Learn More
Human action recognition based on the depth information provided by commodity depth sensors is an important yet challenging task. The noisy depth maps, different lengths of action sequences, and free styles in performing actions, may cause large intra-class variations. In this paper, a new framework based on sparse coding and temporal pyramid matching (TPM)(More)
— Energy infrastructure is a critical underpinning of modern society. To ensure its safe and healthy operation, a wide-area situational awareness system is essential to provide high-resolution understanding of the system dynamics such that proper actions can be taken in time in response to power system disturbances and to avoid cascading blackouts. This(More)
Distributed object recognition is a significantly fast-growing research area, mainly motivated by the emergence of high performance cameras and their integration with modern wireless sensor network technologies. In wireless distributed object recognition, the bandwidth is limited and it is desirable to avoid transmitting redundant visual features from(More)
Multi-view human action recognition has gained a lot of attention in recent years for its superior performance as compared to the single view recognition. In this paper, we propose algorithms for the real-time realization of human action recognition in distributed camera networks (DCNs). We first present a new method for fast calculation of motion(More)
To deal with the problem of view invariant action recognition, this paper presents a novel approach to recognize human actions across cameras via reconstructable paths. Each action is modelled as a bag of visual-words based on the spatio-temporal features. Although this action representation is sensitive to view changes, the proposed reconstructable path is(More)
ii This dissertation is dedicated to my loving wife Ruoning and my cute son Isaac Li (李溪根). iii Acknowledgements I would like to thank all the individuals who have inspired, encouraged, and advised me in the preparation of this dissertation. First and foremost, I would like to thank my advisor, Dr. Hairong Qi. Her willingness to support my work and her(More)
—In this paper, we present a comparative study of several unsupervised unmixing algorithms to anomaly detection in hyperspectral images. The algorithms are called minimum volume constrained non-negative matrix factorization (MVC-NMF) [1], gradient descent maximum entropy (GDME) [2] and unsupervised fully constrained least squares (UFCLS) [3]. Several(More)