Skip to main content

2017 | OriginalPaper | Buchkapitel

Using Stacked Auto-encoder to Get Feature with Continuity and Distinguishability in Multi-object Tracking

verfasst von : Haoyang Feng, Xiaofeng Li, Peixin Liu, Ning Zhou

Erschienen in: Image and Graphics

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Good feature expression of targets plays an important role in multi-object tracking (MOT). Inspired by the self-learning concept of deep learning methods, an online feature extraction scheme is proposed in this paper, based on a conditional random field (CRF). The CRF model is transformed into a certain number of multi-scale stacked auto-encoders with a new loss function. Features obtained with our method contain both continuous and distinguishable characteristics of targets. The inheritance relationship of stacked auto-encoders between adjacent frames is implemented by an online process. Features extracted from our online scheme are applied to improve the network flow tracking model. Experiment results show that the features by our method achieve better performance compared with other handcrafted-features. The overall tracking performance are improved when our features are used in the MOT tasks.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008) Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)
3.
Zurück zum Zitat Butt, A.A., Collins, R.T.: Multi-target tracking by lagrangian relaxation to min-cost network flow. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1846–1853 (2013) Butt, A.A., Collins, R.T.: Multi-target tracking by lagrangian relaxation to min-cost network flow. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1846–1853 (2013)
4.
Zurück zum Zitat Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: IEEE Conference on Computer Vision and Pattern Recognition, p. 2142 (2000) Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: IEEE Conference on Computer Vision and Pattern Recognition, p. 2142 (2000)
5.
Zurück zum Zitat Forsyth, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRef Forsyth, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRef
7.
Zurück zum Zitat Lealtaix, L., Milan, A., Reid, I., Roth, S., Schindler, K.: Motchallenge 2015: towards a benchmark for multi-target tracking (2015) Lealtaix, L., Milan, A., Reid, I., Roth, S., Schindler, K.: Motchallenge 2015: towards a benchmark for multi-target tracking (2015)
8.
Zurück zum Zitat Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: Computer Vision and Pattern Recognition, pp. 1201–1208 (2011) Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: Computer Vision and Pattern Recognition, pp. 1201–1208 (2011)
9.
Zurück zum Zitat Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)CrossRef Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)CrossRef
10.
Zurück zum Zitat Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: International Conference, pp. 1096–1103 (2008) Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: International Conference, pp. 1096–1103 (2008)
11.
Zurück zum Zitat Wang, L., Liu, T., Wang, G., Chan, K.L., Yang, Q.: Video tracking using learned hierarchical features. IEEE Trans. Image Process. 24(4), 1424–1435 (2015)MathSciNetCrossRef Wang, L., Liu, T., Wang, G., Chan, K.L., Yang, Q.: Video tracking using learned hierarchical features. IEEE Trans. Image Process. 24(4), 1424–1435 (2015)MathSciNetCrossRef
13.
Zurück zum Zitat Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008) Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)
14.
Zurück zum Zitat Zou, W.Y., Ng, A.Y., Zhu, S., et al.: Deep learning of invariant features via simulated fixations in video. In: Advances in Neural Information Processing Systems, vol. 25, pp. 3212–3220 (2012) Zou, W.Y., Ng, A.Y., Zhu, S., et al.: Deep learning of invariant features via simulated fixations in video. In: Advances in Neural Information Processing Systems, vol. 25, pp. 3212–3220 (2012)
Metadaten
Titel
Using Stacked Auto-encoder to Get Feature with Continuity and Distinguishability in Multi-object Tracking
verfasst von
Haoyang Feng
Xiaofeng Li
Peixin Liu
Ning Zhou
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-71607-7_31