Skip to main content
SpringerLink
Log in

Deep Learning Algorithms for Object Detection—A Study

  • Conference paper
  • First Online:
Evolution in Computational Intelligence

Part of the book series: Smart Innovation, Systems and Technologies ((SIST,volume 267))

Abstract

In the field of computer vision, creating an effective object detection model is a difficult task. Object detection is the process of predicting objects and locating their instances in a given image. It is used in a wide range of applications, including self-driving cars, navigating visually impaired people in an indoor/outdoor environment, counting crowds, detecting vehicles, tracking objects, etc. Traditionally, the opencv’s feature extraction and feature detecting algorithms are employed to object detection. However, in the real world, the performance of those algorithms is unsatisfactory. In recent days, different deep learning models are available to extract and learn the objects' features to detect the objects and also the performance of these algorithms is acceptable in the real environment. This paper compares the SSD, YOLOv3 and YOLOv4 for detecting objects in the indoor environment and discusses the aspects of sparse and dense prediction for the various deep learning algorithms used for object detection.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 249.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)

    Google Scholar 

  2. Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems 30(11), 3212–3232 (2019)

    Google Scholar 

  3. Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., Pietikäinen, M.: Deep learning for generic object detection: A survey. Int. J. Comput. Vision 128(2), 261–318 (2020)

    Google Scholar 

  4. Han, J., Zhang, D., Cheng, G., Liu, N., Xu, D.: Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Process. Mag. 35(1), 84–100 (2018)

    Google Scholar 

  5. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks (2013). arXiv:1312.6229

  6. 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)

    Google Scholar 

  7. He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)

    Google Scholar 

  8. Girshick, R.: Fast RCNN. In: Proceedings of the IEEE International Conference on CComputer Vision. pp. 1440–1448 (2015)

    Google Scholar 

  9. Ren, S., He, K., Girshick, R., Sun, J.: Faster RCNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

    Google Scholar 

  10. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

    Google Scholar 

  11. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37. Springer, Cham (2016)

    Google Scholar 

  12. Redmon, J., & Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)

    Google Scholar 

  13. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., elongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  14. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask RCNN (2017). arXiv:1703.06870.

  15. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  16. Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement (2018). arXiv:1804.02767.

  17. Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734–750 (2018)

    Google Scholar 

  18. Rashwan, A., Kalra, A., Poupart, P.: Matrix nets: A new deep architecture for object detection. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)

    Google Scholar 

  19. Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra RCNN: Towards balanced learning for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 821–830 (2019)

    Google Scholar 

  20. Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6569–6578 (2019)

    Google Scholar 

  21. Cai, Z., Vasconcelos, N.: Cascade RCNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2019)

    Google Scholar 

  22. Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9627–9636 (2019)

    Google Scholar 

  23. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: Optimal Speed and Accuracy of Object Detection (2020).  arXiv:2004.10934.

  24. https://pjreddie.com/darknet/yolo/

  25. https://github.com/pjreddie/darknet

  26. GitHub: LabelImg: A graphical image annotation tool (2015)

    Google Scholar 

  27. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Kudlur, M.: Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), pp. 265–283 (2016)

    Google Scholar 

  28. Bisong, E.: Google colaboratory. In: Building Machine Learning and Deep Learning Models on Google Cloud Platform, pp. 59–64. Apress, Berkeley, CA (2019)

    Google Scholar 

  29. http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz

Download references

Author information

Authors and Affiliations

  1. Department of IT, Sona College of Technology (Autonomous), Salem, Tamil Nadu, India

    A. Naveenkumar & J. Akilandeswari

Authors
  1. A. Naveenkumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. Akilandeswari
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Electronics and Communication Engineering, Shri Ramswaroop Memorial Group of Professional Colleges (SRMGPC), Lucknow, Uttar Pradesh, India

    Vikrant Bhateja

  2. College of Computing, Michigan Technological University, Michigan, MI, USA

    Jinshan Tang

  3. School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT), Bhubaneswar, India

    Suresh Chandra Satapathy

  4. Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia

    Peter Peer

  5. Department of Computer Science and Engineering, National Institute of Technology (NIT) Mizoram, Aizawl, India

    Ranjita Das

Ethics declarations

The competent authorities allowed us to use the images/data as provided in the study. We shall be entirely responsible for any dispute in the future.

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Naveenkumar, A., Akilandeswari, J. (2022). Deep Learning Algorithms for Object Detection—A Study. In: Bhateja, V., Tang, J., Satapathy, S.C., Peer, P., Das, R. (eds) Evolution in Computational Intelligence. Smart Innovation, Systems and Technologies, vol 267. Springer, Singapore. https://doi.org/10.1007/978-981-16-6616-2_7

Download citation

Publish with us

Policies and ethics

Search

Navigation