机译:在时空特征域上识别步态
Fac. of Inf. & Commun. Technol., Mahidol Univ., Nakhon Pathom, Thailand;
feature extraction; gait analysis; image motion analysis; image recognition; image representation; image sequences; video signal processing; 3D video patch; STIP descriptor; biometric feature; gait feature extraction process; gait recognition; gait representation; histogram of optical flow; histogram of oriented gradient; local spatiotemporal volumes; partial occlusion; person identification; raw gait video sequence; space-time interest points; spatiotemporal feature domain; Feature extraction; Gait recognition; Histograms; Legged locomotion; Optical imaging; Probes; Shape; BoW; Gait recognition; HOF; HOG; STIP; human identification; spatio-temporal;
机译:步态度量学习暹罗网络,利用时空3D-CNN内部和基于LSTM的步态周期片段之间的双重特征
机译:步态公制学习暹罗网络利用两种时空3D-CNN intra和LSTM基于间步态循环段特征的
机译:基于频域步态熵特征的有效基于零件的步态识别
机译:快速小波网络分类器的基于模型和自由模型的特征提取识别步态
机译:一种分析和识别人的步态的方法。
机译:WDR26单倍剂量不足会导致智障癫痫发作步态异常和面部特征明显的综合症
机译:使用时空特征识别类似动作的概率框架