{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:51:15Z","timestamp":1777657875032,"version":"3.51.4"},"reference-count":38,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T00:00:00Z","timestamp":1678406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European High-Performance Computing Joint Undertaking (JU)","doi-asserted-by":"publisher","award":["951745"],"award-info":[{"award-number":["951745"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme and Germany, Italy, Slovenia, France, Spain","award":["951745"],"award-info":[{"award-number":["951745"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with camera and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detection of dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further development of the dataset and improvements in prediction models is needed.<\/jats:p>","DOI":"10.3390\/s23063002","type":"journal-article","created":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T03:35:42Z","timestamp":1678419342000},"page":"3002","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2418-4820","authenticated-orcid":false,"given":"Stevan","family":"Cakic","sequence":"first","affiliation":[{"name":"Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro"},{"name":"DigitalSmart, Bul. Dz. Vasingtona bb, 81000 Podgorica, Montenegro"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5245-3691","authenticated-orcid":false,"given":"Tomo","family":"Popovic","sequence":"additional","affiliation":[{"name":"Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro"},{"name":"DigitalSmart, Bul. Dz. Vasingtona bb, 81000 Podgorica, Montenegro"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7310-6063","authenticated-orcid":false,"given":"Srdjan","family":"Krco","sequence":"additional","affiliation":[{"name":"DunavNET, Bul. Oslobodjenja 133\/2, 21000 Novi Sad, Serbia"}]},{"given":"Daliborka","family":"Nedic","sequence":"additional","affiliation":[{"name":"DunavNET, Bul. Oslobodjenja 133\/2, 21000 Novi Sad, Serbia"}]},{"given":"Dejan","family":"Babic","sequence":"additional","affiliation":[{"name":"Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro"}]},{"given":"Ivan","family":"Jovovic","sequence":"additional","affiliation":[{"name":"Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,10]]},"reference":[{"key":"ref_1","unstructured":"FAO (2018). The Future of Food and Agriculture: Alternative Pathways to 2050, Food and Agriculture Organization of the United Nations."},{"key":"ref_2","unstructured":"USDA (2023, January 20). Livestock and Poultry: World Markets and Trade, Available online: https:\/\/www.fas.usda.gov\/data\/livestock-and-poultry-world-markets-and-trade."},{"key":"ref_3","unstructured":"ETP4HPC (2022). Strategic Research Agenda for High-Performance Computing in Europe: European HPC Research Priorities 2022\u20132027, European Technology Platform for High Performance Computing, NS Oegstgeest."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Cakic, S., Popovic, T., Krco, S., and Nedic, D. (2022, January 1\u20133). Babic, Developing Object Detection Models for Camera Applications in Smart Poultry Farms. Proceedings of the 2022 IEEE International Conference on Omni-layer Intelligent Systems (COINS), Barcelona, Spain.","DOI":"10.1109\/COINS54846.2022.9854975"},{"key":"ref_5","unstructured":"FF4EuroHPC (2023, January 20). HPC Innovation for European SMEs. Available online: https:\/\/cordis.europa.eu\/project\/id\/951745."},{"key":"ref_6","first-page":"12116","article-title":"Do Vision Transformers See Like Convolutional Neural Networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_7","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 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_8","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_9","first-page":"21","article-title":"SSD: Single Shot MultiBox Detector","volume":"9905","author":"Liu","year":"2016","journal-title":"ECCV"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kim, J., Sung, J., and Park, S. (2020, January 1\u20133). Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition. Proceedings of the 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), Seoul, Republic of Korea.","DOI":"10.1109\/ICCE-Asia49877.2020.9277040"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s13735-020-00195-x","article-title":"A survey on instance segmentation: State of the art","volume":"9","author":"Hafiz","year":"2020","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cao, L., Xiao, Z., Liao, X., Yao, Y., Wu, K., Mu, J., Li, J., and Pu, H. (2021). Automated Chicken Counting in Surveillance Camera Environments Based on the Point Supervision Algorithm: LC-DenseFCN. Agriculture, 11.","DOI":"10.3390\/agriculture11060493"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., and Schmidt, M. (2018, January 8\u201314). Where Are the Blobs: Counting by Localization with Point Supervision. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yang, X., Chai, L., Bist, R.B., Subedi, S., and Wu, Z. (2022). A Deep Learning Model for Detecting Cage-Free Hens on the Litter Floor. Animals, 12.","DOI":"10.3390\/ani12151983"},{"key":"ref_17","first-page":"3189691","article-title":"An Evaluation of Deep Learning Methods for Small Object Detection","volume":"2020","author":"Nguyen","year":"2020","journal-title":"Electr. Comput. