{"key":"ref_29","unstructured":"Ghimire, D. (2021, September 13). Complex-YOLO-V3. Available online: https:\/\/github.com\/ghimiredhikura\/Complex-YOLOv3."},{"key":"ref_30","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","unstructured":"Bonghi, R. (2021, September 13). Jetson Stats. Available online: https:\/\/github.com\/rbonghi\/jetson_stats."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4005\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:16:19Z","timestamp":1760123779000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4005"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,15]]},"references-count":31,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23084005"],"URL":"https:\/\/doi.org\/10.3390\/s23084005","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,15]]}}}