{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:18:37Z","timestamp":1783351117726,"version":"3.54.6"},"reference-count":43,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,14]],"date-time":"2024-01-14T00:00:00Z","timestamp":1705190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"US Cotton Incorporated"},{"name":"US Georgia Peanut Commission"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The knowledge that precision weed control in agricultural fields can reduce waste and increase productivity has led to research into autonomous machines capable of detecting and removing weeds in real time. One of the driving factors for weed detection is to develop alternatives to herbicides, which are becoming less effective as weed species develop resistance. Advances in deep learning technology have significantly improved the robustness of weed detection tasks. However, deep learning algorithms often require extensive computational resources, typically found in powerful computers that are not suitable for deployment in robotic platforms. Most ground rovers and UAVs utilize embedded computers that are portable but limited in performance. This necessitates research into deep learning models that are computationally lightweight enough to function in embedded computers for real-time applications while still maintaining a base level of detection accuracy. This paper evaluates the weed detection performance of three real-time-capable deep learning models, YOLOv4, EfficientDet, and CenterNet, when run on a deep-learning-enabled embedded computer, an Nvidia Jetson Xavier AGX. We tested the accuracy of the models in detecting 13 different species of weeds and assesses their real-time viability through their inference speeds on an embedded computer compared to a powerful deep learning PC. The results showed that YOLOv4 performed better than the other models, achieving an average inference speed of 80 ms per image and 14 frames per second on a video when run on an imbedded computer, while maintaining a mean average precision of 93.4% at a 50% IoU threshold. Furthermore, recognizing that some real-world applications may require even greater speed, and that the detection program would not be the only task running on the embedded computer, a lightweight version of the YOLOv4 model, YOLOv4-tiny, was tested for improved performance in an embedded computer. YOLOv4-tiny impressively achieved an average inference speed of 24.5 ms per image and 52 frames per second, albeit with a slightly reduced mean average precision of 89% at a 50% IoU threshold, making it an ideal choice for real-time weed detection.<\/jats:p>","DOI":"10.3390\/s24020514","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T07:25:07Z","timestamp":1705303507000},"page":"514","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Evaluation of Inference Performance of Deep Learning Models for Real-Time Weed Detection in an Embedded Computer"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3426-4904","authenticated-orcid":false,"given":"Canicius","family":"Mwitta","sequence":"first","affiliation":[{"name":"College of Engineering, University of Georgia, Athens, GA 30602, USA"},{"name":"Department of Entomology, University of Georgia, Tifton, GA 31793, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2497-5422","authenticated-orcid":false,"given":"Glen C.","family":"Rains","sequence":"additional","affiliation":[{"name":"Department of Entomology, University of Georgia, Tifton, GA 31793, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Prostko","sequence":"additional","affiliation":[{"name":"Department of Crop and Soil Sciences, University of Georgia, Tifton, GA 31793, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1017\/S0021859605005708","article-title":"Crop Losses to Pests","volume":"144","author":"Oerke","year":"2006","journal-title":"J. Agric. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1614\/WT-06-130.1","article-title":"The Value of Herbicides in U.S. Crop Production","volume":"21","author":"Gianessi","year":"2007","journal-title":"Weed Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1614\/0043-1745(2000)048[0274:TAPCTA]2.0.CO;2","article-title":"Theoretical and Practical Challenges to an IPM Approach to Weed Management","volume":"48","author":"Buhler","year":"2000","journal-title":"Weed Sci."},{"key":"ref_4","unstructured":"Rueda-Ayala, V., Rasmussen, J., and Gerhards, R. (2010). Precision Crop Protection\u2014the Challenge and Use of Heterogeneity, Springer."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1017\/S0043174500079807","article-title":"A History of Weed Control in the United States and Canada","volume":"18","author":"Timmons","year":"1970","journal-title":"Weed Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1614\/0890-037X(2004)018[1563:COWSTW]2.0.CO;2","article-title":"Contributions of Weed Science to Weed Control and Management 1","volume":"18","author":"Hamill","year":"2004","journal-title":"Weed Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0065-2113(08)60253-9","article-title":"Herbicide Resistance: Impact and Management","volume":"58","author":"Powles","year":"1996","journal-title":"Adv. Agron."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1614\/WS-D-13-00109.1","article-title":"Lessons Learned from the History of Herbicide Resistance","volume":"62","author":"Shaner","year":"2014","journal-title":"Weed Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1080\/07352680590961649","article-title":"Benefits of Classical Biological Control for Managing Invasive Plants","volume":"24","author":"Culliney","year":"2005","journal-title":"Crit. Rev. Plant Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1111\/j.1365-3180.2006.00504.x","article-title":"Practical Experiences with a System for Site-Specific Weed Control in Arable Crops Using Real-Time Image Analysis and GPS-Controlled Patch Spraying","volume":"46","author":"Gerhards","year":"2006","journal-title":"Weed Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.compag.2018.08.043","article-title":"Robotic In-Row Weed Control in Vegetables","volume":"154","author":"Utstumo","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1002\/rob.21727","article-title":"Robot for Weed Species Plant-Specific Management","volume":"34","author":"Bawden","year":"2017","journal-title":"J. Field Robot."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"198","DOI":"10.20965\/jrm.2018.p0198","article-title":"Effect for a Paddy Weeding Robot in Wet Rice Culture","volume":"30","author":"Sori","year":"2018","journal-title":"J. Robot. Mechatron."