Generative Model For Skeletal Human Movements Based On Conditional DCGAN

Generative models for images,audio,text,and other data have achieved great success in recent years.Generating artificial human movements can also be useful for many applications,including improvement of data augmentation methods for human motion recognition.The objective of this research is to develop a generative model for skeletal human movement,allowing to control the action type of generated motion while keeping the authenticity of the result and the natural style variability of gesture execution.This dissertation proposes to use a conditional Deep Convolutional Generative Adversarial Network(c DCGAN)applied to pseudo-images representing skeletal pose sequences using tree structure skeleton image format.The evaluation of approach is made on the 3D skeletal data provided in the large NTU RGB+D public dataset.The proposed generative model can output qualitatively correct skeletal human movements for any of the sixty action classes.This dissertation also quantitatively evaluates the performance of model by computing Fréchet inception distances,which shows strong correlation to human judgement.To sum up,the main contribution of this work is proposing a class-conditioned generative model for human skeletal motions based on pseudo-image representation of skeletal pose sequences.