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108049","DOI":"10.1109\/ACCESS.2019.2933060","article-title":"Automated Individual Pig Localisation, Tracking and Behaviour Metric Extraction Using Deep Learning","volume":"7","author":"Cowton","year":"2019","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.13031\/trans.13607","article-title":"Automatic Monitoring of Chicken Movement and Drinking Time Using Convolutional Neural Networks","volume":"63","author":"Lin","year":"2020","journal-title":"Trans. ASABE"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"110819","DOI":"10.1016\/j.measurement.2022.110819","article-title":"ChickTrack\u2014A quantitative tracking tool for measuring chicken activity","volume":"191","author":"Neethirajan","year":"2022","journal-title":"Measurement"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104840","DOI":"10.1016\/j.compag.2019.05.049","article-title":"Automated pig counting using deep learning","volume":"163","author":"Tian","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"O\u00f1oro-Rubio, D., and L\u00f3pez-Sastre, R.J. (2016, January 11\u201314). Towards Perspective-Free Object Counting with Deep Learning. Proceedings of the Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105300","DOI":"10.1016\/j.compag.2020.105300","article-title":"Automated cattle counting using mask R-CNN in Quadcopter Vision System","volume":"171","author":"Xu","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, H.-W., Chen, C.-H., Tsai, Y.-C., Hsieh, K.-W., and Lin, H.-T. (2021). Identifying Images of Dead Chickens with a Chicken Removal System Integrated with a Deep Learning Algorithm. Sensors, 21.","DOI":"10.3390\/s21113579"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yao, Y., Yu, H., Mu, J., Li, J., and Pu, H. (2020). Estimation of the Gender Ratio of Chickens Based on Computer Vision: Dataset and Exploration. Entropy, 22.","DOI":"10.3390\/e22070719"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, J., Su, H., Zheng, X., Liu, Y., Zhou, R., Xu, L., Liu, Q., Liu, D., Wang, Z., and Duan, X. (2022). Study of a QueryPNet Model for Accurate Detection and Segmentation of Goose Body Edge Contours. Animals, 12.","DOI":"10.3390\/ani12192653"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"208","DOI":"10.26599\/BDMA.2021.9020004","article-title":"AIPerf: Automated Machine Learning as an AI-HPC Benchmark","volume":"4","author":"Ren","year":"2021","journal-title":"Big Data Min. Anal."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., and Doll\u00e1r, P. (2014, January 6\u201312). Microsoft COCO: Common Objects in Context. Proceedings of the in Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_29","unstructured":"(2023, January 20). Detectron2 vs. Yolov5. Which One Suits Your Use Case Better?. Available online: https:\/\/medium.com\/ireadrx\/detectron2-vs-yolov5-which-one-suits-your-use-case-better-d959a3d4bdf."},{"key":"ref_30","unstructured":"(2023, January 20). Object Detection: Speed and Accuracy Comparison (Faster R-CNN, R-FCN, SSD, FPN, RetinaNet and YOLOv3). Available online: https:\/\/jonathan-hui.medium.com\/object-detection-speed-and-accuracy-comparison-faster-r-cnn-r-fcn-ssd-and-yolo-5425656ae359."},{"key":"ref_31","unstructured":"(2023, January 20). Detectron2 Package. Available online: https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Buber, E., and Diri, B. (2018, January 25\u201327). Performance Analysis and CPU vs. GPU Comparison for Deep Learning. Proceedings of the 2018 6th International Conference on Control Engineering & Information Technology (CEIT), Istanbul, Turkey.","DOI":"10.1109\/CEIT.2018.8751930"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Yoo, A., Jette, M., and Grondona, M. (2003, January 24). SLURM: Simple Linux Utility for Resource Management. Proceedings of the 9th International Workshop, JSSPP 2003, Seattle, WA, USA.","DOI":"10.1007\/10968987_3"},{"key":"ref_34","unstructured":"(2023, January 20). Yotta Advanced Computing Provider. Available online: https:\/\/www.yac.hr\/."},{"key":"ref_35","unstructured":"(2023, January 20). Coco Dataset Metrics. Available online: https:\/\/cocodataset.org\/#detection-eval."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019). Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression. arXiv.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref_37","unstructured":"(2023, January 20). Why Parallelized Training Might Not Be Working for You. Available online: https:\/\/towardsdatascience.com\/why-parallelized-training-might-not-be-working-for-you-4c01f606ef2c."},{"key":"ref_38","unstructured":"(2023, January 20). agroNET\u2014Digital Farming Management. Available online: https:\/\/digitalfarming.eu\/."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3002\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:51:49Z","timestamp":1760122309000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,10]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23063002"],"URL":"https:\/\/doi.org\/10.3390\/s23063002","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,10]]}}}