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6094","DOI":"10.1080\/01431161.2013.793860","article-title":"Field Spectroscopy for Weed Detection in Wheat and Chickpea Fields","volume":"34","author":"Shapira","year":"2013","journal-title":"Int. J. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s11119-009-9126-0","article-title":"Discrimination of Corn, Grasses and Dicot Weeds by Their UV-Induced Fluorescence Spectral Signature","volume":"11","author":"Longchamps","year":"2010","journal-title":"Precis. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.compag.2017.07.028","article-title":"Maize and Weed Classification Using Color Indices with Support Vector Data Description in Outdoor Fields","volume":"141","author":"Zheng","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_17","first-page":"116","article-title":"Effective Plant Discrimination Based on the Combination of Local Binary Pattern Operators and Multiclass Support Vector Machine Methods","volume":"6","author":"Apopei","year":"2019","journal-title":"Inf. Process. Agric."},{"key":"ref_18","unstructured":"Zhu, W., and Zhu, X. (2009, January 20\u201322). The Application of Support Vector Machine in Weed Classification. Proceedings of the 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chechli\u0144ski, \u0141., Siemi\u0105tkowska, B., and Majewski, M. (2019). A System for Weeds and Crops Identification\u2014Reaching over 10 Fps on Raspberry Pi with the Usage of Mobilenets, Densenet and Custom Modifications. Sensors, 19.","DOI":"10.20944\/preprints201907.0115.v1"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.compag.2017.10.027","article-title":"Weed Detection in Soybean Crops Using ConvNets","volume":"143","author":"Pistori","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_21","first-page":"535","article-title":"Weed Detection in Canola Fields Using Maximum Likelihood Classification and Deep Convolutional Neural Network","volume":"7","author":"Asad","year":"2020","journal-title":"Inf. Process. Agric."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Peteinatos, G.G., Reichel, P., Karouta, J., And\u00fajar, D., and Gerhards, R. (2020). Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks. Remote Sens., 12.","DOI":"10.3390\/rs12244185"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Allmendinger, A., Spaeth, M., Saile, M., Peteinatos, G.G., and Gerhards, R. (2022). Precision Chemical Weed Management Strategies: A Review and a Design of a New CNN-Based Modular Spot Sprayer. Agronomy, 12.","DOI":"10.3390\/agronomy12071620"},{"key":"ref_24","first-page":"59","article-title":"Using Electric Current as a Weed Control Method","volume":"2","author":"Sahin","year":"2017","journal-title":"Eur. J. Eng. Technol. Res."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mwitta, C., Rains, G.C., and Prostko, E. (2022). Evaluation of Diode Laser Treatments to Manage Weeds in Row Crops. Agronomy, 12.","DOI":"10.3390\/agronomy12112681"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sivakumar, A.N.V., Li, J., Scott, S., Psota, E., Jhala, A.J., Luck, J.D., and Shi, Y. (2020). Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid-to Late-Season Weed Detection in UAV Imagery. Remote Sens., 12.","DOI":"10.3390\/rs12132136"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107091","DOI":"10.1016\/j.compag.2022.107091","article-title":"Performance Evaluation of Deep Transfer Learning on Multi-Class Identification of Common Weed Species in Cotton Production Systems","volume":"198","author":"Chen","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_28","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 14\u201319). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_30","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (November, January 27). CenterNet: Keypoint Triplets for Object Detection. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal Visual Object Classes (VOC) Challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A Survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A Comprehensive Survey on Transfer Learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_35","unstructured":"Redmon, J. (2021, February 04). Darknet: Open Source Neural Networks in C. Available online: https:\/\/pjreddie.com\/darknet\/."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft COCO: Common Objects in Context. Proceedings of the 13th European Conference on Computer Vision\u2013ECCV 2014, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_37","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA."},{"key":"ref_38","unstructured":"(2022, November 24). Fran\u00e7ois Chollet Keras, 2015. Available online: https:\/\/github.com\/keras-team\/keras."},{"key":"ref_39","unstructured":"TensorFlow (2022, March 14). TensorFlow 2 Model Zoo. Available online: https:\/\/github.com\/tensorflow\/models\/blob\/master\/research\/object_detection\/g3doc\/tf2_detection_zoo.md."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Rao, Y., He, L., and Zhu, J. (2017, January 18\u201321). A Residual Convolutional Neural Network for Pan-Shaprening. Proceedings of the RSIP 2017\u2014International Workshop on Remote Sensing with Intelligent Processing, Shanghai, China.","DOI":"10.1109\/RSIP.2017.7958807"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Padilla, R., Netto, S.L., Da Silva, E.A.B., and Netto, S.L. (2020, January 1\u20133). A Survey on Performance Metrics for Object-Detection Algorithms Compression of Power Systems Signals View Project A Survey on Performance Metrics for Object-Detection Algorithms. Proceedings of the 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Niteroi, Brazil.","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Del Rincon, J.M., and Miller, P. (2015, January 25\u201328). Data-Augmentation for Reducing Dataset Bias in Person Re-Identification. Proceedings of the AVSS 2015\u201412th IEEE International Conference on Advanced Video and Signal Based Surveillance, Karlsruhe, Germany.","DOI":"10.1109\/AVSS.2015.7301739"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1049\/cit2.12072","article-title":"An Attention-Based Cascade R-CNN Model for Sternum Fracture Detection in X-ray Images","volume":"7","author":"Jia","year":"2022","journal-title":"CAAI Trans. Intell. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/514\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:46:28Z","timestamp":1760103988000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,14]]},"references-count":43,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24020514"],"URL":"https:\/\/doi.org\/10.3390\/s24020514","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,14]]}}}