Abstract
This paper presents a pedestrian detector adaptation approach that aims at adapting a generic detector pre-trained on a public dataset to a specific scene. We hypothesize that the components of the generic detector are useful for constructing a scene-specific detector. For this purpose, our proposed approach is applied to determine the appropriate weights for recombining the components, such that the new detector is expected to perform better in the target scene. Next, the new detector is used to collect new training samples from unlabeled target data. Finally, a weighted CNN is fine-tuned on the extended training set. The experiments demonstrate that the improvements due to the strategies adopted in the proposed approach are significant.
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
Dai, W., Yang, Q., Xue, G.R., Yu, Y.: Boosting for transfer learning. In: ICML, pp. 193–200 (2007)
Deng, J., Berg, A., Satheesh, S., Su, H., Khosla, A., Fei-Fei, L.: Imagenet large scale visual recognition competition (2012). http://www.image-net.org/challenges/LSVRC/2012/
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE TPAMI 34(4), 743–761 (2012)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066–2073 (2012)
Javed, O., Ali, S., Shah, M.: Online detection and classification of moving objects using progressively improving detectors. In: CVPR, pp. 696–701 (2005)
Jiang, W., Zavesky, E., Chang, S., Loui, A.: Cross-domain learning methods for high-level visual concept classification. In: ICIP, pp. 161–164 (2008)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2014)
Pang, J., Huang, Q., Yan, S., Jiang, S., Qin, L.: Transferring boosted detectors towards viewpoint and scene adaptiveness. IEEE TIP 20(5), 1388–1400 (2011)
Rosenberg, C., Hebert, M., Freund, Y.: Semi-supervised self-training of object detection models. In: IEEE Workshop Application of Computer Vision, pp. 29–36 (2005)
Stalder, S., Grabner, H., Van Gool, L.: Cascaded confidence filtering for improved tracking-by-detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 369–382. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15549-9_27
Tan, M., Wang, L., Tsang, I.W.: Learning sparse SVM for feature selection on very high dimensional datasets. In: ICML, pp. 1047–1054 (2010)
Wang, M., Li, W., Wang, X.: Transferring a generic pedestrian detector towards specific scenes. In: CVPR, pp. 3274–3281 (2012)
Wang, M., Wang, X.: Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In: CVPR, pp. 3401–3408 (2011)
Wang, X., Wang, M., Li, W.: Scene-specific pedestrian detection for static video surveillance. IEEE TPAMI 36(2), 361–374 (2014)
Zeng, X., Ouyang, W., Wang, M., Wang, X.: Deep learning of scene-specific classifier for pedestrian detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 472–487. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_31
Zhang, S., Benenson, R., Schiele, B.: Filtered channels features for pedestrian detection. In: CVPR, pp. 1751–1760 (2015)
Zhang, X., He, F., Tian, L., Wang, S.: Cognitive pedestrian detector: adapting detector to specific scene by transferring attributes. Neurocomputing 149, 800–810 (2015)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China (Project No. 61502173), and in part by the Natural Science Foundation of Guangdong Province (Project No. 2016A030310422).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Lei, S., Ji, Q., Wang, S., Wu, S. (2018). Adapting Generic Detector for Semi-Supervised Pedestrian Detection. In: Zeng, B., Huang, Q., El Saddik, A., Li, H., Jiang, S., Fan, X. (eds) Advances in Multimedia Information Processing – PCM 2017. PCM 2017. Lecture Notes in Computer Science(), vol 10735. Springer, Cham. https://doi.org/10.1007/978-3-319-77380-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-77380-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77379-7
Online ISBN: 978-3-319-77380-3
eBook Packages: Computer ScienceComputer Science (R0)