{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T03:21:00Z","timestamp":1772594460668,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2022,5,15]],"date-time":"2022-05-15T00:00:00Z","timestamp":1652572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences"},{"name":"Engineering Research Council of Canada (NSERC)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>River ice segmentation, used for surface ice concentration estimation, is important for validating river processes and ice-formation models, predicting ice jam and flooding risks, and managing water supply and hydroelectric power generation. Furthermore, discriminating between anchor ice and frazil ice is an important factor in understanding sediment transport and release events. Modern deep learning techniques have proved to deliver promising results; however, they can show poor generalization ability and can be inefficient when hardware and computing power is limited. As river ice images are often collected in remote locations by unmanned aerial vehicles with limited computation power, we explore the performance-latency trade-offs for river ice segmentation. We propose a novel convolution block inspired by both depthwise separable convolutions and local binary convolutions giving additional efficiency and parameter savings. Our novel convolution block is used in a shallow architecture which has 99.9% fewer trainable parameters, 99% fewer multiply\u2013add operations, and 69.8% less memory usage than a UNet, while achieving virtually the same segmentation performance. We find that the this network trains fast and is able to achieve high segmentation performance early in training due to an emphasis on both pixel intensity and texture. When compared to very efficient segmentation networks such as LR-ASPP with a MobileNetV3 backbone, we achieve good performance (mIoU of 64) 91% faster during training on a CPU and an overall mIoU that is 7.7% higher. We also find that our network is able to generalize better to new domains such as snowy environments.<\/jats:p>","DOI":"10.3390\/rs14102378","type":"journal-article","created":{"date-parts":[[2022,5,15]],"date-time":"2022-05-15T09:48:22Z","timestamp":1652608102000},"page":"2378","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Efficient Shallow Network for River Ice Segmentation"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2017-772X","authenticated-orcid":false,"given":"Daniel","family":"Sola","sequence":"first","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L G31, Canada"}]},{"given":"K. Andrea","family":"Scott","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L G31, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"7570","DOI":"10.1109\/TGRS.2020.2981082","article-title":"River ice segmentation with deep learning","volume":"58","author":"Singh","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.coldregions.2008.09.006","article-title":"An Overview of River Ice Problems: CRIPE07 Guest Editorial","volume":"55","author":"Hicks","year":"2009","journal-title":"Cold Regions Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.coldregions.2007.09.001","article-title":"Progress in the study and management of river ice jams","volume":"51","author":"Beltaos","year":"2008","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.coldregions.2018.08.014","article-title":"Support vector machine learning applied to digital images of river ice conditions","volume":"155","author":"Kalke","year":"2018","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3181","DOI":"10.1002\/hyp.321","article-title":"Regulation effects on the lower Peace River, Canada","volume":"15","author":"Peters","year":"2001","journal-title":"Hydrol. Process."},{"key":"ref_6","unstructured":"Piesold, K. (2011). Fluvial Geomorphology and Sediment Transport Technical Data Report, BC Hydro."},{"key":"ref_7","unstructured":"Kalke, H., Loewen, M., McFarlane, V., and Jasek, M. (2015, January 18\u201320). Observations of anchor ice formation and rafting of sediments. Proceedings of the 18th Workshop on the Hydraulics of Ice Covered Rivers, Quebec City, QC, Canada."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.coldregions.2017.09.003","article-title":"The transport of sediments by released anchor ice","volume":"143","author":"Kalke","year":"2017","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_9","unstructured":"Ansari, S., Rennie, C.D., Clark, S.P., and Seidou, O. (2019, January 14\u201316). Application of a Fast Superpixel Segmentation Algorithm in River Ice Classification. Proceedings of the 20th Workshop on the Hydraulics of Ice Covered Rivers, Ottawa, ON, Canada."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, X., Jin, J., Lan, Z., Li, C., Fan, M., Wang, Y., Yu, X., and Zhang, Y. (2020). ICENET: A semantic segmentation deep network for river ice by fusing positional and channel-wise attentive features. Remote Sens., 12.","DOI":"10.3390\/rs12020221"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, Y., Jin, J., Wang, Y., Fan, M., Wang, N., and Zhang, Y. (2021). ICENETv2: A Fine-Grained River Ice Semantic Segmentation Network Based on UAV Images. Remote Sens., 13.","DOI":"10.3390\/rs13040633"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Van Beeck, K., Tuytelaars, T., Scarramuza, D., and Goedem\u00e9, T. (2018, January 8\u201314). Real-time embedded computer vision on UAVs. