Trace Inference, Curvature Consistency, and Curve Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Experiments in the machine interpretation of visual motion
Experiments in the machine interpretation of visual motion
Computing perceptual organization in computer vision
Computing perceptual organization in computer vision
An application of heuristic search methods to edge and contour detection
Communications of the ACM
Use of the Hough transformation to detect lines and curves in pictures
Communications of the ACM
Measurement of Image Velocity
Moving Object Tracking in Video
AIPR '00 Proceedings of the 29th Applied Imagery Pattern Recognition Workshop
| Hi-index | 0.00 |
In this paper, we present a perceptual organization-based method for detecting moving objects from image sequences. To achieve the characteristics of real-time, efficiency, and robustness, a perceptual computation model of edge partitioning and grouping was proposed for the extraction of edge traces on the fly. Each edge trace is made up of generic edge tokens (GETs) which are perceptual features, and defined qualitatively based on the principles of Gestalt laws. Motion detection uses two basic computations: (1) segment motion GETs (MGETs) by computing the gradient differences between GET streams in consecutive frames; and (2) detect motion objects by perceptually grouping MGETs into object clusters. The MGETs in each cluster are constrained by the proximity of the features, and the motion continuation of the cluster measured by motion persistence, etc. Experimental results are provided.