{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:59:06Z","timestamp":1780448346838,"version":"3.54.1"},"reference-count":38,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11774379"],"award-info":[{"award-number":["11774379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Low-frequency multi-source direction-of-arrival (DOA) estimation has been challenging for micro-aperture arrays. Deep learning (DL)-based models have been introduced to this problem. Generally, existing DL-based methods formulate DOA estimation as a multi-label multi-classification problem. However, the accuracy of these methods is limited by the number of grids, and the performance is overly dependent on the training data set. In this paper, we propose an off-grid DL-based DOA estimation. The backbone is based on circularly fully convolutional networks (CFCN), trained by the data set labeled by space-frequency pseudo-spectra, and provides on-grid DOA proposals. Then, the regressor is developed to estimate the precise DOAs according to corresponding proposals and features. In this framework, spatial phase features are extracted by the circular convolution calculation. The improvement in spatial resolution is converted to increasing the dimensionality of features by rotating convolutional networks. This model ensures that the DOA estimations at different sub-bands have the same interpretation ability and effectively reduce network model parameters. The simulation and semi-anechoic chamber experiment results show that CFCN-based DOA is superior to existing methods in terms of generalization ability, resolution, and accuracy.<\/jats:p>","DOI":"10.3390\/s21082767","type":"journal-article","created":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T15:30:39Z","timestamp":1618414239000},"page":"2767","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Off-Grid DOA Estimation Based on Circularly Fully Convolutional Networks (CFCN) Using Space-Frequency Pseudo-Spectrum"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4398-9077","authenticated-orcid":false,"given":"Wenqiong","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1853-5903","authenticated-orcid":false,"given":"Yiwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfei","family":"Tong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8486-2377","authenticated-orcid":false,"given":"Ming","family":"Bao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/79.526899","article-title":"Two decades of array signal processing research: The parametric approach","volume":"13","author":"Krim","year":"1996","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Trees, H.L.V. (2002). Introduction. Optimum Array Processing, John Wiley & Sons. Chapter 1.","DOI":"10.1002\/0471221104.ch1"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1365","DOI":"10.3390\/s150101365","article-title":"Cooperative Surveillance and Pursuit Using Unmanned Aerial Vehicles and Unattended Ground Sensors","volume":"15","author":"Fargeas","year":"2015","journal-title":"Sensors"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","article-title":"Multiple emitter location and signal parameter estimation","volume":"34","author":"Schmidt","year":"1986","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/29.32276","article-title":"ESPRIT-estimation of signal parameters via rotational invariance techniques","volume":"37","author":"Roy","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6407","DOI":"10.1109\/TSP.2015.2465302","article-title":"Performance Analysis of an Improved MUSIC DoA Estimator","volume":"63","author":"Vallet","year":"2015","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_7","unstructured":"Zhou, L., Zhao, Y., and Cui, H. (2008, January 20\u201323). High resolution wideband DOA estimation based on modified MUSIC algorithm. Proceedings of the 2008 International Conference on Information and Automation, Changsha, China."},{"key":"ref_8","first-page":"58","article-title":"Algorithm on high resolution DOA estimation under condition of unknown number of signal sources","volume":"26","author":"Ying","year":"2005","journal-title":"J. China Inst. Commun."},{"key":"ref_9","first-page":"981","article-title":"Underwater Multi-source DOA Estimation under Condition of Unknown Number of Signals","volume":"21","author":"Tuo","year":"2009","journal-title":"Comput. Simul."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wan, F., Wen, J., and Liang, L. (2020, January 28\u201331). A Source Number Estimation Method Based on Improved Eigenvalue Decomposition Algorithm. Proceedings of the 2020 IEEE 20th International Conference on Communication Technology (ICCT), Nanning, China.","DOI":"10.1109\/ICCT50939.2020.9295790"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3010","DOI":"10.1109\/TSP.2005.850882","article-title":"A sparse signal reconstruction perspective for source localization with sensor arrays","volume":"53","author":"Malioutov","year":"2005","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/TSP.2012.2222378","article-title":"Off-Grid Direction of Arrival Estimation Using Sparse Bayesian Inference","volume":"61","author":"Yang","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1109\/JSTSP.2011.2159773","article-title":"Sparse Signal Recovery With Temporally Correlated Source Vectors Using Sparse Bayesian Learning","volume":"5","author":"Zhang","year":"2011","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_14","first-page":"1178","article-title":"Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation","volume":"21","author":"Agatonovi","year":"2012","journal-title":"Radio Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Agatonovic, M., Stankovic, Z., and Milovanovic, B. (2012, January 26\u201330). High resolution two-dimensional DOA estimation using artificial neural networks. Proceedings of the 2012 6th European Conference on Antennas and Propagation (EUCAP), Prague, Czech Republic.","DOI":"10.1109\/EuCAP.2012.6206729"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1002\/ecja.20295","article-title":"2D DOA estimation using beam steering antenna by the switched parasitic elements and RBF neural network","volume":"89","author":"Matsumoto","year":"2006","journal-title":"Electron. Commun. Jpn. (Part I Commun.)"