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-11012-3_1"},{"key":"ref_13","first-page":"156","article-title":"Fast depth prediction and obstacle avoidance on a monocular drone using probabilistic convolutional neural network","volume":"32","author":"Yang","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jiao, Z., Zhang, Y., Xin, J., Mu, L., Yi, Y., Liu, H., and Liu, D. (2019, January 22\u201326). A deep learning based forest fire detection approach using UAV and YOLOv3. Proceedings of the 2019 1st International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China.","DOI":"10.1109\/ICIAI.2019.8850815"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"107938","DOI":"10.1016\/j.agrformet.2020.107938","article-title":"A near real-time deep learning approach for detecting rice phenology based on UAV images","volume":"287","author":"Yang","year":"2020","journal-title":"Agric. For. Meteorol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nagi, A.S., Kumar, D., Sola, D., and Scott, K.A. (2021). RUF: Effective Sea Ice Floe Segmentation Using End-to-End RES-UNET-CRF with Dual Loss. Remote Sens., 13.","DOI":"10.3390\/rs13132460"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1080\/1088937X.2020.1766592","article-title":"Sea-ice information and forecast needs for industry maritime stakeholders","volume":"43","author":"Wagner","year":"2020","journal-title":"Polar Geogr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.coldregions.2017.06.011","article-title":"Automated monitoring of river ice processes using shore-based imagery","volume":"142","author":"Ansari","year":"2017","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_19","unstructured":"Bharathi, P., and Subashini, P. (2013, January 7\u20138). Texture based color segmentation for infrared river ice images using K-means clustering. Proceedings of the 2013 International Conference on Signal Processing, Image Processing & Pattern Recognition, Coimbatore, India."},{"key":"ref_20","unstructured":"Kalke, H., and Loewen, M. (2017, January 9\u201312). Predicting surface ice concentration using machine learning. Proceedings of the 19th Workshop on the Hydraulics of Ice Covered Rivers, Whitehorse, YT, Canada."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European conference on computer vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_23","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep Learning With Depthwise Separable Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18\u201323). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019, January 27\u201328). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Juefei-Xu, F., Naresh Boddeti, V., and Savvides, M. (2017, January 21\u201326). Local binary convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.456"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1109\/TPAMI.2006.244","article-title":"Face description with local binary patterns: Application to face recognition","volume":"28","author":"Ahonen","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V. (2019, January 15\u201320). Mnasnet: Platform-aware neural architecture search for mobile. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref_32","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_35","unstructured":"Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). Enet: A deep neural network architecture for real-time semantic segmentation. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., and Sang, N. (2018, January 8\u201314). Bisenet: Bilateral segmentation network for real-time semantic segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Li, H., Xiong, P., Fan, H., and Sun, J. (2019, January 16\u201317). Dfanet: Deep feature aggregation for real-time semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00975"},{"key":"ref_38","unstructured":"Chen, W., Gong, X., Liu, X., Zhang, Q., Li, Y., and Wang, Z. (2019). Fasterseg: Searching for faster real-time semantic segmentation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. (2018, January 18\u201323). Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref_40","unstructured":"Krishnamoorthi, R. (2018). Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv."},{"key":"ref_41","unstructured":"Frankle, J., and Carbin, M. (2018). The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv."},{"key":"ref_42","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_43","unstructured":"Singh, A., Kalke, H., Loewen, M., and Ray, N. (2019). Alberta River Ice Segmentation Dataset, IEEE Dataport."},{"key":"ref_44","unstructured":"Schindler, A., Lidy, T., and Rauber, A. (2016, January 23\u201324). Comparing Shallow versus Deep Neural Network Architectures for Automatic Music Genre Classification. Proceedings of the FMT, St. Polten, Austria."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Pasupa, K., and Sunhem, W. (2016, January 5\u20136). A comparison between shallow and deep architecture classifiers on small dataset. Proceedings of the 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), Yogyakarta, Indonesia.","DOI":"10.1109\/ICITEED.2016.7863293"},{"key":"ref_46","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_47","first-page":"26","article-title":"Divide the gradient by a running average of its recent magnitude","volume":"42","author":"Tieleman","year":"2012","journal-title":"COURSERA Neural Netw. Mach. Learn."},{"key":"ref_48","unstructured":"Bradski, G. (2000). Dr. Dobb\u2019s Journal of Software Tools, The OpenCV Library\u2019."},{"key":"ref_49","unstructured":"Kr\u00e4henb\u00fchl, P., and Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. Advances in Neural Information Processing Systems 24 (NIPS 2011), Proceedings of the 24th International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 12\u201315 December 2011, Curran Associates Inc."},{"key":"ref_50","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_51","unstructured":"Singh, A. (2021). River_ice_segmentation. GitHub Repository, GitHub."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/10\/2378\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:10:57Z","timestamp":1760137857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/10\/2378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,15]]},"references-count":51,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["rs14102378"],"URL":"https:\/\/doi.org\/10.3390\/rs14102378","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,15]]}}}