Journals / Avrupa Bilim ve Teknoloji Dergisi / 2021 / Cilt: 0 - Sayı: 25

A Review On Object Detection And Tracking With Deep Learning Techniques

Derin Öğrenme Teknikleri İle Nesne Tespiti Ve Takibi Üzerine Birİnceleme

Pages
159–171
Publication Date
2022-10-11
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The aim of this study is to examine the applications of deep learning and object detection andtracking, to explain the latest developments, to help researchers who will work in this field by giving information about popularlibraries, data sets, algorithms.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Deep learning is one of the artificial intelligence approaches that has recently become popular for minimizing human error.
📊
Key Findings & Data:Deeplearning techniques have the ability to successfully detect and interpret with the use of large amounts of data in many areas.Especially, the rapid increase in labeled data accumulated in the field of image processing has made it necessary to turn to deeplearning algorithms.
💡
Conclusion & Impact:The aim of this study is to examine the applications of deep learning and object detection andtracking, to explain the latest developments, to help researchers who will work in this field by giving information about popularlibraries, data sets, algorithms.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Deep learning is one of the artificial intelligence approaches that has recently become popular for minimizing human error. Deeplearning techniques have the ability to successfully detect and interpret with the use of large amounts of data in many areas.Especially, the rapid increase in labeled data accumulated in the field of image processing has made it necessary to turn to deeplearning algorithms. With the increasing data in these areas, deep learning methods are used to separate useful information from bigdata and to give meaning to text, images and audio files. In recent years, there has been an increase in the studies conducted in thefield of object detection and object tracking. If there is an object to be followed after detection and analysis on non-stationary imagessuch as videos, it is more difficult to extract meaningful information. In such cases, the use of deep learning algorithms enables imageprocessing problems to be solved easily. The aim of this study is to examine the applications of deep learning and object detection andtracking, to explain the latest developments, to help researchers who will work in this field by giving information about popularlibraries, data sets, algorithms.

Özet

Derin öğrenme, son zamanlarda insan hatalarını en aza indirmesiyle popüler olan yapay zekâ yaklaşımlarındandır. Derin öğrenme teknikleri birçok alanda büyük miktardaki veri kullanımı ile başarılı bir şekilde algılama, yorumlama yapabilme yeteneğine sahiptir.Özellikle görüntü işleme alanında birikmiş etiketli verilerdeki hızlı artış derin öğrenme algoritmalarına yönelmeyi zorunlu halegetirmiştir. Bu alanlardaki verilerin giderek artmasıyla büyük verilerden yararlı bilgiyi ayırmak ve metin, görüntü, ses dosyalarınaanlam kazandırmak amacıyla derin öğrenme yöntemleri kullanılmaktadır. Son yıllarda, nesne tespiti ve nesne takibi alanında yapılançalışmalarda artış görülmektedir. Videolar gibi durağan olmayan görüntüler üzerinde tespit ve analiz sonrasında takip edilecek olanbir nesne varsa anlamlı bilgiler çıkarmak daha zor olmaktadır. Bu gibi durumlarda derin öğrenme algoritmalarının kullanılması görüntü işleme problemlerinin kolaylıkla çözüme kavuşturulabilmesini sağlamaktadır. Bu çalışmanın amacı; derin öğrenme ile nesnetespiti ve takibi konusunda yapılan uygulamaları incelemek, son gelişmeleri anlatmak, popüler kütüphaneler, veri setleri, algoritmalarhakkında bilgi vererek bu alanda çalışacak olan araştırmacılara yardımcı olmaktır.

🔖

Cite This Article

YÜKSEL, A. S., TAN, F. G., AYDEMİR, E., ERSOY, M. (2022). A Review On Object Detection And Tracking With Deep Learning Techniques. Avrupa Bilim ve Teknoloji Dergisi, Cilt: 0 - Sayı: 25, 159–171. https://ajindex.com/articles/457335

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (1)

  1. Amidi, A., Amidi, S. (2020). Derin Öğrenme El Kitabı. Derin Öğrenme El Kitabı: https://stanford.edu/~shervine/l/tr/teaching/cs229/cheatsheet-deep-learning adresinden alındı. Avidan, S. (2004). Support Vector Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1064-1072, doi:10.1109/TPAMI.2004.53. Avila, S., Thome, N., Cord, M., Valle, E., De A. Araújo, A. (2013). Pooling in image representation: The visual codeword point of view. Computer Vision and Image Understanding, 453-465, doi: 10.1016/j.cviu.2012.09.007. Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B. (2016). Simple online and realtime tracking. Proceedings - International Conference on Image Processing, ICIP, 3464– 3468, doi: 10.1109/ICIP.2017.8296962. Bolouri, H. (1995). Book Review: Fundamentals of Neural Networks — Architectures, Algorithms, and Applications: L. FAUSETT. International Journal of Electrical Engineering Education, doi: 10.1177/002072099503200320. Brocardo, M., Traore, I., Woungang, I., Obaidat, M. (2017). Authorship verification using deep belief network systems. International Journal of Communication Systems, doi: 10.1002/dac.3259. Brunetti, A., Buongiorno, D., Trotta, G., Bevilacqua, V. (2018). Computer vision and deep learning techniques for pedestrian detection and tracking: A survey. Neurocomputing, doi: 10.1016/j.neucom.2018.01.092. Cbinsights, C. (2019). The Race For AI: Here Are The Tech Giants Rushing To Snap Up Artificial Intelligence Startups. 2020 tarihinde CBINSIGHTS adresinden alındı. Chaudhary, S., Khan, M., Bhatnagar, C. (2018). Multiple Anomalous Activity Detection in Videos. Procedia Computer Science, 336-345, doi: 10.1016/j.procs.2017.12.045. Cheng, X., Song, C., Gu, Y., Chen, B. (2020). Learning Attention for Object Tracking with Adversarial Learning Network, doi: 10.21203/rs.3.rs-15512/v3. Ciaparrone, G., Luque Sánchez, F., Tabik, S., Troiano, L., Tagliaferri, R., Herrera, F. (2020). Deep learning in video multi-object tracking: A survey. Neurocomputing, 61-88, doi: 10.1016/j.neucom.2019.11.023. Collobert, R., Farabet, C., Kavukcuoğlu, K. (2017). Torch | Scientific computing for LuaJIT. NIPS Workshop on Machine Learning Open Source Software. Cortes, C., Vapnik, V. (1995). Support-Vector Networks. Machine Learning, doi: 10.1023/A:1022627411411. Cömert, O., Hekim, M., Adem, K. (2019). Faster R-CNN Kullanarak Elmalarda Çürük Tespiti. Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi, 335-341, doi: 10.29137/umagd.469929. Daş, R.,