Abstract
Multi-object tracking is a key research problem in computer vision area, and with the fast development of the deep learning based image and video processing algorithms, the performance and accuracy of multi-object tracking methods are dramatically improved. However, current multi-object tracking methods mostly focus on human and seldom animals, and usually there are too many parameters, which make these methods very complicated and very hard to use in practical scenarios. In order to solve these problems, we proposed an easy-use multi-object tracking method based on bounding boxes and object appearance features. In our method, we take animals as the tracking object. In order to count the number of them in a closed area we firstly tracking and identify them based on the fact that two different objects cannot appears in a same video frame and the trajectory of an animal is continuous. Then, we store the appearance features of each individual animal and when it cannot be identified by tracking, we use appearance feature to re-identify it. Thirdly, we combined these two methods and when the whole system converged to stable state, we can get the total mumble of these animals. The results show that our method can tracking the multi-object accurately and can be easily used in practice.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Luo, W., Xing, J., Zhang, X., Zhao, X., Kim, T.-K.: Multiple object tracking: a literature review. Comput. Sci. (2014)
Elbahri, M., Kpalma, K., Taleb, N., Chikr El-Mezouar, M.: A novel object position coding for multi-object tracking using sparse representation. Int. J. Image, Graph. Signal Process. (IJIGSP) 7(8), 1–12 (2015). https://doi.org/10.5815/ijigsp.2015.08.01
Bochinski, E., Eiselein, V., Sikora, T.: High-speed tracking-by-detection without using image information. In: IEEE AVSS (2017)
Sadeghian, A., Alahi, A., Savarese, S.: Tracking the untrackable: learning to track multiple cues with long-term dependencies. In: 16th IEEE International Conference on Computer Vision, pp. 300–311. IEEE, Venice (2017)
Jatoth, R.K., Gopisetty, S., Hussain, M.: Performance analysis of alpha beta filter, kalman filter and meanshift for object tracking in video sequences. IJIGSP 7(3), 24–30 (2015). https://doi.org/10.5815/ijigsp.2015.03.04
Tirandaz, H., Azadi, S.: Utilizing GVF active contours for real-time object tracking. Int. J. Image, Graph. Signal Process. (IJIGSP) 7(6), 59–65 (2015). https://doi.org/10.5815/ijigsp.2015.06.08
Rao, G.M., Satyanarayana, C.: Object tracking system using approximate median filter, kalman filter and dynamic template matching. Int. J. Intell. Syst. Appl. (IJISA) 6(5), 83–89 (2014). https://doi.org/10.5815/ijisa.2014.05.09
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: 14th European Conference on Computer Vision, pp. 21–37. Springer, Amsterdam (2016)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Girshick, R.: Fast R-CNN. In: 15th IEEE International Conference on Computer Vision, pp. 1440–1448. IEEE, Santiago (2015)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 29th IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 779–788. IEEE, Las Vegas (2016)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823. IEEE, Boston (2015)
Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708. IEEE, Columbus (2014)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 6738–6746. IEEE, Honolulu (2017)
Liu, J., Deng, Y., Bai, T., Wei, Z., Huang, C.: Targeting ultimate accuracy: face recognition via deep embedding. arXiv:1506.07310v4 (2015)
Chu, Q., Ouyang, W., Li, H., Wang, X., Liu, B., Yu, N.: Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism. In: 16th IEEE International Conference on Computer Vision, pp. 4846–4855. IEEE, Venice (2017)
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In 24th IEEE International Conference on Image Processing, pp. 3645–3649, IEEE, Beijing (2018)
Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: 15th IEEE International Conference on Computer Vision, pp. 4705–4713. IEEE, Santiago (2015)
Tayyab, M., Qadri, M.T., Ahmed, R., Dhool, M.A.: Real time object tracking using FPGA development kit. Int. J. Inf. Technol. Comput. Sci. (IJITCS) 6(11), 54–58 (2014). https://doi.org/10.5815/ijitcs.2014.11.08
Singh, S., Saini, R., Saurav, S., Saini, A.K.: Real-time object tracking with active PTZ camera using hardware acceleration approach. Int. J. Image, Graph. Signal Process. (IJIGSP) 9(2), 55–62 (2017). https://doi.org/10.5815/ijigsp.2017.02.07
Ramaravind, K.M., Shravan, T.R., Omkar, S.N.: Scale adaptive object tracker with occlusion handling. Int. J. Image Graph. Signal Process. (IJIGSP) 8(1), 27–35 (2016). https://doi.org/10.5815/ijigsp.2016.01.03
Gordon, D., Farhadi, A., Fox, D: Re3: real-time recurrent regression networks for visual tracking of generic objects. arXiv:1705.06368v3 (2018)
Acknowledgment
This project was financially supported by the Fundamental Research Funds for the Central Universities (Grant No. 2662017JC028) and Hubei Provincial Natural Science Foundation of China (Grant No. 2015CFB437).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, F., Jia, W., Yang, Z. (2020). A Multi-object Tracking Method Based on Bounding Box and Features. In: Hu, Z., Petoukhov, S., Dychka, I., He, M. (eds) Advances in Computer Science for Engineering and Education II. ICCSEEA 2019. Advances in Intelligent Systems and Computing, vol 938. Springer, Cham. https://doi.org/10.1007/978-3-030-16621-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-16621-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16620-5
Online ISBN: 978-3-030-16621-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)