Activity recognition with echo state networks using 3D body joints and objects category
نویسندگان
چکیده
In this paper we present our experiments with an echo state network (ESN) for the task of classifying high-level human activities from video data. ESNs are recurrent neural networks which are biologically plausible, fast to train and they perform well in processing arbitrary sequential data. We focus on the integration of body motion with the information on objects manipulated during the activity, in order to overcome the visual ambiguities introduced by the processing of articulated body motion. We investigate the outputs learned and the accuracy of classification obtained with ESNs by using a challenging dataset of long high-level activities. We finally report the results achieved on this dataset.
منابع مشابه
WALKING WALKing walking: Action Recognition from Action Echoes
Recognizing human actions represented by 3D trajectories of skeleton joints is a challenging machine learning task. In this paper, the 3D skeleton sequences are regarded as multivariate time series, and their dynamics and multiscale features are efficiently learned from action echo states. Specifically, first the skeleton data from the limbs and trunk are projected into five high dimensional no...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملCategory-Specific Salient View Selection via Deep Convolutional Neural Networks
In this paper, we present a new framework to determine up front orientations and detect salient views of 3D models. The salient viewpoint to human preferences is the most informative projection with correct upright orientation. Our method utilizes two Convolutional Neural Network (CNN) architectures to encode category-specific information learnt from a large number of 3D shapes and 2D images on...
متن کامل3D Face Recognition using Patch Geodesic Derivative Pattern
In this paper, a novel Patch Geodesic Derivative Pattern (PGDP) describing the texture map of a face through its shape data is proposed. Geodesic adjusted textures are encoded into derivative patterns for similarity measurement between two 3D images with different pose and expression variations. An extensive experimental investigation is conducted using the publicly available Bosphorus and BU-3...
متن کاملRGB-D Object Recognition Using Deep Convolutional Neural Networks
We address the problem of object recognition from RGB-D images using deep convolutional neural networks (CNNs). We advocate the use of 3D CNNs to fully exploit the 3D spatial information in depth images as well as the use of pretrained 2D CNNs to learn features from RGB-D images. There exists currently no large scale dataset available comprising depth information as compared to those for RGB da...
متن کامل