Andere Kunden interessierten sich auch für
![Time- and Space-Efficient Self-Stabilizing Algorithms]( "Time- and Space-Efficient Self-Stabilizing Algorithms")
Time- and Space-Efficient Self-Stabilizing Algorithms29,70 €![Human Face Detection and Head Pose Estimation on image and video]( "Human Face Detection and Head Pose Estimation on image and video")
Human Face Detection and Head Pose Estimation on image and video47,99 €![Scene Reconstruction Pose Estimation and Tracking]( "Scene Reconstruction Pose Estimation and Tracking")
Scene Reconstruction Pose Estimation and Tracking114,99 €![ARTIFICIAL INTELLIGENCE BASED IMAGE PROCESSING IDENTIFICATION MODEL]( "ARTIFICIAL INTELLIGENCE BASED IMAGE PROCESSING IDENTIFICATION MODEL")
ARTIFICIAL INTELLIGENCE BASED IMAGE PROCESSING IDENTIFICATION MODEL36,99 €![Assembly Language Applications]( "Assembly Language Applications")
Assembly Language Applications69,99 €![A Novel Technique for Web Log Mining with Transaction Identification]( "A Novel Technique for Web Log Mining with Transaction Identification")
A Novel Technique for Web Log Mining with Transaction Identification26,99 €![Defining an Effective Security Policy for Companies using Cloud Compt.]( "Defining an Effective Security Policy for Companies using Cloud Compt.")
Defining an Effective Security Policy for Companies using Cloud Compt.16,99 €
This book explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, a convolutional neural network approach is applied on RGB videos and is extended to three dimensional convolutions. This is done via encoding the time dimension in videos as the third dimension in convolutional space, and directly regressing to human body joint positions in 3D coordinate space. This research shows the ability of such a network to achieve state-of-the-art performance on the selected Human3.6M dataset, thus demonstrating the possibility of successfully representing temporal data with an additional dimension in the convolutional operation.