Abstract
Real-time target detection and location has important values in video surveillance. Aimed at the low accuracy of existing real-time object detection algorithms, this paper proposes a multi-scale real-time target detection algorithm based on residual convolution neural network. Firstly, the residual convolutional neural network is introduced into the YOLOv3-Tiny algorithm. The jump connection of the low-level and high-level networks forms the residual module in the YOLOv3-Tiny algorithm to effectively prevent network degradation while increasing the depth of the neural network. Secondly, a new prediction layer is added to the neural network to improve the results of small target detection. Finally, the trained model is tested on the Pascal VOC public dataset. The experimental results show that the proposed algorithm achieves 64.6% accuracy on the validation dataset, and the speed of 60FPS in the video detection. The detection accuracy is improved to a higher level at a small cost of a little lower speed still meeting the real-time detection requirements, and small targets in the image can be effectively detected. The algorithm is effective and robust.
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
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 511–518. IEEE, Kauai (2001)
Redmon, J., Divvala, S., Girshick, R.: 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)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7263–7271. IEEE, Honolulu (2017)
Ren, S., He, K., Girshick, R.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2015)
Lin, T., Dollár, P., Girshick, R.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Veit, A., Matera, T., Neumann, L.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, pp. 448–456. JMLR.org, Lille (2001)
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778. IEEE, Las Vegas (2016)
Sadeghi, M.A., Forsyth, D.: 30 Hz object detection with DPM V5. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 65–79. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_5
Yan, J., Lei, Z., Wen, L.: The fastest deformable part model for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2497–2504. IEEE, Columbus (2014)
Lenc, K., Vedaldi, A.: R-CNN minus R. arXiv preprint arXiv:1506.06981 (2015)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448. IEEE (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Bai, Z., Jiang, D. (2019). On the Multi-scale Real-Time Object Detection Using ResNet. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11857. Springer, Cham. https://doi.org/10.1007/978-3-030-31654-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-31654-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31653-2
Online ISBN: 978-3-030-31654-9
eBook Packages: Computer ScienceComputer Science (R0)