Data augmentation for haar cascade based automobile detection

• Autorzy: Pawełczyk M.
• Języki publikacji: EN

Abstrakty

EN

The article describes recent object detection methods with their main advantages and drawbacks and shows results of application of machine learning Haar Cascade algorithm for automobile detection. The article underlines problems related to the feature dataset generation and presents an overview of current dataset augmentation methods such as image mirroring, cropping, rotating, shearing and color modification. New methods fot image dataset augmentation, such as utilization of CAD models and Deep Learning solutions, are also proposed. In order to ensure low cost, real time detection machine learning based Haar Cascade detector has been proposed and tested on a custom dataset specifically created for dataset augmentation methods evalutation. Article provides all input parameters for detector training process, along with a brief description of object detection metrics. Finally the article presents results of the baseline detector and augumented calssificator created based on vertical image mirroring technique, for different dataset configurations. Algorithms performance for real time detection on high resolution images was also evaluated.

Słowa kluczowe

EN

automobile detection; object detection; Haar cascade; data augmentation

PL

kaskady klasyfikatorów Haara; detekcja; objekt

• Wydawca: Wydawnictwo Naukowe Sieci Badawczej Łukasiewicz - Przemysłowego Instytutu Motoryzacji
• Czasopismo: Archiwum Motoryzacji
• Rocznik: 2018
• Tom: Vol. 82, nr 4
• Strony: 117--129
• Opis fizyczny: Bibliogr. 15 poz., rys., tab.

Twórcy

autor

Pawełczyk M.

• Warsaw University of Technology, Faculty of Power and Aeronautical Engineering, Institute of Aviation, Nowowiejska 24, 00-665 Warszawa, Poland

Bibliografia

• [1] Başer E., Altun Y. Detection And Classification Of Vehicles In Traffic By Using Haar Cascade Classifier. Proceedings of the 58th ISERD International Conference, Prague, Czech Republic, December 2016.
• [2] Breckon T. P., Barnes S. E., Eichner M. L., Wahren K. Autonomous Real-time Vehicle Detection from a MediumLevel UAV. Proc. 24th International Unmanned Air Vehicle Systems, 29.1-29.9, 2009.
• [3] Capece N., Erra U., Scolamiero R. Converting Night-Time Images to Day-Time Images through a Deep Learning Approach. 2017 21st International Conference Information Visualisation (IV), London, 2017, 324-331, doi:10.1109/iV.2017.16.
• [4] Cheng H. Y., Weng Ch. Ch., Chen Y. Y. Vehicle detection in aerial surveillance using dynamic Bayesian networks. IEEE Transactions on Image Processing, vol. 21, no. 4, April 2012, pp. 2152-2159.
• [5] Haralick R. M., Shanmugam K. Texturial Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973; doi:10.1109/TSMC.1973.4309314.
• [6] Haar A. Zur Theorie der orthogonalen Funktionensysteme. Mathematische Annalen, 1910, 331–371.
• [7] Papageorgiou C., Oren M., Poggio T. A general framework for object detection. Proceedings of the IEEE International Conference on Computer Vision, February 1998, 555-562, doi: 10.1109/ICCV.1998.710772.
• [8] Pawełczyk M., Bibik P. Usage of modern engineering software in the design of unmanned rotorcraft. Prace Instytutu Lotnictwa eISSN 2300-5408 231, Warsaw 2013, 52-59.
• [9] Soo S. Object detection using haar-cascade classifier. Institute of Computer Science, University of Tartu, 2014, 1-12.
• [10] Tsai L. W., Hsieh J. W., Fan K. Ch. Vehicle detection using normalized color and edge map. IEEE Transactions on Image Processing, March 2007, 16; 3: 850-864.
• [11] Viola P., Jones M. Rapid Object Detection using a Boosted Cascade of Simple Features, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, doi:10.1109/CVPR.2001.990517.
• [12] Zhu J.-Y., Park T., Isola P., Efros A. A. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, 2017 IEEE International Conference on Computer Vision (ICCV), 2017, doi: 10.1109/ICCV.2017.244.
• [13] https://github.com/junyanz/CycleGAN.
• [14] https://github.com/tzutalin/labelImg.
• [15] https://software.intel.com/en-us/neural-compute-stick.