![](bga.png)
5 CONCLUSIONS
In this paper, we proposed a method for tracking
multiple pedestrians in video sequences. The pro-
posed method extracts pedestrian regions in each
video frame, detects obstacle areas in the scene from
the extracted pedestrian regions, and tracks pedestri-
ans while estimating their occlusion states from the
detected obstacle areas. The efficacy of our proposal
was demonstrated through experiments on simulation
video sequences. The experimental results showed
that the proposed method, which estimates the occlu-
sion states of pedestrians and reflects them on region
association process, improves the robustness in visual
tracking multiple pedestrians under situations where
pedestrians are temporary occluded by still objects.
In future work, we plan to investigate a method for
updating detected obstacle areas by new input video
frames, and extend the proposed method in order to
deal with situations where pedestrians are temporary
occluded by occasionally moving obstacles, e.g, tem-
porary parked cars and stacked objects.
REFERENCES
AVSS2007 (2007). i-Lids dataset for AVSS2007. http://
www.eecs.qmul.ac.uk/
∼
andrea/avss2007 d.html.
Bernardin, K. and Stiefelhagen, R. (2008). Evaluating
multiple object tracking performance: The CLEAR
MOT metrics. EURASIP J. Image Video Process.,
2008(1):Article ID 246309.
Bewley, A., Ge, Z., Ott, L., Ramos, F., and Upcroft, B.
(2016). Simple online and realtime tracking. In IEEE
Int. Conf. Image Process., pages 3464–3468.
Bochinski, E., Senst, T., and Sikora, T. (2018). Extend-
ing IOU based multi-object tracking by visual infor-
mation. In IEEE Int. Conf. Adv. Video Signal Based
Surv., pages 1–6.
Cao, Z., Simon, T., Wei, S.-E., and Sheikh, Y. (2017).
Realtime multi-person 2D pose estimation using part
affinity fields. In IEEE Conf. Comput. Vision Pattern
Recognit., pages 1302–1310.
Hofmann, M., Haag, M., and Rigoll, G. (2013). Unified
hierarchical multi-object tracking using global data
association. In IEEE Int. Workshop Perform. Eval.
Tracking Surv., pages 22–28.
Huang, C., Wu, B., and Nevatia, R. (2008). Robust ob-
ject tracking by hierarchical association of detection
responses. In Eur. Conf. Comput. Vision, pages 788–
801.
Jiang, Z. and Huynh, D. Q. (2018). Multiple pedestrian
tracking from monocular videos in an interacting mul-
tiple model framework. IEEE Trans. Image Process.,
27(3):1361–1375.
Ju, J., Kim, D., Ku, B., Han, D. K., and Ko, H. (2017).
Online multi-person tracking with two-stage data as-
sociation and online appearance model learning. IET
Comput. Vision, 11(1):87–95.
Li, Y., Huang, C., and Nevatia, R. (2009). Learning to asso-
ciate: HybridBoosted multi-target tracker for crowded
scene. In IEEE Conf. Comput. Vision Pattern Recog-
nit., pages 2953–2960.
Mekonnen, A. A. and Lerasle, F. (2019). Comparative eval-
uations of selected tracking-by-detection approaches.
IEEE Trans. Circuits Syst. Video Technol., 29(4):996–
1010.
Meshgi, K., ichi Maeda, S., Oba, S., Skibbe, H., zhe Li, Y.,
and Ishii, S. (2016). An occlusion-aware particle filter
tracker to handle complex and persistent occlusions.
Comput. Vision Image Unders., 150:81–94.
Mitzel, D. and Leibe, B. (2011). Real-time multi-person
tracking with detector assisted structure propagation.
In IEEE Int. Conf. Comput. Vision Workshops , pages
974–981.
Osawa, T., Wu, X., Sudo, K., Wakabayashi, K., Arai, H.,
and Yasuno, T. (2007). MCMC based multi-body
tracking using full 3D model of both target and envi-
ronment. In IEEE Int. Conf. Adv. Video Signal Based
Surv., pages 224–229.
Possegger, H., Mauthner, T., Roth, P. M., and Bischof,
H. (2014). Occlusion geodesics for online multi-
object tracking. In IEEE Conf. Comput. Vision Pattern
Recognit., pages 1306–1313.
POV-Ray (2019). POV-Ray The persistence of vision ray-
tracer, persistence of vision raytracer pty. ltd. http:
//www.povray.org/.
Salvi, D., Waggoner, J., Temlyakov, A., and Wang, S.
(2013). A graph-based algorithm for multi-target
tracking with occlusion. In IEEE Workshop Appl.
Comput. Vision, pages 489–496.
Shu, G., Dehghan, A., Oreifej, O., Hand, E., and Shah, M.
(2012). Part-based multiple-person tracking with par-
tial occlusion handling. In IEEE Conf. Comput. Vision
Pattern Recognit., pages 1815–1821.
Song, B., Jeng, T.-Y., Staudt, E., and Roy-Chowdhury,
A. K. (2010). A stochastic graph evolution framework
for robust multi-target tracking. In Eur. Conf. Comput.
Vision, pages 605–619.
Zhang, L., Li, Y., and Nevatia, R. (2008). Global data asso-
ciation for multi-object tracking using network flows.
In IEEE Conf. Comput. Vision Pattern Recognit.
Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., and Yang,
M.-H. (2018). Online multi-object tracking with dual
matching attention networks. In Eur. Conf. Comput.
Vision, pages 379–396.