Abstract | ||
---|---|---|
This paper presents a feature fusion-based tracking algorithm using optical flow under the non-prior training active feature model (NPT-AFM) framework. The proposed object tracking procedure can be divided into three steps: (i) localization of human objects, (ii) prediction and correction of the object’s location by utilizing spatio-temporal information, and (iii) restoration of occlusion using the NPT-AFM[15]. Feature points inside an ellipsoidal shape including objects are estimated instead of its shape boundary, and are updated as an element of the training set for the AFM. Although the proposed algorithm uses the greatly reduced number of feature points, the proposed feature fusion-based multiple people tracking algorithm enables the tracking of occluded people in complicated background. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11581772_74 | PCM (1) |
Keywords | Field | DocType |
multiple people,non-prior training,feature point,proposed object tracking procedure,proposed feature,occluded people,ellipsoidal shape,human object,proposed algorithm,active feature model,optical flow,object tracking | Computer vision,Feature fusion,Ellipsoid,Pattern recognition,Occultation,Computer science,Feature (computer vision),Video tracking,Feature model,Artificial intelligence,Predictor–corrector method,Optical flow | Conference |
Volume | ISSN | ISBN |
3767 | 0302-9743 | 3-540-30027-9 |
Citations | PageRank | References |
3 | 0.41 | 10 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junhaeng Lee | 1 | 115 | 6.23 |
Sangjin Kim | 2 | 52 | 5.17 |
Daehee Kim | 3 | 143 | 25.67 |
Jeongho Shin | 4 | 124 | 17.26 |
Joonki Paik | 5 | 611 | 71.87 |