Abstract：Aimed to the poor discrimination of the traditional histogram feature,a Hierarchical Structure Histogram (HSH) is proposed in this paper.Firstly,it transforms the target image into hierarchical sub images according to the intensity value.Then,it calculates the histograms based on the structure image element for each hierarchical sub image according to the predefined structure image element.Finally,it integrates the histograms to obtain the final hierarchical structure feature.Take image matching and visual tracking as two representative examples,a lot of experiments were carried out based on the proposed feature.The experimental results indicate that the proposed feature owns better discriminative performance and local description performance than the referenced features.The similarity map obtained from the HSH-based image matching has a much more discriminative single-humped characteristic.The HSH feature can also dramatically decrease the tracking errors for visual tracking.
[1] 余旺盛,等.基于区域边缘统计的图像特征描述新方法[J].计算机学报.2014,37(6):1398-1410. W S Yu,et al.A new image feature descriptor based ob region edge statistical[J].Chinese Journal of Computers.2014,37(6):1398-1410.(in Chinese)
[2] T Ojala,et al.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(7):972-987.
[3] N Dalal,et al.Histograms of oriented gradients for human detection[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].San Diego,USA:IEEE Press,2005.20-25.
[4] S T Birchfield,et al.Spatiograms versus histograms for region-based tracking[A].In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].San Diego,USA:IEEE Press,2005.1158-1163.
[5] D Lowe.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision.2004,60(2):91-110.
[6] B Fan,et al.Rotationally invariant descriptors using intensity order pooling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):2031-2045.
[7] C Ma,et al.Hierarchical convolutional features for visual tracking[A].Proceedings of the IEEE International Conference on Computer Vision[C].Santiago,Chile:Springer-Verlag,2015.3074-3082.
[8] F Zhao,et al.Deep semantic ranking based hashing for multi-label image retrieval[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Boston,USA:IEEE Press,2015.1556-1564.
[9] K Zhang,et al.Robust visual tracking via convolutional networks without training[J].IEEE Transactions on Image Processing,2016,25(4):1779-1792.
[10] T Liu,et al.Real-time part-based visual tracking via adaptive correlation filters[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015[C].Boston,USA:IEEE Press,2015.4902-4912.
[11] P Perez,et al.Color-based probabilistic tracking[A].In:Proceedings of the European Conference on Computer Vision[C].Berlin,Germany:Springer-Verlag,2002.661-75.
[12] Y Wu,et al.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2015,37(9):1834-1848.
[13] K Mikolajczyk,et al.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(10):1615-1630.
[14] B Fan,et al.Receptive fields selection for binary feature description[J].IEEE Transactions on Image Processing.2014,23(6):2583-2595.
2017, Vol. 45 
