Derin Ogrenme kullanilarak Ses Sinyali FFT Spektrumlarina dayali Gemi Tipleri Siniflandirilmasi

Yıl 2023, Cilt: 10 Sayı: 1, 57 - 65, 31.01.2023

Mustafa Eren Yıldırım

https://doi.org/10.31202/ecjse.1149363

Öz

Gemi tiplerinin tanınmasi, denizcilik sektöründe ihtiyaç duyulan ve ilgi ceken bir uygulamadir. Literatürdeki çalışmaların büyük bir kısmı kıyı kameraları tarafından çekilen görüntülerin, radar görüntülerinin veya ses özelliklerinin kullanımına odaklanmıştır. Görüntü tabanlı tanıma durumunda, çok sayıda ve çeşitlilikte gemi görüntüsünün toplanması gerekir. Ses tabanlı tanıma durumunda ise, sistemlerin performansi arka plan gürültüsünden olumsuz etkilenebilir. Bu çalışma, görüntü tabanlı bir derin öğrenme ağı ile ses-frekans alanı özelliklerini kullanan bir yöntem sunmaktadir. Yöntem, gemilerin ses kayıtlarının hızlı Fourier dönüşümünü hesaplar ve elde edilen spektrumlari resim formatinda kaydeder. Bu resimler sınıflandırma için ResNet50 ağına verilir. Önerilen yöntemin performansını test etmek için dokuz farklı gemi tipine sahip erisime acik bir veri seti kullanılmıştır. Elde edilen sonuçlara göre onerilen metot %99 siniflandirma basarisi saglamistir.

Anahtar Kelimeler

Sinyal isleme, gemi tipi siniflandirma, ResNet50, mel frekansi kepstral katsayilari

Ship Type Recognition using Deep Learning with FFT Spectrums of Audio Signals

Öz

Ship type recognition has gained serious interest in applications required in the maritime sector. A large amount of the studies in literature focused on the use of images taken by shore cameras, radar images, and audio features. In the case of image-based recognition, a very large number and variety of ship images must be collected. In the case of audio-based recognition, systems may suffer from the background noise. In this study, we present a method, which uses the frequency domain characteristics with an image-based deep learning network. The method computes the fast Fourier transform of sound records of ships and generates the frequency vs magnitude graphs as images. Next, the images are given into the ResNet50 network for classification. A public dataset with nine different ship types is used to test the performance of the proposed method. According to the results, we obtained a 99% accuracy rate.

