Abstract
Aiming at the problem that each detection feature layer of the single-shot multibox detector (SSD) algorithm does not perform feature fusion and the detection effect is poor, an adaptive feature fusion SSD model is proposed. Firstly, the location of the shallow feature map and the multi-scale receptive field on the deep feature map are added, and the scaling and adaptive fusion of different scale feature maps are carried out to improve the representation ability of detail information. Secondly, the feature layer of the same scale can provide different ranges of feature information, transfer the specific features with detailed information to the abstract features with semantic information, and use the global average pool to guide learning and expand the expression ability of features. After training and testing on the PASCAL VOC data set, the detection accuracy reaches 80.6% and the detection speed reaches 60.9 fps, which verifies the robustness and real-time performance of the algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fang, L.P., He, H.J., Zhou, G.M.: Research overview of object detection methods. J. Comput. Eng. Appl. 54, 11–18 (2018)
Liu, W., Anguelov, D., Erhan, D., et al.: SSD: single shot multibox detector. In: 14th European Conference on Computer Vision, Amsterdam, Netherlands, pp. 21–37 (2016)
Singh, B., Davis, L.S.: An analysis of scale invariance in object detection – SNIP. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 3578–3587 (2018)
Li, Y., Chen, Y., Wang, N., et al.: Scale-aware trident networks for object detection. In: 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), pp. 6054–6063 (2019)
Lin, T.-Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, pp. 936–944 (2017)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2017)
Redmon, J., Farhadi, A.:YOLOv3: an incremental improvement. J. Comput. Vis. Pattern Recogn. arXiv:1804.02767 (2018)
Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 6154–6162 (2018)
Liu, S., Qi, L., Qin, H., Shi, J., et al.: Path aggregation network for instance segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 8759–8768 (2018)
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 10781–10790 (2020)
Zhu, M., Han, K., Yu, C., et al.: Dynamic feature pyramid networks for object detection. J. arXiv:2012.00779 (2020)
Fu, C.-Y., Liu, W., Ranga, A., et al.: DSSD: deconvolutional single shot detector. J. arXiv:1701.06659 (2017)
Zhai, S., Shang, D., Wang, S., et al.: DF-SSD: an improved SSD object detection algorithm based on denseNet and feature fusion. J. IEEE Access 8, 24344–24357 (2020)
Yin, Q., Yang, W., Ran, M., et al.: FD-SSD: an improved SSD object detection algorithm based on feature fusion and dilated convolution. J. Signal Process. Image Commun, 98, 116402 (2021)
Zheng, L., Fu, C., Zhao, Y.: Extend the shallow part of single shot multibox detector via convolutional neural network. In: Tenth International Conference on Digital Image Processing, pp. 287–293. IEEE, International Society for Optics and Photonics (2018)
Acknowledgments
This work was supported by the Natural Science Foundation of Anhui Province, China (Grand No. 2108085MF197 and Grand No.1708085MF154), the Natural Science Foundation of the Anhui Higher Education Institutions of China (Grant No. KJ2019A0162), the Open Research Fund of Anhui Key Laboratory of Detection Technology and Energy Saving Devices, Anhui Polytechnic University (Grant No. DTESD2020B02), the National Natural Science Foundation Pre-research of Anhui Polytechnic University (Xjky2022040), and the Graduate Science Foundation of the Anhui Higher Education Institutions of China (Grant No. YJS20210448 and YJS20210449).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Y., Wang, F., Xie, Z., Wang, Y. (2022). Multi-scale Object Detection Algorithm Based on Adaptive Feature Fusion. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)