Abstract
Object detection in still images has been extensively investigated recent years. But object detection in videos is still a challenging research topic. Directly using those methods for still images in videos would suffer from blurring and low resolution in video images. Some methods utilized the temporal information to boost the detection accuracy, but they are usually expensive in time in estimating optical flow. In this paper, we propose Recurrent RetinaNet, a flexible end-to-end approach for object detection in videos. In this work, a backbone network is leveraged to generate several feature maps, then a feature pyramid network extracts pyramid features from the feature maps. Detection boxes are generated according to the shapes of pyramid features. Two subnets with convolutional layers and Convolutional LSTM layers, are added on the top for box regression and classification. Note that the boxes are generated regardless of the content of images, there may be an extreme foreground-background imbalance. Thus, focal loss, which has been shown effective in object detection on images, is employed as the loss function for the classification subnet. Experiments show that the approach improves the detection accuracy and avoids the detection loss of some objects in some cases compared to RetinaNet and the model complexity is still good enough for real-time applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). http://tensorflow.org/. Software available from tensorflow.org
Chollet, F., et al.: Keras (2015). https://github.com/keras-team/keras
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009, IEEE (2009)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR 2014 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. Cornell University Library (2017)
Hetang, C., Qin, H., Liu, S., Yan, J.: Impression network for video object detection. arXiv preprint arXiv:1712.05896 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: Proceedings of CVPR, vol. 2, p. 7 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, vol. 1, p. 4 (2017)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)
Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NIPS 2015 (2015)
Xue, W., Zhao, H., Zhang, L.: Encoding multi-resolution two-stream CNNs for action recognition. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9949, pp. 564–571. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46675-0_62
Zhang, K., Zhang, L.: Extracting hierarchical spatial and temporal features for human action recognition. Multimedia Tools Appl. 77(13), 16053–16068 (2018). Springer
Acknowledgement
The work was supported by the National Basic Research Program of China (Grant No. 2015CB856004) and the Key Basic Research Program of Shanghai Municipality, China (15JC1400103,16JC1402800).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., Zhao, H., Zhang, L. (2018). Recurrent RetinaNet: A Video Object Detection Model Based on Focal Loss. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11304. Springer, Cham. https://doi.org/10.1007/978-3-030-04212-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-04212-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04211-0
Online ISBN: 978-3-030-04212-7
eBook Packages: Computer ScienceComputer Science (R0)