A Hybrid Framework for Action Recognition in Low-Quality Video Sequences

Vision-based activity recognition is essential for security, monitoring and surveillance applications. Further, real-time analysis having low-quality video and contain less information about surrounding due to poor illumination, and occlusions. Therefore, it needs a more robust and integrated model for low quality and night security operations. In this context, we proposed a hybrid model for illumination invariant human activity recognition based on sub-image histogram equalization enhancement and k-key pose human silhouettes. This feature vector gives good average recognition accuracy on three low exposure video sequences subset of original actions video datasets. Finally, the performance of the proposed approach is tested over three manually downgraded low qualities Weizmann action, KTH, and Ballet Movement dataset. This model outperformed on low exposure videos over existing technique and achieved comparable classification accuracy to similar state-of-the-art methods.

[1]  Weiyao Lin,et al.  Image-based fusion for video enhancement of night-time surveillance , 2010 .

[2]  Alexandros André Chaaraoui,et al.  Silhouette-based human action recognition using sequences of key poses , 2013, Pattern Recognit. Lett..

[3]  L. McMillan,et al.  Video enhancement using per-pixel virtual exposures , 2005, SIGGRAPH 2005.

[4]  Quan Pan,et al.  Combining scene model and fusion for night video enhancement , 2009 .

[5]  Sangkeun Lee,et al.  An Efficient Content-Based Image Enhancement in the Compressed Domain Using Retinex Theory , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Leiting Chen,et al.  A Survey of Video Enhancement Techniques , 2012, J. Inf. Hiding Multim. Signal Process..

[7]  Kuldeep Singh,et al.  Image enhancement using Exposure based Sub Image Histogram Equalization , 2014, Pattern Recognit. Lett..

[8]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[9]  Ramesh Raskar,et al.  Gradient domain context enhancement for fixed cameras , 2005, Int. J. Pattern Recognit. Artif. Intell..

[10]  Sos S. Agaian,et al.  Transform Coefficient Histogram-Based Image Enhancement Algorithms Using Contrast Entropy , 2007, IEEE Transactions on Image Processing.

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[12]  Václav Hlavác,et al.  Pose primitive based human action recognition in videos or still images , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Rajiv Kapoor,et al.  Hybrid classifier based human activity recognition using the silhouette and cells , 2015, Expert Syst. Appl..

[14]  Alfredo Petrosino,et al.  Human activity modeling by spatio temporal textural appearance , 2013, Pattern Recognit. Lett..

[15]  John See,et al.  Deep CNN object features for improved action recognition in low quality videos , 2016, IEEE CSE 2016.

[16]  John See,et al.  Spatio-temporal mid-level feature bank for action recognition in low quality video , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Greg Mori,et al.  Action recognition by learning mid-level motion features , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Deepu Rajan,et al.  Human action recognition using Pose-based discriminant embedding , 2012, Signal Process. Image Commun..

[19]  James W. Davis,et al.  The Recognition of Human Movement Using Temporal Templates , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Leiting Chen,et al.  An Efficient Contourlet-Transform-Based Algorithm for Video Enhancement , 2011, J. Inf. Hiding Multim. Signal Process..

[21]  Yang Wang,et al.  Human Action Recognition by Semilatent Topic Models , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Dinesh Kumar Vishwakarma,et al.  A review of state-of-the-art techniques for abnormal human activity recognition , 2019, Eng. Appl. Artif. Intell..

[23]  Alexandros Iosifidis,et al.  Discriminant Bag of Words based representation for human action recognition , 2014, Pattern Recognit. Lett..

[24]  I. Jolliffe.  Principal Component Analysis and Factor Analysis , 1986 .

[25]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[26]  Ronen Basri,et al.  Actions as Space-Time Shapes , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Ming-Ting Sun,et al.  An effecive night video enhancement algorithm , 2011, 2011 Visual Communications and Image Processing (VCIP).

[28]  Hongxun Yao,et al.  Distinctive action sketch for human action recognition , 2018, Signal Process..

[29]  Dinesh Kumar Vishwakarma,et al.  Covariate Conscious Approach for Gait Recognition Based Upon Zernike Moment Invariants , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[30]  John See,et al.  On the Effects of Low Video Quality in Human Action Recognition , 2015, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[31]  Tej Singh,et al.  Video benchmarks of human action datasets: a review , 2018, Artificial Intelligence Review.

[32]  J.K. Aggarwal,et al.  Human activity analysis , 2011, ACM Comput. Surv..

[33]  John See,et al.  Action recognition in low quality videos by jointly using shape, motion and texture features , 2015, 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).