Abstract
This paper proposes a solution based on Adaptive learning using the CNN model. The proposed method automatically updates the recognition model according to online training dataset accumulated directly from the system and retraining recognition model. The data updating task focuses on data samples that are less similar to previous trained ones. The purpose of this solution is to upgrade the model to a new one more adaptive, expecting to reach higher accuracy. In the adaptive learning approach, the recognition system is capable of self-learning and complementing data, without experts needed for data labeling or training. The proposed solution includes 5 main phases: (1) Detect and recognize low confident objects; (2) Track objects in n frames in future progress to make sure whether they are interesting objects or not. (3) In case of objects that are recognized with high confidence: labeling (same class of object) for the corresponding data samples to be recognized with low confidence scores which were tracked in the previous process. In case of objects determined not to be of interesting objects, the samples are labeled as Negative for all previous samples, which were tracked in n previous frames; (4) Initialize a training dataset based on a selective combination of previously trained data and the new data. (5) Retrain and update the model if it results in higher accuracy. We have conducted experiments to compare results of the proposed model—PDnet and some state of the art methods such as AlexNet and Vgg. The experimental results demonstrate that the proposed method provides the higher accuracy when the model are self-learned over time. On the other hand, our adaptive learning is applicable to the traditional recognition models such as AlexNet and Vgg model for improving accuracy.
Similar content being viewed by others
References
Vapnik V (2013) The nature of statistical learning theory. Springer, Berlin
Ho TK (1995) Random decision forests. In: Proceedings of the third international conference on document analysis and recognition, vol 1. IEEE, pp 278–282
Barandiaran I (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832–844
van Gerven M, Bohte S (2018) Artificial neural networks as models of neural information processing. Frontiers Media SA, Lausanne
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1–9
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 770–778
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 580–587
Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision. IEEE, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. pp 91–99
Deng J, Dong W, Socher R, Li LJ, Li K, Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition (CVPR 2009). IEEE, pp 248–255
Tran DP, Nhu NG, Hoang VD (2018) Pedestrian action prediction based on deep features extraction of human posture and traffic scene. In: Asian conference on intelligent information and database systems. Springer, pp 563–572
Hoang VD, Le MH, Jo KH (2012) Robust human detection using multiple scale of cell based histogram of oriented gradients and adaboost learning. In: International conference on computational collective intelligence. Springer, pp 61–71
Yu Jun, Tao Dacheng MWYR (2015) Learning to rank using user clicks and visual features for image retrieval. In: IEEE transactions on cybernetics. pp 767–779
Yu J, Tao D, Wang M (2012) Adaptive hypergraph learning and its application in image classification. IEEE Trans Image Process 21(7):3262–3272
Yu J, Rui Y, Tao D (2014) Click prediction for web image reranking using multimodal sparse coding. In: IEEE transactions on image processing. pp 2019–2032
Yu J, Kuang Z, Zhang B, Lin D, Fan J (2018) Leveraging content sensitiveness and user trustworthiness to recommend fine-grained privacy settings for social image sharing. In: IEEE transactions on information forensics and security. pp. 1317–1332
Yu J, Wang M, Tao D (2012) Semisupervised multiview distance metric learning for cartoon synthesis. In: IEEE transactions on image processing. pp 4636–4648
Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. In: IEEE transactions on image processing. pp 5659–5670
Hong C, Yu J, Tao D, Wang M (2015) Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. In: IEEE transactions on industrial electronics. pp 3742–3751
Hong C, Yu J, You J, Chen X, Tao D (2015) Multi-view ensemble manifold regularization for 3d object recognition. Inf Sci 320:395–405
Long M, Cao Y, Cao Z, Wang J, Jordan MI (2018) Transferable representation learning with deep adaptation networks. IEEE Trans Pattern Anal Mach Intell 37:256–270
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks?. In: Advances in neural information processing systems. pp 3320–3328
Danelljan M, Robinson A, Khan FS, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: European conference on computer vision. Springer, pp 472–488
Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. In: IEEE transactions on image processing. pp 2420–2432
Long M, Zhu H, Wang J, Jordan MI (2016) Deep transfer learning with joint adaptation networks, arXiv preprint arXiv:1605.06636
Huang C, Lucey S, Ramanan D (2017) Learning policies for adaptive tracking with deep feature cascades. In: IEEE international conference on computer vision (ICCV). IEEE, pp 105–114
Qi Y, Zhang S, Qin L, Yao H, Huang Q, Lim J et al (2016) Hedged deep tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4303–4311
Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4293–4302
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification, ArXiv e-prints
Badrinarayanan V, Kendall A, Cipolla R (2015) SegNet: a deep convolutional encoder–decoder architecture for image segmentation, ArXiv e-prints
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE computer society conference on computer vision and pattern recognition (CVPR 2005), vol 1. IEEE, pp 886–893
Bishop G, Welch G et al (2001) An introduction to the kalman filter. Proc SIGGRAPH Course 8(27599–3175):59
Lucas BD, Kanade T et al (1981) An iterative image registration technique with an application to stereo vision. In: IJCAI’81 proceedings of the 7th international joint conference on artificial intelligence, vol 2, pp 674–679
Tomasi C, Kanade T (1991) Detection and tracking of point features. Int J Comput Vis 9:137–154
Shi J, Tomasi C (1993) Good features to track. Cornell University, New York
Kalal Z, Mikolajczyk K, Matas J (2010) Forward-backward error: automatic detection of tracking failures. In: 2010 20th international conference on pattern recognition (ICPR). IEEE, pp 2756–2759
Acknowledgements
This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under Grant No. 102.05-2015.09. Diem-Phuc Tran is a PhD student in Computer Science, Duy Tan University, Da Nang City, Viet Nam. Van-Dung Hoang has been serving as a senior lecturer in Quang Binh University, Viet Nam. He has been also working as a collaborative researcher in Ton Duc Thang University, Viet Nam.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tran, DP., Hoang, VD. Adaptive Learning Based on Tracking and ReIdentifying Objects Using Convolutional Neural Network. Neural Process Lett 50, 263–282 (2019). https://doi.org/10.1007/s11063-019-10040-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-019-10040-w