Abstract | ||
---|---|---|
Reichardt motion detector is the most basic mechanism of motion perception of biological vision system. But because of the aperture problem and the dependence of scene pattern, the detected motion information is always ambiguity. However, the vision cognition mechanism shows that: the motion perception of vision system doesn’t only detect motion velocity, but also supplies the temporal feature to assist object recognition. Thus this paper puts emphasis on the contribution of temporal features to the moving object recognition and extraction, rather than the accuracy of motion estimation. A spatial-temporal iterative feed forward method was proposed to identify the moving objects. The common motion information is propagated along the similar spatial features; the temporal synchrony binds spatial features of the same object. By the interactive process, the moving object will be recognized and extracted by the bound spatial feature, and the ambiguity motion information will be corrected. The proposed method can overcome error motion information caused by noise, camera-self oscillation and poor luminance. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/CIT.2010.116 | CIT |
Keywords | Field | DocType |
object recognition,motion perception,motion information,reichardt motion detector,temporal feature,common motion information,motion estimation,ambiguity motion information,visual cognition mechanism,extraction method,error motion information,motion velocity,biology,oscillations,detectors,information retrieval,vision system,visual perception,pixel,feed forward,feature extraction,aperture problem,cognition | Structure from motion,Computer vision,3D single-object recognition,Motion field,Computer science,Motion detector,Artificial intelligence,Motion estimation,Optical flow,Kinetic depth effect,Match moving | Conference |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Min Li | 1 | 103 | 26.84 |
Huibin Wang | 2 | 29 | 10.99 |
Xijun Yan | 3 | 2 | 1.75 |
Xu Lizhong | 4 | 155 | 24.51 |