To satisfy the distinctive feature extraction requirement of one-shot learning gesture recognition for mobile robot control,a improved three-dimensional local sparse motion scale invariant feature transform(3d SMoSIFT...
详细信息
ISBN:
(纸本)9781479970186
To satisfy the distinctive feature extraction requirement of one-shot learning gesture recognition for mobile robot control,a improved three-dimensional local sparse motion scale invariant feature transform(3d SMoSIFT) feature descriptor is proposed,which fuses RGB-d ***,gray pyramid,depth pyramid andoptical flow pyramids are built as scale space for each gray frame(converted from RGB frame) anddepth *** interest regions are extracted according the variance of optical flow,andvariance is calculated in horizontal and vertical ***,corners are just extracted in each interest region as interest points,and then the information of gray anddepth optical flow is simultaneously used to detect robust keypoints around the motion pattern in the scale ***,SIFT descriptors are calculated on 3d gradient space and 3d motion *** improved feature descriptor has been evaluated under a bag of feature model on one-shot learning Chalearn Gesture *** demonstrate that the proposed methoddistinctly improves the accuracy of gesture *** results also show that the improved 3d SMoSIFT feature descriptor surpasses other spatiotemporal feature descriptors and is comparable to the state-of-the-art approaches.
暂无评论