Classification of Human and Vehicles with The Deep Learning Based on Transfer Learning Method

Abstract

There has been a significant increase in the use of deep learning algorithms in recent years. Convolutional neural network (CNN), one of the deep learning models, is frequently used in applications to distinguish important objects such as humans and vehicles from other objects, especially in image processing. After the ImageNet Large Scale Visual Recognition Competition (ILSVRC) in 2012, the use of ESA in applications is becoming quite common. With the development of image processing hardware, the image processing process is significantly reduced. Thanks to these developments, the performance of studies on deep learning is increasing. In this study, a system based on deep learning has been developed to detect and classify objects (human, car and motorcycle / bicycle) from images captured by drones. Two datasets, the image set of Stanford University and the drone image set created at Afyon Kocatepe University (AKÜ), are used to train and test the deep neural network with the transfer learning method. Training and testing processes are carried out using a total of 3841 images, 2591 from the Stanford dataset and 1250 from the AKÜ dataset. The precision, recall and f1 score values are evaluated according to the process of determining and classifying human, car and motorcycle / bicycle classes using GoogleNet, VggNet and ResNet50 deep learning algorithms. According to this evaluation result, high performance results are obtained with 0.916 precision, 0.895 recall and 0.906 f1 score value in the ResNet50 model.

Keywords

• Deep Learning
• Object Detection
• CNN

Derin Öğrenme Tabanlı Transfer Öğrenme Yöntemiyle İnsan ve Araçların Sınıflandırılması

Abstract

Son yıllarda derin öğrenme algoritmalarının kullanımında önemli bir artış görülmektedir. Uygulamalarda derin öğrenme modellerinden evrişimli sinir ağı (ESA) özellikle görüntü işlemede insan ve araç gibi önemli nesneleri diğer nesnelerden ayırmak için sıklıkla kullanılmaktadır. Görüntü işleme donanımlarının gelişmesiyle görüntü işleme süreci önemli ölçüde azaltılmaktadır. Bu gelişmeler sayesinde derin öğrenme üzerine yapılan çalışmaların performansı artmaktadır. Bu çalışmada, dronlar tarafından elde edilen görüntülerden nesneleri (insan, araba ve motosiklet/bisiklet) tespit etmek ve sınıflandırmak için derin öğrenmeye dayalı bir sistem geliştirilmiştir. Derin sinir ağının transfer öğrenme yöntemiyle eğitilmesi ve test edilmesi için açık kaynak olan Stanford Üniversitesi görüntü seti ve Afyon Kocatepe Üniversitesi (AKÜ)’nde oluşturulan drone görüntü seti olmak üzere iki veri seti kullanılmıştır. GoogleNet, VggNet ve ResNet50 derin öğrenme algoritmaları kullanılarak insan, araba ve motosiklet/bisiklet sınıflarını tespit etme ve sınıflandırma işlemine göre kesinlik, duyarlılık ve f1 skor değerleri değerlendirilmiştir. Bu değerlendirme sonucuna göre ResNet50 modelinde 0,916 kesinlik, 0,895 hassasiyet ve 0,906 f1 skor değeriyle performansı yüksek sonuçlar elde edilmiştir.
Anahtar Kelimeler: Derin öğrenme, Nesne tespiti, CNN

Keywords

• Derin Öğrenme
• Nesne Tespiti
• CNN

References

1. [1] P. Panchal, G. Prajapati, S. Patel, H. Shah, and J. Nasriwala, "A review on object detection and tracking methods," International Journal for Research in Emerging Science and Technology, vol. 2, no. 1, pp. 7-12, 2015.
2. (2] H. Li, Z. Wu, and J. Zhang, "Pedestrian detection based on deep learning model," In 2016 9th International Congress on Image and Signal Processing, Bio Medical Engineering and Informatics, 2016, pp. 796-800.
3. [3] M. Hassanalian, and A. Abdelkefi, "Classifications, applications, and design challenges of drones: A review," Progress in Aerospace Sciences, vol. 91, pp. 99-131, 2017.
4. [4] U. Shah, and A. Harpale, "A Review of Deep Learning Models for Computer Vision," In 2018 IEEE Punecon, Pune, India, pp. 1-6, 2018.
5. [5] M. F. Haque, H. Y. Lim, and D. S. Kang, "Object Detection Based on VGG with ResNet Network," In 2019 International Conference on Electronics, Information, and Communication, Auckland, New Zealand, pp. 1-3, 2019.
6. [6] Y. C. Chang, H. T. Chen, J. H. Chuang, and I. C. Liao, "Pedestrian Detection in Aerial Images Using Vanishing Point Transformation and Deep Learning," In 2018 25th IEEE International Conference on Image Processing, Athens, Greece, pp.1917-1921, 2018.
7. [7] H. Song, I. K. Choi, M.S. Ko, J. Bae, S. Kwak, and J. Yoo, "Vulnerable pedestrian detection and tracking using deep learning," In 2018 International Conference on Electronics, Information, and Communication, Honolulu, USA, pp. 1-2, 2018.
8. [8] Y. Li, Z. Ding, C. Zhang, Y. Wang, and J. Chen, "SAR Ship Detection Based on Resnet and Transfer Learning," In IGARSS 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, pp. 1188-1191, 2019.

