This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quantization to classify the direction of movement of an object and to estimate its centroid by referring to a codebook of the space-time patch feature, which is generated from multiple learning samples. We segmented the objects’ regions based on the probability calculated from the mask images of the learning samples by using the estimated centroid of the object. Even though occlusions occur when multiple objects overlap in different directions of movement, our method detects objects individually because their direction of movement is classified. Experimental results show that object detection is more accurate with our method than with the conventional method, which is only based on appearance features.
Combined Object Detection and Segmentation by Using Space-Time Patches
Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007
2007-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Multiple Object , Centroid Position , Mask Image , Object Detection , Learning Sample Pattern Recognition , Artificial Intelligence , Algorithm Analysis and Problem Complexity , Computer Science , Biometrics , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics
Segmentation of Range Data into Rigid Subsets using Surface Patches
British Library Conference Proceedings | 1998
|Video Denoising via Empirical Bayesian Estimation of Space-Time Patches
British Library Online Contents | 2018
|Online Contents | 2000