![](bg6.png)
global approach based on the Faster R-CNN detection
presents a reduced number of false positive trajecto-
ries. We have successfully found a way to keep the
same ID for each object as long as possible by our
”update step” to correct tracklets and associate non
detections.
In the future work, we will use a network camera
to track objects.
ACKNOWLEDGEMENT
This work is sponsored by a co-guardianship between
the University of Sousse (Tunisia) and Blaise Pascal
University (France).
REFERENCES
Ahuja, R. K., Magnanti, T. L., and Orlin, J. B. (1993). Net-
work flows: theory, algorithms, and applications.
Badie, J. (2015). Optimizing Process for Tracking People
in video-camera network. PhD thesis, Universite Nice
Sophia Antipolis.
Badie, J. and Bremond, F. (2014). Global tracker: an on-
line evaluation framework to improve tracking qual-
ity. In Advanced Video and Signal Based Surveillance
(AVSS), 2014 11th IEEE International Conference on,
pages 25–30. IEEE.
Bae, S.-H. and Yoon, K.-J. (2014). Robust online multi-
object tracking based on tracklet confidence and on-
line discriminative appearance learning. In 2014 IEEE
Conference on Computer Vision and Pattern Recogni-
tion, pages 1218–1225. IEEE.
Bar-Shalom, Y., Fortmann, T., and Scheffe, M. (1980). Joint
probabilistic data association for multiple targets in
clutter. In Proc. Conf. on Information Sciences and
Systems, pages 404–409.
Battini, C. and Landi, G. (2015). 3d tracking based
augmented reality for cultural heritage data manage-
ment. The International Archives of Photogramme-
try, Remote Sensing and Spatial Information Sciences,
40(5):375.
Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier,
E., and Van Gool, L. (2011). Online multiper-
son tracking-by-detection from a single, uncalibrated
camera. IEEE transactions on pattern analysis and
machine intelligence, 33(9):1820–1833.
Chong, C.-Y., Mori, S., Govaers, F., and Koch, W. (2014).
Comparison of tracklet fusion and distributed kalman
filter for track fusion. In Information Fusion (FU-
SION), 2014 17th International Conference on, pages
1–8. IEEE.
Dehghan, A., Modiri Assari, S., and Shah, M. (2015).
Gmmcp tracker: Globally optimal generalized max-
imum multi clique problem for multiple object track-
ing. In Proceedings of the IEEE Conference on Com-
puter Vision and Pattern Recognition, pages 4091–
4099.
Erdem, C. E., Sankur, B., and Tekalp, A. M. (2004). Per-
formance measures for video object segmentation and
tracking. IEEE Transactions on Image Processing,
13(7):937–951.
Gidaris, S. and Komodakis, N. (2015). Object detection
via a multi-region and semantic segmentation-aware
cnn model. In Proceedings of the IEEE International
Conference on Computer Vision, pages 1134–1142.
Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE
International Conference on Computer Vision, pages
1440–1448.
Hadi, R. A., Sulong, G., and George, L. E. (2014). Vehicle
detection and tracking techniques: a concise review.
arXiv preprint arXiv:1410.5894.
Kuo, C.-H., Huang, C., and Nevatia, R. (2010). Multi-target
tracking by on-line learned discriminative appearance
models. In Computer Vision and Pattern Recognition
(CVPR), 2010 IEEE Conference on, pages 685–692.
IEEE.
Maamatou, H., Chateau, T., Gazzah, S., Goyat, Y., and
Amara, N. E. B. (2015). Transfert d’apprentissage par
un filtre s
´
equentiel de monte carlo: application
`
a la
sp
´
ecialisation d’un d
´
etecteur de pi
´
etons. In Journ
´
ees
francophones des jeunes chercheurs en vision par or-
dinateur.
Mao, Y. and Yin, Z. (2015). Training a scene-specific pedes-
trian detector using tracklets. In 2015 IEEE Win-
ter Conference on Applications of Computer Vision,
pages 170–176. IEEE.
Nillius, P., Sullivan, J., and Carlsson, S. (2006). Multi-
target tracking-linking identities using bayesian net-
work inference. In 2006 IEEE Computer Society Con-
ference on Computer Vision and Pattern Recognition
(CVPR’06), volume 2, pages 2187–2194. IEEE.
Ouyang, W., Wang, X., Zeng, X., Qiu, S., Luo, P., Tian,
Y., Li, H., Yang, S., Wang, Z., Loy, C.-C., et al.
(2015). Deepid-net: Deformable deep convolutional
neural networks for object detection. In Proceedings
of the IEEE Conference on Computer Vision and Pat-
tern Recognition, pages 2403–2412.
Poiesi, F., Mazzon, R., and Cavallaro, A. (2013). Multi-
target tracking on confidence maps: An application to
people tracking. Computer Vision and Image Under-
standing, 117(10):1257–1272.
Simonyan, K. and Zisserman, A. (2014). Very deep con-
volutional networks for large-scale image recognition.
arXiv preprint arXiv:1409.1556.
Stauffer, C. (2003). Estimating tracking sources and sinks.
In Computer Vision and Pattern Recognition Work-
shop, 2003. CVPRW’03. Conference on, volume 4,
pages 35–35. IEEE.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.,
Anguelov, D., Erhan, D., Vanhoucke, V., and Rabi-
novich, A. (2015). Going deeper with convolutions.
In Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition, pages 1–9.
Tran, Q.-V. (2016). Non-contact breath motion detection
using the lucas-kanade algorithm.
Multi Target Tracking by Linking Tracklets with a Convolutional Neural Network
497