9. [9] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
10. [10] L. Deng, and D. Yu, "Deep learning: methods and applications," Foundations and Trends in Signal Processing, 2014, vol. 7, no. 3–4, pp. 197-387, 2014.
11. [11] C. Kyrkou, G. Plastiras, T. Theocharides, S. I. Venieris, and C. S. Bouganis, "DroNet: Efficient convolutional neural network detector for real-time UAV applications," In 2018 Design, Automation & Test in Europe Conference & Exhibition, Dresden, Germany, pp. 967-972, 2018.
12. [12] K. K. Çevik, and A. Çakı, "Görüntü İşleme Yöntemleriyle Araç Plakalarının Tanınarak Kapı Kontrolünün Gerçekleştirilmesi," Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, vol. 10, no. 1, pp. 31-38, 2010.
13. [13] F. Bayram, "Derin öğrenme tabanlı otomatik plaka tanıma," Politeknik Dergisi, vol. 23 , no. 4, pp. 955 - 960, 2020.
14. [14] A. Kızrak, and B. Bolat, "Derin Öğrenme ile Kalabalık Analizi Üzerine Detaylı Bir Araştırma,” Bilişim Teknolojileri Dergisi, vol.11, pp. 263-286, 2018.
15. [15] E. Cengil, and A. Çınar, “A New Approach for Image Classification: Convolutional Neural Network,” European Journal of Technic, vol. 6, no. 2, pp. 96-103, 2016.
16. [16] W. Rawat, and Z. Wang, "Deep convolutional neural networks for image classification: A comprehensive review," Neural computation, vol. 29 no. 9, pp. 2352-2449, 2017.
17. [17] T. Pala, U. Güvenç, H. T. Kahraman, İ. Yücedağ, and Y. Sönmez, "Comparison of Pooling Methods for Handwritten Digit Recognition Problem," In 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), pp. 1-5, 2018.
18. [18] S. Ioffe, and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," In International conference on machine learning, pp. 448-456, 2015.
19. [19] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, 1929-1958, 2014.
20. [20] Y. LeCun, L. D. Jackel, L. Bottou, C. Cortes, J. S. Denker, H. Drucker, and V. Vapnik, "Learning algorithms for classification: A comparison on handwritten digit recognition," Neural Networks: The Statistical Mechanics Perspective, New Jersey, USA, 261-276, 1995.
21. [21] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, and A. Rabinovich, "Going deeper with convolutions," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015.
22. [22] K. He, X. Zhang, S. Ren, and J.Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, USA, pp. 770-778, 2016.
23. [23] E. Cengiz, C. Yılmaz, H. T. Kahraman, and F. Bayram, "Pedestrian and Vehicles Detection with ResNet in Aerial Images," 4th. International Symposium on Innovative Approaches in Engineering and Natural Sciences, Samsun, Turkey, pp. 416-419, 2019.
24. [24] T. Tang, Z. Deng, S. Zhou, L. Lei, and H. Zou, "Fast vehicle detection in UAV images," In 2017 International Workshop on Remote Sensing with Intelligent Processing, Shanghai, China, pp. 1-5, 2017.
25. [25] J. H. Yoo, H. I. Yoon, H. G.Kim, H. S. Yoon, and S. S. Han, "Optimization of Hyper-parameter for CNN Model using Genetic Algorithm," In 2019 1st International Conference on Electrical, Control and Instrumentation Engineering (ICECIE), pp. 1-6, 2019.