Skip to main content
SpringerLink
Log in

An anchor box setting technique based on differences between categories for object detection

  • Regular Paper
  • Published:
International Journal of Intelligent Robotics and Applications Aims and scope Submit manuscript

Abstract

Detection accuracy and speed are crucial in object detection in computer vision. This work proposes a novel technique called On-Category Anchors (OC-Anchors) to improve the accuracy of real-time single-stage object detectors. The key concept of the OC-Anchors technique is to create anchors based on the categories of foreground objects. The OC-Anchors are set to reflect the bounding box features of the foreground object category. This approach improves the accuracy of predicting the bounding boxes of objects. The performance of the proposed OC-Anchors technique is examined in detail in the YOLOv2 framework with the COCO dataset. The results show that the OC-Anchors technique significantly improves the detection accuracy in tests on COCO test-dev, without substantially affecting the prediction speed. The improvement in average precision ranges from 21.6 to 27.1%.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

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

  • Dai, J.F., Li, Y., He, K.M., et al.: R-fcn: Object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379–387 (2016)

  • Deng, J., Dong, W., Socher, R., et al.: ImageNet: s large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)

  • Du, X.D., Cai, Y.H., Lu, T., et al.: A robotic grasping method based on deep learning. Robot. 39(6), 820–828+837 (2017)

  • Erhan, D., Szegedy, C., Toshev, A., et al.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147–2154 (2014)

  • Everingham, M., Van Gool, L., Williams, C.K., et al.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)

    Article  Google Scholar 

  • Fu, C.Y., Liu, W., Ranga, A., et al. Dssd: Deconvolutional single shot detector (2017). arXiv:1701.06659

  • He, K.M., Zhang, X.Y., Ren, S.Q., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

  • He, K.M., Gkioxari, G., Dollár, P., et al.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

  • Huang, L.W., Jiang, B.T., Lv, S.Y., et al.: Survey on deep learning based recommender systems. Chin. J. Comput. 41(07), 1619–1647 (2018)

    MathSciNet  Google Scholar 

  • Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv:1502.03167

  • Lei, Y.G., Jia, F., Zhou, X., et al.: A deep learning-based method for machinery health monitoring with big data. Chin. J. Comput. 51(21), 49–56 (2015)

    Google Scholar 

  • Li, H.H., Zhou, K.P., Han, T.C.: Ship object detection based on SSD improved with CReLU and FPN. Chin. J. Sci. Instrum. 41(04), 183–190 (2020)

    Google Scholar 

  • Lin, M., Chen, Q., Yan, S.C.: Network in network (2013). arXiv:1312.4400

  • Lin, T.-Y., Maire, M., Belongie, S., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740–755 (2014)

  • Lin, T.-Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

  • Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal Loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

  • Liu, W., Anguelov, D., Erhan, D., et al.: Ssd: single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37 (2016)

  • Liu, S.T., Huang, D., Wang, Y.H.: Receptive field block net for accurate and fast object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 385–400 (2018)

  • Long, X.Y., Zhao, S.K., Jiang, C., et al.: Deep learning-based planar crack damage evaluation using convolutional neural networks. Eng. Fract. Mech. 246, 107604 (2021)

    Article  Google Scholar 

  • Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts (2016). arXiv:1608.03983

  • Ma, Z.X., Yang, F., Qiao, X.: Intelligent Detection Method of Railway subgrade defect. Computer Engineering and Applications (2020). http://kns.cnki.net/kcms/detail/11.2127.tp.20200325.0916.006.html

  • Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR’06), pp. 850–855 (2006)

  • Peng, Y.Q., Zhao, X.S., Tao, H.F., et al.: Hand gesture recognition against complex background based on deep learning. Robot. 41(04), 534–542 (2019)

    Google Scholar 

  • Qin, R.N., Wang, R.: Instance-level object detection algorithm fusing adversarial learning strategies. Pattern Recogn. Artif. Intell. 32(11), 1006–1013 (2019)

    Google Scholar 

  • Redmon, J.: Darknet: open source neural networks in c (2013–2016). http://pjreddie.com/darknet/

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

  • Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018). arXiv:1804.02767

  • Redmon, J., Divvala, S., Girshick, R., et al.: 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)

  • Ren, S.Q., He, K.M., Girshick, R., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

  • Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv:1409.1556

  • Wang, T., Anwer, R.M., Cholakkal, H., et al.: Learning rich features at high-speed for single-shot object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1971–1980 (2019)

  • Wang, D.M., Yan, Y., Zhou, G.L., et al.: 3D Vision-based picking system with instance segmentation network and iterative optimization method. Robot. 41(05), 637–648 (2019)

    Google Scholar 

  • Yu, J., Jiang, Y., Wang, Z., et al.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516–520 (2016)

  • Zhou, W.J.: Static Gesture Recognition Approach Based on DSSD. Hefei University of Technology, Master (2019)

  • Zi, B., Yin, Z.Q., Li, Y.C., et al.: Fast mobile component location method for cable-driven parallel robots based on YOLO model. Chin. J. Mech. Eng. 55(03), 64–72 (2019)

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by Youth Project of National Natural Science Foundation of China (Grant no. 518-05141), Science and Technology Plan Project of Tianjin (Grant no. 19ZXZNGX00100), the Natural Science Foundation of Hebei Province (Grant no. A2019202171), Key R&D Program of Hebei Province (Grant no. 19227208D).

Author information

Authors and Affiliations

  1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, 300401, China

    Shuyong Duan, Ningning Lu & Bin Cao

  2. Tianjin SIASUN Robot & Automation CO., LTD, Tianjin, 300300, China

    Zhongwei Lyu

  3. Department of Aerospace Engineering and Engineering Mechanics, University of Cincinnati, Cincinnati, OH, 45241-1886, USA

    Guirong Liu

Authors
  1. Shuyong Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ningning Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhongwei Lyu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guirong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bin Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guirong Liu or Bin Cao.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duan, S., Lu, N., Lyu, Z. et al. An anchor box setting technique based on differences between categories for object detection. Int J Intell Robot Appl 6, 38–51 (2022). https://doi.org/10.1007/s41315-021-00176-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41315-021-00176-1

Keywords

Search

Navigation