Haiyong Zhao

Learn More
—This paper presents a new method of human activity recognition, which is based on ℜ transform and dynamic time warping (DTW) after the key frame is extracted from a cycle. For a key binary human silhouette, ℜ transform is employed to represent low-level features. The advantage of the ℜ transform lies in its low computational complexity and geometric(More)
—This paper presents a new classification method for single subject's motion. We employ ℜ transform descriptor and Linear-chain Conditional Random Fields for representation and classification. What it solves is that global features are described and adjacent states are independent. We extract binary silhouettes from a video sequence and segment them into(More)
—In this paper, we present a new posture classification system to analyze different human activities directly from video sequence. For well recognizing each posture of an activity, we propose an adaptation of Radon transform called R-transform, which is invariant to common geometrical transformations, to represent low-level features. The advantage of the R(More)
We present a new gait identification method based on dynamic time warping (DTW), as video surveillance system requires high accuracy and precision. It could reduce computational cost of gait recognition, significantly improve the recognition rate for gait and meet the demand of video surveillance. The characters of human appearance have been utilized to(More)
  • 1