Object detection and tracking methods: A comprehensive review

Yıl 2017, Cilt: 6 Sayı: 2, 40 - 49, 16.12.2017

Kazım Hanbay , Hüseyin Üzen

Öz

Image processing is a method for reading, extracting, and processing
important data in a digital image. One of the fundamental part of the image
processing is collecting knowledge acquisition about recognized objects and
environments in the image like human vision system. Many methods are developed
to meet the needs of detection, identification, classification and tracking of
objects in images. Especially, finding the target object in the
images and following this object in the future time periods is frequently used
in many applications. One of the main problems which makes object tracking and
analysis difficult is tracking the object in a changing environments. Several
effective methods are developed in order to solve these kinds of problems. In
this paper, current and widely used methods for object tracking are discussed
and those methods were examined with their strengths and weaknesses.

Anahtar Kelimeler

Object tracking, background subtraction, object detection, performance analysis, object classification

Nesne tespit ve takip metotları: Kapsamlı bir derleme

Öz

Görüntü işleme dijital bir görüntü içerisindeki önemli
bilgilerin okunması, çıkartılması ve işlenmesi için kullanılan bir yöntemdir. Görüntü
içerisinde bulunan bir nesne ya da bir ortam hakkında insan görme sistemine
benzer şekilde nitel bilgiler edinilmesi ve kullanılması görüntü işlemenin
temel amaçlarındandır. Görüntülerde bulunan nesnelerin tespiti,
tanımlanması, sınıflandırılması ve takibi gibi ihtiyaçları karşılayacak birçok
yöntem geliştirilmiştir. Özellikle görüntülerdeki
hedef nesnenin bulunması ve ileriki zaman dilimlerinde bu nesnenin
kaybedilmemesi birçok alandaki uygulamalarda sıklıkla kullanılmaktadır.
Takip edilecek nesnenin değişken bir ortam içinde bulunması nesne takibi ve
analizini zorlaştıran temel problemdir. Bu problemleri çözmek
ve nesnenin başarılı bir şekilde takip edilmesi için birçok farklı yöntem
gelişmiştir. Bu çalışmada nesne takibi için güncel ve
yaygın kullanılan yöntemler ele alınmıştır. İncelenen
yöntemler güçlü/zayıf yönleri ile irdelenmiştir.

Anahtar Kelimeler

Nesne izleme, arka plan çıkarma, nesne algılama, performans analizi, nesne sınıflandırması

