scholarly journals Three dimensional binary edge feature representation for pain expression analysis

2015 ◽  
Author(s):  
Xing Zhang ◽  
Lijun Yin ◽  
Jeffrey F. Cohn
Keyword(s):  
Expression Analysis ◽  
Three Dimensional ◽  
Feature Representation ◽  
Pain Expression ◽  
Binary Edge ◽  
Edge Feature

scholarly journals Latent 3D Volume for Joint Depth Estimation and Semantic Segmentation from a Single Image

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5765 ◽  
Author(s):  
Seiya Ito ◽  
Naoshi Kaneko ◽  
Kazuhiko Sumi
Keyword(s):  
3D Structure ◽  
Three Dimensional ◽  
Semantic Segmentation ◽  
Depth Estimation ◽  
Image Features ◽  
Feature Representation ◽  
Single Image ◽  
Feature Vectors ◽  
3D Space ◽  
3D Volume

This paper proposes a novel 3D representation, namely, a latent 3D volume, for joint depth estimation and semantic segmentation. Most previous studies encoded an input scene (typically given as a 2D image) into a set of feature vectors arranged over a 2D plane. However, considering the real world is three-dimensional, this 2D arrangement reduces one dimension and may limit the capacity of feature representation. In contrast, we examine the idea of arranging the feature vectors in 3D space rather than in a 2D plane. We refer to this 3D volumetric arrangement as a latent 3D volume. We will show that the latent 3D volume is beneficial to the tasks of depth estimation and semantic segmentation because these tasks require an understanding of the 3D structure of the scene. Our network first constructs an initial 3D volume using image features and then generates latent 3D volume by passing the initial 3D volume through several 3D convolutional layers. We apply depth regression and semantic segmentation by projecting the latent 3D volume onto a 2D plane. The evaluation results show that our method outperforms previous approaches on the NYU Depth v2 dataset.

Wavelet-Based Surface Analysis for Form Feature Extraction

2000 ◽  
Author(s):  
Lei Sun ◽  
Abir Qamhiyah
Keyword(s):  
Feature Extraction ◽  
Wavelet Transforms ◽  
Three Dimensional ◽  
Feature Representation ◽  
Cad Model ◽  
Vanishing Moments ◽  
Planar Surfaces ◽  
Solid Models ◽  
Form Features ◽  
Form Feature

Abstract A new procedure for extracting form features from solid models with non-planar surfaces is presented in this paper. In the procedure, a surface is selected as the unit for feature representation, i.e. “feature primitive.” Three-dimensional wavelet transforms are applied to code and classify surfaces in a CAD model. Form features are then extracted by clustering the coded surfaces. Two wavelet bases, Harr and Daubechies with different vanishing moments, have been implemented. An example is presented to demonstrate the proposed procedure.

A Multi-Gradation Stereo Matching Method Based on Edge Feature Points

2013 ◽  
Vol 748 ◽  
pp. 624-628
Author(s):  
Zhu Lin Li
Keyword(s):  
Object Recognition ◽  
Stereo Matching ◽  
Three Dimensional ◽  
Feature Points ◽  
Image Pair ◽  
Three Dimensional Reconstruction ◽  
Matching Method ◽  
Matching Algorithm ◽  
Dimensional Reconstruction ◽  
Edge Feature

A gradation stereo matching algorithm based on edge feature points was proposed. Its basic idea is: firstly edge feature points of image pair were extracted; then, gradient invariability and singular eigenvalue invariability were analyzed, two-grade stereo matching method was build, foundation matrix was solved further, and three-grade stereo matching algorithm was finished by foundation matrix guidance. The result indicates that the algorithm can improve matching precision, from 58.3% to 73.2%, it is simple and utility, and it is important for object recognition, tracking, and three-dimensional reconstruction.

