Abstract
The goal of online multi-object tracking (MOT) is to estimate the tracks of multiple objects instantly with each incoming frame using up-to-the-moment information. Conventional approaches to MOT do not account for motion of the camera or background. Also, traditional optical flow features or color features do not produce satisfactory discrimination. This paper attempts to deal with such problems by turning the online MOT problem into the problem of minimizing the global energy by constructing a conditional random field model. At the same time, structural information and discriminative deep appearance features are integrated together to make data association more accurate. In this way, individual objects are not only more precisely associated across frames, but are also dynamically constrained with each other in a global manner. We conduct experiments using the MOT challenge benchmark to verify the effectiveness of our method and achieve competitive results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, pp. 91–99 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation, pp. 580–587 (2013)
Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., Yan, J.: POI: multiple object tracking with high performance detection and appearance feature. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 36–42. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_3
Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: IEEE Conference on Computer Vision & Pattern Recognition (2008)
Yang, M., Wu, Y., Jia, Y.: A hybrid data association framework for robust online multi-object tracking. IEEE Trans. Image Process. PP(99), 1 (2017)
Li, S., Wei, Y., Hoseinnezhad, R., Wang, B., Kong, L.J.: Multi-object tracking for generic observation model using labeled random finite sets. IEEE Trans. Signal Process. 66(2), 368–383 (2017)
Shafiee, M.J., Azimifar, Z., Wong, A.: A deep-structured conditional random field model for object silhouette tracking. Plos One 10(8), e0133036 (2015)
Shafiee, M.J., Azimifar, Z., Fieguth, P.: Model-based tracking: temporal conditional random fields (2010)
Zhang, B., Perina, A., Li, Z., Murino, V., Liu, J., Ji, R.: Bounding multiple Gaussians uncertainty with application to object tracking. Int. J. Comput. Vision 118(3), 364–379 (2016)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014)
Multiple object tracking benchmark. http://motchallenge.net/
Acknowledgement
This work was supported by the National Natural Science Foundation of China (NO.61806168), Fundamental Research Funds for the Central Universities (NO. SWU117059), and Venture & Innovation Support Program for Chongqing Overseas Returnees (NO. CX2018075).
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
Zeng, X., Wu, S., Xiao, G. (2019). Multi-object Tracking with Conditional Random Field. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1143. Springer, Cham. https://doi.org/10.1007/978-3-030-36802-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-36802-9_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36801-2
Online ISBN: 978-3-030-36802-9
eBook Packages: Computer ScienceComputer Science (R0)