{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:28:41Z","timestamp":1760232521703,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Robust and automated image segmentation in high-throughput image-based plant phenotyping has received considerable attention in the last decade. The possibility of this approach has not been well studied due to the time-consuming manual segmentation and lack of appropriate datasets. Segmenting images of greenhouse and open-field grown crops from the background is a challenging task linked to various factors such as complex background (presence of humans, equipment, devices, and machinery for crop management practices), environmental conditions (humidity, cloudy\/sunny, fog, rain), occlusion, low-contrast and variability in crops and pose over time. This paper presents a new ubiquitous deep learning architecture ThelR547v1 (Thermal RGB 547 layers version 1) that segmented each pixel as crop or crop canopy from the background (non-crop) in real time by abstracting multi-scale contextual information with reduced memory cost. By evaluating over 37,328 augmented images (aug1: thermal RGB and RGB), our method achieves mean IoU of 0.94 and 0.87 for leaves and background and mean Bf scores of 0.93 and 0.86, respectively. ThelR547v1 has a training accuracy of 96.27%, a training loss of 0.09, a validation accuracy of 96.15%, and a validation loss of 0.10. Qualitative analysis further shows that despite the low resolution of training data, ThelR547v1 successfully distinguishes leaf\/canopy pixels from complex and noisy background pixels, enabling it to be used for real-time semantic segmentation of horticultural crops.<\/jats:p>","DOI":"10.3390\/s22228807","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T02:36:40Z","timestamp":1668479800000},"page":"8807","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ThelR547v1\u2014An Asymmetric Dilated Convolutional Neural Network for Real-time Semantic Segmentation of Horticultural Crops"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5931-853X","authenticated-orcid":false,"given":"Md Parvez","family":"Islam","sequence":"first","affiliation":[{"name":"The United Graduate School of Agricultural Sciences, Ehime University, Matsuyama 790-8566, Ehime, Japan"},{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Kenji","family":"Hatou","sequence":"additional","affiliation":[{"name":"The United Graduate School of Agricultural Sciences, Ehime University, Matsuyama 790-8566, Ehime, Japan"},{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Takanori","family":"Aihara","sequence":"additional","affiliation":[{"name":"The United Graduate School of Agricultural Sciences, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Masaki","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Soki","family":"Okamoto","sequence":"additional","affiliation":[{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Shuhei","family":"Senoo","sequence":"additional","affiliation":[{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]},{"given":"Kirino","family":"Sumire","sequence":"additional","affiliation":[{"name":"Graduate School of Agriculture, Ehime University, Matsuyama 790-8566, Ehime, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.molp.2020.01.008","article-title":"Crop phenomics and high-throughput phenotyping: Past decades, current challenges, and future perspectives","volume":"13","author":"Yang","year":"2020","journal-title":"Mol. Plant."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/MSP.2015.2405111","article-title":"Image analysis: The new bottleneck in plant phenotyping (Applications Corner)","volume":"32","author":"Minervini","year":"2015","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"59741","DOI":"10.1109\/ACCESS.2021.3073715","article-title":"End to end segmentation of canola field images using dilated U-Net","volume":"9","author":"Ullah","year":"2021","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ko, T., and Lee, S. (2020). Novel method of semantic segmentation applicable to augmented reality. Sensors, 20.","DOI":"10.3390\/s20061737"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kaur, R., Hosseini, H.G., Sinha, R., and Lind\u00e9n, M. (2022). Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images. BMC Med. Imaging, 22.","DOI":"10.1186\/s12880-022-00829-y"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"630425","DOI":"10.3389\/fpls.2021.630425","article-title":"TheLNet270v1\u2013A novel deep-network architecture for the automatic classification of thermal images for greenhouse plants","volume":"12","author":"Islam","year":"2021","journal-title":"Front. Plant Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"17298814211007665","DOI":"10.1177\/17298814211007665","article-title":"Multilevel feature fusion dilated convolutional network for semantic segmentation","volume":"18","author":"Ku","year":"2021","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lin, X., Wa, S., Zhang, Y., and Ma, Q. (2022). A dilated segmentation network with the morphological correction method in farming area image Series. Remote Sens., 14.","DOI":"10.3390\/rs14081771"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kallipolitis, A., Revelos, K., and Maglogiannis, I. (2021). Ensembling EfficientNets for the classification and interpretation of histopathology images. Algorithms, 14.","DOI":"10.3390\/a14100278"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, L. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kuznichov, D., Zvirin, A., Honen, Y., and Kimmel, R. (2019). Data augmentation for leaf segmentation and counting tasks in rosette plants. arXiv.","DOI":"10.1109\/CVPRW.2019.00314"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. arXiv.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.scienta.2012.01.022","article-title":"Determining the emissivity of the leaves of nine horticultural crops by means of infrared thermography","volume":"137","author":"Valera","year":"2012","journal-title":"Sci. Hortic."},{"key":"ref_18","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Kavukcuoglu, K., Chintala, S., and LeCun, Y. (2013). Pedestrian detection with unsupervised multi-stage feature learning. arXiv.","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref_20","unstructured":"Dumoulin, V., and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, J., Wu, P., Tong, Y., Zhang, X., Lei, M., and Gao, J. (2021). Bearing fault diagnosis via improved one-dimensional multi-scale dilated CNN. Sensors, 21.","DOI":"10.3390\/s21217319"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Liu, Y., Gong, C., Chen, Y., and Yu, H. (2020). Applications of deep learning for dense scenes analysis in agriculture: A review. Sensors, 20.","DOI":"10.3390\/s20051520"},{"key":"ref_23","unstructured":"Ramachandran, P., Zoph, B., and Le, V.Q. (2017). Swish: A self-gated activation function. arXiv."},{"key":"ref_24","unstructured":"Nair, V., and Geoffrey, E.H. (2010, January 21\u201324). Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning, ICML, Haifa, Israel."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.isprsjprs.2009.06.004","article-title":"Object based image analysis for remote sensing","volume":"65","author":"Blaschke","year":"2010","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_26","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8807\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:18:11Z","timestamp":1760145491000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8807"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,15]]},"references-count":27,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228807"],"URL":"https:\/\/doi.org\/10.3390\/s22228807","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,11,15]]}}}