Continuous Gesture Recognition with Hand-Oriented Spatiotemporal Feature

Abstract

In this paper, an efficient spotting-recognition framework is proposed to tackle the large scale continuous gesture recognition problem with the RGB-D data input. Concretely, continuous gestures are firstly segmented into isolated gestures based on the accurate hand positions obtained by two streams Faster R-CNN hand detector In the subsequent recognition stage, firstly, towards the gesture representation, a specific hand-oriented spatiotemporal (ST) feature is extracted for each isolated gesture video by 3D convolutional network (C3D). In this feature, only the hand regions and face location are considered, which can effectively block the negative influence of the distractors, such as the background, cloth and the body and so on. Next, the extracted features from calibrated RGB and depth channels are fused to boost the representative power and the final classification is achieved by using the simple linear SVM. Extensive experiments are conducted on the validation and testing sets of the Continuous Gesture Datasets (ConGD) to validate the effectiveness of the proposed recognition framework. Our method achieves the promising performance with the mean Jaccard Index of 0.6103 and outperforms other results in the ChaLearn LAP Large-scale Continuous Gesture Recognition Challenge.