Human Action Recognition Based on Normalized Interest Points and Super-Interest Points

2014 ◽  
Vol 11 (01) ◽  
pp. 1450005
Author(s):  
Yangyang Wang ◽  
Yibo Li ◽  
Xiaofei Ji
Keyword(s):  
Action Recognition ◽  
Clustering Algorithm ◽  
Three Dimensional ◽  
Temporal Correlation ◽  
Human Action Recognition ◽  
Human Action ◽  
Feature Representation ◽  
Interest Point ◽  
Interest Points ◽  
Active Research

Visual-based human action recognition is currently one of the most active research topics in computer vision. The feature representation directly has a crucial impact on the performance of the recognition. Feature representation based on bag-of-words is popular in current research, but the spatial and temporal relationship among these features is usually discarded. In order to solve this issue, a novel feature representation based on normalized interest points is proposed and utilized to recognize the human actions. The novel representation is called super-interest point. The novelty of the proposed feature is that the spatial-temporal correlation between the interest points and human body can be directly added to the representation without considering scale and location variance of the points by introducing normalized points clustering. The novelty concerns three tasks. First, to solve the diversity of human location and scale, interest points are normalized based on the normalization of the human region. Second, to obtain the spatial-temporal correlation among the interest points, the normalized points with similar spatial and temporal distance are constructed to a super-interest point by using three-dimensional clustering algorithm. Finally, by describing the appearance characteristic of the super-interest points and location relationship among the super-interest points, a new feature representation is gained. The proposed representation formation sets up the relationship among local features and human figure. Experiments on Weizmann, KTH, and UCF sports dataset demonstrate that the proposed feature is effective for human action recognition.

scholarly journals PVRNet: Point-View Relation Neural Network for 3D Shape Recognition

2019 ◽  
Vol 33 ◽  
pp. 9119-9126 ◽  
Author(s):  
Haoxuan You ◽  
Yifan Feng ◽  
Xibin Zhao ◽  
Changqing Zou ◽  
Rongrong Ji ◽  
...  
Keyword(s):  
Point Cloud ◽  
Shape Recognition ◽  
Three Dimensional ◽  
Feature Representation ◽  
Research Attention ◽  
Single View ◽  
3D Shape ◽  
3D Data ◽  
Effective Network ◽  
Fusion Feature

Three-dimensional (3D) shape recognition has drawn much research attention in the field of computer vision. The advances of deep learning encourage various deep models for 3D feature representation. For point cloud and multi-view data, two popular 3D data modalities, different models are proposed with remarkable performance. However the relation between point cloud and views has been rarely investigated. In this paper, we introduce Point-View Relation Network (PVRNet), an effective network designed to well fuse the view features and the point cloud feature with a proposed relation score module. More specifically, based on the relation score module, the point-single-view fusion feature is first extracted by fusing the point cloud feature and each single view feature with point-singe-view relation, then the pointmulti- view fusion feature is extracted by fusing the point cloud feature and the features of different number of views with point-multi-view relation. Finally, the point-single-view fusion feature and point-multi-view fusion feature are further combined together to achieve a unified representation for a 3D shape. Our proposed PVRNet has been evaluated on ModelNet40 dataset for 3D shape classification and retrieval. Experimental results indicate our model can achieve significant performance improvement compared with the state-of-the-art models.

scholarly journals A Novel Sketch-Based Three-Dimensional Shape Retrieval Method Using Multi-View Convolutional Neural Network

Symmetry ◽  
2019 ◽  
Vol 11 (5) ◽  
pp. 703 ◽  
Author(s):  
Dianhui Mao ◽  
Zhihao Hao
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Three Dimensional ◽  
Large Data ◽  
Feature Space ◽  
3D Models ◽  
Feature Representation ◽  
Model Calculations ◽  
Projection View

Retrieving 3D models by adopting hand-drawn sketches to be the input has turned out to be a popular study topic. Most current methods are based on manually selected features and the best view produced for 3D model calculations. However, there are many problems with these methods such as distortion. For the purpose of dealing with such issues, this paper proposes a novel feature representation method to select the projection view and adapt the maxout network to the extended Siamese network architecture. In addition, the strategy is able to handle the over-fitting issue of convolutional neural networks (CNN) and mitigate the discrepancies between the 3D shape domain and the sketch. A pre-trained AlexNet was used to sketch the extract features. For 3D shapes, multiple 2D views were compiled into compact feature vectors using pre-trained multi-view CNNs. Then the Siamese convolutional neural networks were learnt for transforming the two domains’ original characteristics into nonlinear feature space, which mitigated the domain discrepancy and kept the discriminations. Two large data sets were used for experiments, and the experimental results show that the method is superior to the prior art methods in accuracy.

Sign in / Sign up

Export Citation Format

Share Document