Abstract To solve the problem of low computational efficiency and many redundant feature points in feature point detection algorithm, a fast spatial-temporal feature point detection algorithm based on local neighbor pixels is proposed. The spatial-temporal feature points are located quickly by finding the points with great difference in pixel value in 3D spatial-temporal local neighborhood. Then the redundant feature points are removed with the 3D non-maxima suppression method, and the screened feature points are applied to human action recognition. In addition, the range of pixel segmentation threshold in local area and other detection problems of parameter optimization are analyzed according to binomial probability distribution principle. The experimental results show that the proposed algorithm not only improves the speed of feature point detection but also reliably detects enough amounts of feature points with the least redundancy, which leads to the high accuracy in human action recognition.
[1] Harris C, Stephens M. A Combined Corner and Edge Detector// Proc of the 4th Alvey Vision Conference. Manchester, UK, 1988: 147-151 [2] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [3] Laptev I, Lindeberg T. Space-Time Interest Points // Proc of the 9th IEEE International Conference on Computer Vision. Nice, France, 2003, I: 432-439 [4] Dollár P, Rabaud V, Cottrell G, et al. Behavior Recognition via Sparse Spatio-Temporal Features // Proc of the 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Beijing, China, 2005: 65-72 [5] Rosten E, Drummond T. Fusing Points and Lines for High Performance Tracking // Proc of the 10th IEEE International Conference on Computer Vision. Beijing, China, 2005, II: 1508-1515 [6] Koelstra S, Patras I. The FAST-3D Spatio-Temporal Interest Region Detector // Proc of the 10th Workshop on Image Analysis for Multimedia Interactive Services. London, UK, 2009: 242-245 [7] Yu T H, Kim T K, Cipolla R. Real-Time Action Recognition by Spatiotemporal Semantic and Structural Forests // Proc of the British Machine Vision Conference. Aberystwyth, UK, 2010. DOI: 10.5244/C.42.52 [8] Zhou L P. Corners Detection Based on Improved Harris Algorithm. Computer Technology and Development, 2013, 23(2): 11-14 (in Chinese) (周龙萍.基于改进的Harris算法检测角点.计算机技术与发展, 2013, 23(2): 11-14) [9] Wang J, Wang H L, Xiang M S, et al. Subpixel Accuracy Central Location of Circle Target Based on Nonmaximum Suppression. Chinese Journal of Scientific Instrument, 2012, 33(7): 1460-1468 (in Chinese) (王 静,王海亮,向茂生,等.基于非极大值抑制的圆目标亚像素中心定位.仪器仪表学报, 2012, 33(7): 1460-1468) [10] Gorelick L, Blank M, Shechtman E, et al. Actions as Space-Time Shapes. IEEE Trans of Pattern Analysis and Machine Intelligence, 2007, 29(12): 2247-2253 [11] Laptev I, Marszalek M, Schmid C, et al. Learning Realistic Human Actions from Movies // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA, 2008: 1-8 [12] Mahbub U, Imtiaz H, Ahad M A R, et al. Motion Clustering-Based Action Recognition Technique Using Optical Flow // Proc of the International Conference on Informatics, Electronics & Vision. Dhaka, Bangladesh, 2012: 919-924 [13] Acar E, Senst T, Kuhn A, et al. Human Action Recognition Using Lagrangian Descriptors // Proc of the 14th IEEE International Workshop on Multimedia Signal Processing. Banff, Canada, 2012: 360-365
2015, Vol. 28 