Anahtar Kelimeler

Signal Processing, Ship type recognition, ResNet50, MFCC

Kaynakça

• [1]. Xinqiang C., Yongsheng Y., W. Shengzheng, W. Huafeng, T. Jinjun, Z. Jiansen, W. Zhihuan, “Ship Type Recognition via a Coarse-to-Fine Cascaded Convolution Neural Network”. in The Journal of Navigation, 73(4),pp. 813-832, 2020.
• [2]. Chuang L. Z. H., C. Yujen, S. T. Tang, “A simple ship echo identification procedure with SeaSonde HF radar”. in Geoscience and Remote Sensing Letters IEEE, 12, pp. 2491–2495, 2015.
• [3]. Makedonas A., C. Theoharatos, V. Tsagarıs, V. Anastasopoulos, S. Costıcoglou, “Vessel classification in Cosmo-Skymed SAR data using hierarchical feature selection”. in The International Archives of Photogrammetry. Remote Sensing and Spatial Information Sciences, 40, pp. 975, 2015.
• [4]. Antelo J., G. Ambrosio, J. González-Jiménez, C. Galindo, “Ship Detection and Recognition in High-Resolution Satellite Images”. in Proceedings of IEEE International Geoscience & Remote Sensing Symposium, 2009.
• [5]. Kaçar U., D. Kumlu, M. Kırcı, “A Novel Approach for Automatic Ship Type Classification”. in Proceedings of the 23nd Signal Processing and Communications Applications Conference (SIU), 2015.
• [6]. Wu J., Y. Zhu, Z. Wang, Z. Song, X. Lıu, W. Wang, Z. Zhang, Y. Yu, Z. Xu, T. Zhang, J. Zhou, “A novel ship classification approach for high resolution SAR images based on the BDA-KELM classification model”. International Journal of Remote Sensing, 38, pp. 6457-6476, 2017.
• [7]. Singh K.K., M. Sıddhartha, A. Singh, “Diagnosis of Coronavirus Disease (COVID-19) from Chest X-Ray images using modified XceptionNet”. Romanian Journal of Information Science and Technology, 23(S), pp. 91-115, 2020.
• [8]. Ince Ö.F., I.F. Ince, M.E. Yıldırım, J.S. Park, J.K. Song, B.W. Yoon, “Human activity recognition with analysis of angles between skeletal joints using a RGB-depth sensor”. ETRI Journal, 42, pp. 78–89, 2020.
• [9]. Leung H.K., X.Z. Chen, C.W. Yu, H.Y. Lıang, J.Y. Wu, Y.L. Chen, “A Deep-Learning-Based Vehicle Detection Approach for Insufficient and Nighttime Illumination Conditions”. Applied Sciences, 9, pp. 4769-4795, 2019.
• [10]. Bentes C., A. Frost, D. Velotto, B. Tings, “Ship-iceberg Discrimination with Convolutional Neural Networks in High Resolution SAR Images”. in Proceedings of the 11th European Conference on Synthetic Aperture Radar, pp. 1–4, 2016.
• [11]. Dong C., J. Liu, F. Xu, C. Liu, “Ship Detection from Optical remote-sensing Images Using Multi-Scale Analysis and Fourier HOG Descriptor”. Remote Sensing, 11, pp. 1529-1547, 2019.
• [12]. Rainey K., J. Reeder, A. Corelli, Convolution neural networks for ship type recognition, SPIE Defense + Security, 984409, 2016.
• [13]. Feng Y.C., D. Wenhui, X. Sun, M.L Yan, X. Gao, “Towards Automated Ship Detection and Category Recognition from High-Resolution Aerial Images”. Remote Sensing, 11, pp. 1901-1923, 2019.
• [14]. Shen S., H. Yang, J. Li, G. Xu, M. Sheng, “Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data”. Entropy (Basel), 20(12), pp. 990-1003, 2018.
• [15]. Zhang L., D. Wu, X. Han, Z. Zhu, “Feature extraction of underwater target signal using Mel frequency cepstrum coefficients based on acoustic vector sensor”. Journal of Sensors,7864213, 2016.
• [16]. Tuncer T., E. Aydemır, “An Automated Local Binary Pattern Ship Identification Method by Using Sound”. Acta Infologica, 4(1), pp.57-63, 2020.
• [17]. Hladnık A., et al., “Fast Fourier Transform in Papermaking and Printing: Two Application Examples”. Acta Polytechnica Hungarica, 9(5), pp. 155-166, 2012.
• [18]. Smıth S.W., Chapter 8: The Discrete Fourier Transform. The Scientist and Engineer's Guide to Digital Signal Processing, 2nd ed., San Diego, Calif.: California Technical Publishing, 1999.
• [19]. Krizhevsky A., I. Sutskever, G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks”. in Proceedings of Neural Information Processing Systems, NIPS, 2012.
• [20]. Szegedy C., et al., “Going deeper with convolutions”. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, 2015.
• [21]. Sımonyan K. and A. ZISSERMAN, “Very deep convolutional networks for large-scale image recognition”. International Conference on Learning Representations (ICLR), 2015.
• [22]. Kaiming H., Z. Xiangyu, R. Shaoqing, S. Jian, “Deep Residual Learning for Image Recognition”. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.
• [23]. Chu Y., X. Yue, L.Yu, M. Sergei, Z. Wang, “Automatic Image Captioning Based on ResNet50 and LSTM with Soft Attention”. Wireless Communications and Mobile Computing 2020, ID8909458, 2020.
• [24]. Abadi M. et al., Tensorflow: Large-scale machine learning on heterogeneous systems, 2015.
• [25]. Chollet F. et. al., Keras, https://github.com/keras-team/keras, 2015.