Kaynakça

• [1] Hjelmås E., Kee L.B., Face Detection: A Survey,Computer vision and image understanding, 83, 236–274., 2001
• [2] Anagnostopoulos C.-N.E., Anagnostopoulos I.E., Psoroulas I.D., Loumos, V., Kayafas, E., License Plate Recognition From Still Images and Video Sequences: A Survey,IEEE Transactions on intelligent transportation systems, 9, 3:377–391, 2008
• [3] Balaji S.R., KarthikeyanS.,A survey on moving object tracking using image processing, 2017 11th International Conference on Intelligent Systems and Control (ISCO), IEEE, pp. 469–474, 2017
• [4] Wang D., Unsupervised video segmentation based on watersheds and temporal tracking,IEEE Transactions on Circuits and Systems for video Technology, 8.5:539–546, 1998
• [5] Chen Y., Yang X., Zhong B., Pan S., et al., CNNTracker: Online discriminative object tracking via deep convolutional neural network,Applied Soft Computing, 38:1088–1098, 2016
• [6] Luo W., Xing J., Milan A., Zhang X., Multiple Object Tracking: A Literature Review,arXiv Prepr. arXiv1409.7618, 2014
• [7] Risha K.P., Kumar A.C., Novel Method of Detecting Moving Object in Video,Procedia Technology, 24:1055–1060, 2016
• [8] Avidan S., Support vector tracking,IEEE transactions on pattern analysis and machine intelligence, 26.8: 1064-1072, 2004
• [9] Hinton G., Deng L., Yu D., Dahl G., Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups,IEEE Signal Processing Magazine, 29.6: 82-97, 2012
• [10] Krizhevsky A., Sutskever I., Hinton G.E., ImageNet Classification with Deep Convolutional Neural Networks, In: Advances in neural information processing systems, p. 1097-1105,2012
• [11] Szegedy C., Liu W., Jia Y., Sermanet P., Going Deeper With Convolutions, In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1–9, 2015
• [12] Taigman, Y., Yang, M., Ranzato, M., Wolf, L., DeepFace: Closing the gap to human-level performance in face verification, In: Proceedings of the IEEE conference on computer vision and pattern recognition, p. 1701-1708, 2014
• [13] Wu Y., Lim J., Yang M.-H., Online Object Tracking: A Benchmark, In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2411-2418, 2013
• [14] Karasulu B., Videolardaki Hareketli Nesnelerin Tespit Ve Takibi İçin Uyarlanabilir Arkaplan Çıkarımı Yaklaşımı Tabanlı Bir Sistem,Uludağ Üniversitesi Mühendislik-Mimarlık Fakültesi Dergis, 18, 2013
• [15] Shaikh S.H., Saeed K., Chaki N.,Moving Object Detection Approaches, Challenges and Object Tracking, In: Moving Object Detection Using Background Subtraction. Springer International Publishing, p. 5-14, 2014
• [16] Aldhaheri A.R., Edirisinghe E.A., Detection and Classification of a Moving Object in a Video Stream, In: Proc. of the Intl. Conf. on Advances in Computing and Information Technology-ACIT, 2014.
• [17] Hardas A., Vibha M., Moving Object Detection using Background Subtraction Shadow Removal and Post Processing,Int. J. Comput. Appl., 975–8887, 2015
• [18] Li G., Wang Y., Shu W., Real-Time Moving Object Detection for Video Monitoring Systems, In: Intelligent Information Technology Application, 2008. IITA'08. Second International Symposium on, IEEE, pp. 163–166, 2008
• [19] Martin C., Background Subtraction Using Running Gaussian Average: a Color Channel Comparison,In: Seminar aus Bildverarbeitung und Mustererkennung, 2014
• [20] Manipriya S., Mala C., Mathew S., Performance Analysis of Spatial Color Information for Object Detection Using Background Subtraction,IERI Procedia, 10:63–69, 2014
• [21] Stauffer, C., GrimsonW.E.L.,Adaptive background mixture models for real-time tracking, Proceedings,1999. IEEE Computer Society Conference on, IEEE, pp. 246–252, 1999
• [22] Doyle D.D., Jennings A.L., Black J.T., Optical flow background estimation for real-time pan/tilt camera object tracking,Measurement, 48:195–207, 2014
• [23] Tiwari, M., Singhai, R., A Review of Detection and Tracking of Object from Image and Video Sequences,International Journal of Computational Intelligence Research, 13, 973–1873, 2017
• [24] Chate M., Amudha S., Gohokar V., Object Detection and tracking in Video Sequences,ACEEE International Journal on signal & Image processing, 3, 2012,
• [25] Mohan A.S., Resmi R., Video image processing for moving object detection and segmentation using background subtraction, In: Computational Systems and Communications (ICCSC), 2014 First International Conference on,IEEE, pp. 288–292, 2014
• [26] Haritaoglu I., Harwood D., Davis L.S., W/sup 4/: real-time surveillance of people and their activities,IEEE Transactions on pattern analysis and machine intelligence, 22, 809–830, 2000
• [27] Zhiqiang W., Xiaopeng J., Peng W., Real-time moving object detection for video monitoring systems,Journal of Systems Engineering and Electronics,17, 731–736, 2006
• [28] Zhang T., Liu Z., Lian X., Wang X., Study on moving-objects detection technique in video surveillance system, Chinese Control and Decision Conference, IEEE, pp. 2375–2380, 2010
• [29] Krishna M.T.G., Ravishankar M., Babu D.R.R., Automatic detection and tracking of moving objects in complex environments for video surveillance applications, In: Electronics Computer Technology (ICECT), 2011 3rd International Conference on,IEEE, pp. 234–238, 2011
• [30] Due Trier., Jain A.K., Taxt T., Feature extraction methods for character recognition-A survey, PatternRecognition, 29, 641–662, 1996.
• [31] Fan L., Wang Z., Cail B., Tao C., A survey on multiple object tracking algorithm, In: Information and Automation (ICIA), 2016 IEEE International Conference on, IEEE, pp. 1855–1862, 2016
• [32] Javed O., Shah M., Tracking and object classification for automated surveillance, In: European Conference on Computer Vision. Springer, Berlin, Heidelberg, pp. 343-357, 2002
• [33] Hu, W., Tan, T., Wang, L., Maybank, S., A Survey on Visual Surveillance of Object Motion and Behaviors, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 34.3: 334-352, 2004
• [34] Talu M.F., Nesne Takip Yöntemlerinin Sınıflandırılması,İstanbul Ticaret Üniversitesi Fen Bilim. Derg., 18, 45–63, 2010
• [35] Yilmaz A., Javed O., Shah M., Object Tracking: A Survey,ACM computing surveys., 38, 2006
• [36] Parekh H.S., Thakore D.G., Jaliya U.K., A survey on object detection and tracking methods, International Journal of Innovative Research in Computer and Communication Engineering, 2.2: 2970-2979. 2014
• [37] Bagherpour P., Cheraghi S.A., Mokji M.B.M., Upper Body Tracking Using KLT and Kalman Filter, Procedia Computer Science, 13, 185–191, 2012
• [38] Wang, N., Yeung, D.-Y., Learning a deep compact image representation for visual tracking, Advances in neural information processing systems., p. 809-817, 2013.
• [39] Zhou X, Xie L, Zhang P, Zhang Y. An ensemble of deep neural networks for object tracking, In: Image Processing (ICIP), 2014 IEEE International Conference on, IEEE, p. 843-847, 2014
• [40] Zhang D., Maei H., Wang X., Wang Y.-F., Deep Reinforcement Learning for Visual Object Tracking in Videos,arXiv Prepr. arXiv1701.08936, 2017
• [41] Girshick R., Donahue J., Darrell T., Malik J., Rich feature hierarchies for accurate object detection and semantic segmentation, In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.580–587, 2014
• [42] Behrendt K., Novak L., Botros R., A deep learning approach to traffic lights: Detection, tracking, and classification, In: Robotics and Automation (ICRA), 2017 IEEE International Conference on, pp. 1370–1377, 2017
• [43] Gordon D., Farhadi A., Fox D., Re3: Real-Time Recurrent Regression Networks for Object Tracking, arXiv preprint arXiv:1705.06368, 2017.
• [44] Bae S.-H., Yoon K.-J., Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017