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"741","DOI":"10.2528\/PIER13012114","article-title":"Efficient neural network approach for 2D doa estimation based on antenna array measurements","volume":"137","author":"Agatonovic","year":"2013","journal-title":"Prog. Electromagn. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TAP.2009.2037766","article-title":"On the Design of a Compact Neural Network-Based DOA Estimation System","volume":"58","author":"Fonseca","year":"2010","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1109\/8.475924","article-title":"Direction finding in phased arrays with a neural network beamformer","volume":"43","author":"Southall","year":"1995","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.1109\/TAP.2005.850735","article-title":"A smart antenna system for direction of arrival estimation based on a support vector regression","volume":"53","author":"Pastorino","year":"2005","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, H., Gui, G., Sari, H., and Adachi, F. (2018, January 27\u201330). Deep Learning for Super-Resolution DOA Estimation in Massive MIMO Systems. Proceedings of the 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall), Chicago, IL, USA.","DOI":"10.1109\/VTCFall.2018.8691023"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"7315","DOI":"10.1109\/TAP.2018.2874430","article-title":"Direction-of-Arrival Estimation Based on Deep Neural Networks with Robustness to Array Imperfections","volume":"66","author":"Liu","year":"2018","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, D., Yin, J., and Wu, Y. (2018). A Direct Position-Determination Approach for Multiple Sources Based on Neural Network Computation. Sensors, 18.","DOI":"10.3390\/s18061925"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/JSTSP.2019.2901664","article-title":"Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals","volume":"13","author":"Chakrabarty","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yao, Y., Lei, H., and He, W. (2020). A-CRNN-Based Method for Coherent DOA Estimation with Unknown Source Number. Sensors, 20.","DOI":"10.3390\/s20082296"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/JSTSP.2019.2900164","article-title":"CRNN-Based Multiple DoA Estimation Using Acoustic Intensity Features for Ambisonics Recordings","volume":"13","author":"Perotin","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"19859","DOI":"10.1038\/s41598-020-76608-y","article-title":"Super resolution DOA estimation based on deep neural network","volume":"10","author":"Liu","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/TCSVT.2020.2986402","article-title":"RefineDet++: Single-Shot Refinement Neural Network for Object Detection","volume":"31","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chung, H., Seo, H., Joo, J., Lee, D., and Kim, S. (2021). Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network. Energies, 14.","DOI":"10.3390\/en14010228"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Smith, L.N. (2017, January 27\u201329). Cyclical Learning Rates for Training Neural Networks. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.","DOI":"10.1109\/WACV.2017.58"},{"key":"ref_32","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy."},{"key":"ref_33","unstructured":"Stoeckle, C., Munir, J., Mezghani, A., and Nossek, J.A. (2015, January 3\u20135). DoA Estimation Performance and Computational Complexity of Subspace- and Compressed Sensing-based Methods. Proceedings of the 19th International ITG Workshop on Smart Antennas (WSA 2015), Ilmenau, Germany."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., and Sun, J. (2015, January 7\u201312). Convolutional neural networks at constrained time cost. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhen, P., Liu, B., Cheng, Y., Chen, H.B., and Yu, H. (2019, January 7\u20139). Fast video facial expression recognition by deeply tensor-compressed LSTM neural network on mobile device. Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing, Washington, DC, USA.","DOI":"10.1145\/3318216.3363322"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Amert, T., Otterness, N., Yang, M., Anderson, J.H., and Smith, F.D. (2017, January 5\u20138). GPU Scheduling on the NVIDIA TX2: Hidden Details Revealed. Proceedings of the IEEE Real-Time Systems Symposium (RTSS), Paris, France.","DOI":"10.1109\/RTSS.2017.00017"},{"key":"ref_37","first-page":"3033","article-title":"Angle of Arrival Estimation Through a Full-Hardware Approach for Adaptive Beamforming","volume":"67","author":"Avitabile","year":"2020","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3447","DOI":"10.1109\/TSP.2008.920469","article-title":"A Consistent Metric for Performance Evaluation of Multi-Object Filters","volume":"56","author":"Schuhmacher","year":"2008","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/8\/2767\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:47:59Z","timestamp":1760161679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/8\/2767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,14]]},"references-count":38,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,4]]}},"alternative-id":["s21082767"],"URL":"https:\/\/doi.org\/10.3390\/s21082767","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,14]]}}}