Object finding is a fast-developing technique in the area of Computer Vision and Machine Learning. Computer vision is one of the principal tasks of deep learning field. Object detection is a technique that identifies the existence of object in an image or video. Object detection can be used in many areas for improving efficiency in the task. The applications for object detection are in home automation, self-driving cars, people counting, agriculture, traffic monitoring, military defence systems, sports, industrial work, robotics, aviation industry and many others. Object detection can be done through various techniques like R-CNN, Fast R-CNN, Faster R-CNN, Single Shot detector (SSD) and YOLO v3. A comparison of these algorithms is done and also their results as well as performance is analysed. The performance and exactness should be utmost important in analysing the algorithms.

Object Detection, Object Finding, R-CNN, Fast RCNN, Faster RCNN, Single Shot Detector, YOLO v3

[1] Y. LeCun, Y. Bengio, G. Hinton, “Deep Learning”, Nature, Vol.521, pp.436-444, 2015.
[2] R. Girshick, J. Donahue, T. Darrell, J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation”, IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, pp. 580-587, 2014.
[3] R. Girshick, “Fast R-CNN”, IEEE International Conference on Computer Vision (ICCV), Santiago, USA pp.1440-1448, 2015.
[4] Z. Zhao, X. Wu, S. Xu, P. Zheng, “Object Detection with Deep Learning: A Review”, IEEE Transactions on Neural Networks and Learning Systems, Vol.30, Issue.11, pp.3212-3232, 2019.
[5] S. Ren, K. He, R. Girshick, J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.39, Issue.6, pp.1137-1149, 2017.
[6] J.R.R. Uijlings, K.E.A. van de Sande, T. Gevers and A.W.M. Smeulders, “Selective Search for Object Recognition”, International Journal of Computer Vision, Vol.104, pp.154–171, 2013.
[7] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Fu, A.C. Berg, “SSD: Single Shot Multibox Detector”, Springer, Vol.9905, pp.21-37, 2016.
[8] Z. Shen, Z. Liu, J. Li, Y. Jiang, Y. Chen, X. Xue, “DSOD: Learning Deeply Supervised Object Detectors from Scratch”, IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp.1937-1945, 2017.
[9] S. Zhai, D. Shang, S. Wang, S. Dong, “DF-SSD: An Improved SSD Object Detection Algorithm Based on DenseNet and Feature Fusion”, IEEE Access, Vol.8, pp.24344-24357, 2020.
[10] J. Redmon, A. Farhadi, “YOLO9000: Better, Faster, Stronger”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, pp.6517-6525, 2017.
[11] J. Redmon, A. Farhadi, “YOLOv3: An Incremental Improvement”, ResearchGate, 2018.
[12] J. Sang, Z. Wu, P. Guo, H. Hu, H. Xiang, Q. Zhang, B. Cai, “An Improved Yolov2 for Vehicle Detection”, Sensors, Vol.18, Issue.12, pp.4272, 2018.
[13] A. Agrawal, A.N. Modi, A. Passos, A. Lavoie, A. Agarwal, A. Shankar, I. Ganichev, J. Levenberg, M. Hong, R. Monga, S. Cai, “Tensor?ow Eager: A Multistage, Python-Embedded DSL for Machine Learning”, Proceedings of Machine Learning and Systems 1 (MLSys 2019), Stanford, California, pp. 178-189, 2019.
[14] J. Y. Lu, C. Ma, L. Li, X.Y. Xing, Y. Zhang, Z.G. Wang. J.W. Xu, “A Vehicle Detection Method for Aerial Image Based on YOLO”, Journal of Computer and Communications, Vol.6, Issue.11, pp.98-107, 2018.
[15] L. Zhao, S. Li, “Object Detection Algorithm Based on Improved YOLOv3”, Electronics, Vol.9, Issue.3, pp.537, 2020.
[16] N. Raviteja, M. Lavanya, S. Sangeetha, “An Overview on Object Detection and Recognition”, International Journal of Computer Sciences and Engineering, Vol.8, Issue.2, pp.42-45, 2020.
[17] A. Kaur, D. Kaur, “Yolo Deep Learning Model Based Algorithm for Object Detection”, International Journal of Computer Sciences and Engineering, Vol.8, Issue.1, pp.174-178, 2020.