•  
  •  
 

Corresponding Author

El-Nahry, I.

Subject Area

Electrical Engineering

Article Type

Original Study

Abstract

Visual analysis of human arm motion is currently one of the most active research topics in computer vision. This strong interest is driven by a wide spectrum of promising applications in many areas such as virtual reality, biomechanical analysis, smart surveillance and perceptual- interface. Human behaviors, from image sequences involving human. In this paper, a process is described an algorithm for analyzing the arm motion of a human target in a video sequences by image skeletonization. The novelty of this algorithm comes from (i) automatic arm detection, (ii) removing spurious features, (iii) robust of skeleton and features extraction. The cues of the proposed algorithm are used to determine human arm activities such as velocity of shoulder, elbow, wrist and hand. Unlike other algorithms, this does not require a priori human model, or a large number of "pixels on target". Furthermore, it is computationally inexpensive and thus ideal for video applications such as biomechanical analysis.

Keywords

Computer Vision; Motion Segmentation; Image Skeletonization; Feature Extraction; Motion analysis

Share

COinS