Improved Collaborative Representation Classifier Based on l2-Regularized for Human Action Recognition

Abstract

Human action recognition is an important recent challenging task. Projecting depth images onto three depth motion maps (DMMs) and extracting deep convolutional neural network (DCNN) features are discriminant descriptor features to characterize the spatiotemporal information of a specific action from a sequence of depth images. In this paper, a unified improved collaborative representation framework is proposed in which the probability that a test sample belongs to the collaborative subspace of all classes can be well defined and calculated. The improved collaborative representation classifier (ICRC) based on 2 -regularized for human action recognition is presented to maximize the likelihood that a test sample belongs to each class, then theoretical investigation into ICRC shows that it obtains a final classification by computing the likelihood for each class. Coupled with the DMMs and DCNN features, experiments on depth image-based action recognition, including MSRAction3D and MSRGesture3D datasets, demonstrate that the proposed approach successfully using a distance-based representation classifier achieves superior performance over the state-of-the-art methods, including SRC, CRC, and SVM.

Human Motion Gesture Recognition Algorithm in Video Based on Convolutional Neural Features of Training Images

“…The deep convolutional features of video frames are extracted through deep neural networks; then a pyramidlike structure of video feature expression is constructed, and then the feature expression of the entire video sequence is obtained; finally, the video is classified and recognized by the classifier [7,8]. A multi-source deep neural network model is constructed, which non-linearly represents image features from different sources, and estimates the human body's action posture by extracting high-level human joint features from video information [9]. By fine-tuning the deep convolutional neural network trained on the Imagen net dataset, several feature fusion strategies are proposed based on the idea of fusing the features of the convolutional neural network.…”

Pedestrian Re-Identification Monitoring System Based on Deep Convolutional Neural Network

“…Pedestrian re-identification refers to the similarity matching of pedestrian targets under the surveillance of multiple cameras without the overlapping of viewing angles. Its application in monitoring systems is a hot topic in the field of computer vision [5], [36]. As shown in Figure 1 [6], the target (the pedestrian, point 1), can be identified and locked in multiple cameras in different locations or in the same video (point 1, dotted circles).…”