scholarly journals VB-Net: Voxel-Based Broad Learning Network for 3D Object Classification

2020 ◽  
Vol 10 (19) ◽  
pp. 6735 ◽  
Author(s):  
Zishu Liu ◽  
Wei Song ◽  
Yifei Tian ◽  
Sumi Ji ◽  
Yunsick Sung ◽  
...  
Keyword(s):  
Deep Learning ◽  
Three Dimensional ◽  
Object Classification ◽  
Point Clouds ◽  
Learning System ◽  
Learning Networks ◽  
3D Object ◽  
Feature Extractor ◽  
Irregular Point ◽  
3D Object Classification

Point clouds have been widely used in three-dimensional (3D) object classification tasks, i.e., people recognition in unmanned ground vehicles. However, the irregular data format of point clouds and the large number of parameters in deep learning networks affect the performance of object classification. This paper develops a 3D object classification system using a broad learning system (BLS) with a feature extractor called VB-Net. First, raw point clouds are voxelized into voxels. Through this step, irregular point clouds are converted into regular voxels which are easily processed by the feature extractor. Then, a pre-trained VoxNet is employed as a feature extractor to extract features from voxels. Finally, those features are used for object classification by the applied BLS. The proposed system is tested on the ModelNet40 dataset and ModelNet10 dataset. The average recognition accuracy was 83.99% and 90.08%, respectively. Compared to deep learning networks, the time consumption of the proposed system is significantly decreased.

3D object classification based on deep belief networks and point clouds

2019 ◽  
Vol 9 (6) ◽  
pp. 527
Author(s):  
Majid Mohamed Himmi ◽  
El Houssine Bouyakhf ◽  
Fatima Zahra Ouadiay ◽  
Mohamed Hannat ◽  
Nabila Zrira
Keyword(s):  
Object Classification ◽  
Point Clouds ◽  
Belief Networks ◽  
Deep Belief Networks ◽  
3D Object ◽  
3D Object Classification

scholarly journals Noise-Resistant Deep Learning for Object Classification in Three-Dimensional Point Clouds Using a Point Pair Descriptor

2018 ◽  
Vol 3 (2) ◽  
pp. 865-872 ◽  
Author(s):  
Dmytro Bobkov ◽  
Sili Chen ◽  
Ruiqing Jian ◽  
Muhammad Z. Iqbal ◽  
Eckehard Steinbach
Keyword(s):  
Deep Learning ◽  
Three Dimensional ◽  
Object Classification ◽  
Point Clouds ◽  
Point Pair

3D object classification based on deep belief networks and point clouds

2019 ◽  
Vol 9 (6) ◽  
pp. 527
Author(s):  
Fatima Zahra Ouadiay ◽  
Nabila Zrira ◽  
Mohamed Hannat ◽  
El Houssine Bouyakhf ◽  
Majid Mohamed Himmi
Keyword(s):  
Object Classification ◽  
Point Clouds ◽  
Belief Networks ◽  
Deep Belief Networks ◽  
3D Object ◽  
3D Object Classification

3D Object Classification Using 2D Perspectives of Point Clouds

2020 ◽  
pp. 453-462
Author(s):  
Leland Jansen ◽  
Nathan Liebrecht ◽  
Sara Soltaninejad ◽  
Anup Basu
Keyword(s):  
Object Classification ◽  
Point Clouds ◽  
3D Object ◽  
3D Object Classification

scholarly journals A Deep Learning Method for 3D Object Classification and Retrieval Using the Global Point Signature Plus and Deep Wide Residual Network

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2644
Author(s):  
Long Hoang ◽  
Suk-Hwan Lee ◽  
Ki-Ryong Kwon
Keyword(s):  
Deep Learning ◽  
3D Model ◽  
Mixed Reality ◽  
Object Classification ◽  
Residual Network ◽  
Retrieval Task ◽  
Shape Information ◽  
3D Object ◽  
Practical Applications ◽  
3D Object Classification

A vital and challenging task in computer vision is 3D Object Classification and Retrieval, with many practical applications such as an intelligent robot, autonomous driving, multimedia contents processing and retrieval, and augmented/mixed reality. Various deep learning methods were introduced for solving classification and retrieval problems of 3D objects. Almost all view-based methods use many views to handle spatial loss, although they perform the best among current techniques such as View-based, Voxelization, and Point Cloud methods. Many views make network structure more complicated due to the parallel Convolutional Neural Network (CNN). We propose a novel method that combines a Global Point Signature Plus with a Deep Wide Residual Network, namely GPSP-DWRN, in this paper. Global Point Signature Plus (GPSPlus) is a novel descriptor because it can capture more shape information of the 3D object for a single view. First, an original 3D model was converted into a colored one by applying GPSPlus. Then, a 32 × 32 × 3 matrix stored the obtained 2D projection of this color 3D model. This matrix was the input data of a Deep Residual Network, which used a single CNN structure. We evaluated the GPSP-DWRN for a retrieval task using the Shapnetcore55 dataset, while using two well-known datasets—ModelNet10 and ModelNet40 for a classification task. Based on our experimental results, our framework performed better than the state-of-the-art methods.

scholarly journals CNN-based 3D object classification using Hough space of LiDAR point clouds

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Wei Song ◽  
Lingfeng Zhang ◽  
Yifei Tian ◽  
Simon Fong ◽  
Jinming Liu ◽  
...  
Keyword(s):  
Object Classification ◽  
Point Clouds ◽  
3D Object ◽  
Hough Space ◽  
3D Object Classification

scholarly journals Joint Multi-view 2D Convolutional Neural Networks for 3D Object Classification

2020 ◽  
Author(s):  
Jinglin Xu ◽  
Xiangsen Zhang ◽  
Wenbin Li ◽  
Xinwang Liu ◽  
Junwei Han
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Computational Cost ◽  
Three Dimensional ◽  
Object Classification ◽  
Autonomous Driving ◽  
Outer Product ◽  
3D Object ◽  
Localization And Mapping ◽  
3D Object Classification

Three-dimensional (3D) object classification is widely involved in various computer vision applications, e.g., autonomous driving, simultaneous localization and mapping, which has attracted lots of attention in the committee. However, solving 3D object classification by directly employing the 3D convolutional neural networks (CNNs) generally suffers from high computational cost. Besides, existing view-based methods cannot better explore the content relationships between views. To this end, this work proposes a novel multi-view framework by jointly using multiple 2D-CNNs to capture discriminative information with relationships as well as a new multi-view loss fusion strategy, in an end-to-end manner. Specifically, we utilize multiple 2D views of a 3D object as input and integrate the intra-view and inter-view information of each view through the view-specific 2D-CNN and a series of modules (outer product, view pair pooling, 1D convolution, and fully connected transformation). Furthermore, we design a novel view ensemble mechanism that selects several discriminative and informative views to jointly infer the category of a 3D object. Extensive experiments demonstrate that the proposed method is able to outperform current state-of-the-art methods on 3D object classification. More importantly, this work provides a new way to improve 3D object classification from the perspective of fully utilizing well-established 2D-CNNs.

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

Sign in / Sign up

Export Citation Format

Share Document