Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
3D Images, Point Clouds and Videos Classification and Management by...
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (31 December 2020) | Viewed by 21753

Special Issue Editors

Prof. Dr. Basilio Sierra

E-Mail Website
Guest Editor
Universidad del Pais Vasco, Leioa, Spain
Interests: supervised classification; one-class classification; machine learning; pattern precognition; nearest neighbor algorithm; genetic algorithms; estimation of distribution algorithms; Bayesian networks; applications in medicine; machine learning and data mining in general
Dr. Naiara Aginako

E-Mail Website
Guest Editor
Universidad del Pais Vasco, Leioa, Spain
Interests: computer vision; biometric applications; machine learning; 3D vision; deep learning
Dr. José María Martínez-Otzeta

E-Mail Website
Guest Editor
Ciencia de la Computación e Inteligencia Artificial, Centros de Gipuzkoa/FACULTAD DE INFORMATICA, Universidad del Pais Vasco, 48940 Leioa, Spain
Interests: machine learning; computer vision; 3D vision; deep learning; video action recognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, image capture systems have increasingly been used in industrial, commercial, and agricultural applications as a means to obtain information which could improve the quality of the obtained products. The methodologies and technologies related to video processing, imaging processing, 3D modeling, and multimedia have significantly been implemented in the field of computer vision. The continuous development of these technologies has led to an introduction of new methodologies and applications in this field. Machine learning algorithms and deep learning provide paradigms to process and classify obtained 3D images or point clouds, as well as video action recognition.

Recently, advancements in sensor technologies that acquire point cloud data have paved the way for the development of new ideas, methodologies, and solutions in countless remote sensing applications.

This Special Issue addresses the latest research advances in 3D image, point cloud, and video classification. This covers a wide area of applications, such as industrial pieces recognition, crop status management, video action recognition, etc. and several techniques: machine learning, deep learning, etc. The papers will help readers to explore and share their knowledge and experience in technologies and development techniques.

Prof. Dr. Basilio Sierra
Dr. Naiara Aginako
Dr. José María Martínez-Otzeta
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • machine learning
  • 3D model processing
  • robotic applications
  • deep learning for point cloud processing
  • point cloud classification
  • modeling urban and natural environments from aerial and mobile LiDAR/image-based point clouds
  • industrial applications with large-scale point clouds
  • machine and robot vision
  • 3D Image detection, recognition, and tracking
  • biometrics and biomedical image analysis
  • action recognition
  • mathematical methods in image processing, analysis, and representation
  • artificial intelligence tools in image analysis
  • pattern recognition algorithms applied for images

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 1514 KiB  
Article
3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts
by Ibon Merino, Jon Azpiazu, Anthony Remazeilles and Basilio Sierra
Sensors 2021, 21(4), 1078; https://doi.org/10.3390/s21041078 - 4 Feb 2021
Cited by 14 | Viewed by 3349
Abstract
Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than [...] Read more.
Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

29 pages, 1329 KiB  
Article
A Generalization Performance Study Using Deep Learning Networks in Embedded Systems
by Joseba Gorospe, Rubén Mulero, Olatz Arbelaitz, Javier Muguerza and Miguel Ángel Antón
Sensors 2021, 21(4), 1031; https://doi.org/10.3390/s21041031 - 3 Feb 2021
Cited by 17 | Viewed by 3620
Abstract
Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the [...] Read more.
Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

26 pages, 7917 KiB  
Article
Affordance-Based Grasping Point Detection Using Graph Convolutional Networks for Industrial Bin-Picking Applications
by Ander Iriondo, Elena Lazkano and Ander Ansuategi
Sensors 2021, 21(3), 816; https://doi.org/10.3390/s21030816 - 26 Jan 2021
Cited by 21 | Viewed by 4817
Abstract
Grasping point detection has traditionally been a core robotic and computer vision problem. In recent years, deep learning based methods have been widely used to predict grasping points, and have shown strong generalization capabilities under uncertainty. Particularly, approaches that aim at predicting object [...] Read more.
Grasping point detection has traditionally been a core robotic and computer vision problem. In recent years, deep learning based methods have been widely used to predict grasping points, and have shown strong generalization capabilities under uncertainty. Particularly, approaches that aim at predicting object affordances without relying on the object identity, have obtained promising results in random bin-picking applications. However, most of them rely on RGB/RGB-D images, and it is not clear up to what extent 3D spatial information is used. Graph Convolutional Networks (GCNs) have been successfully used for object classification and scene segmentation in point clouds, and also to predict grasping points in simple laboratory experimentation. In the present proposal, we adapted the Deep Graph Convolutional Network model with the intuition that learning from n-dimensional point clouds would lead to a performance boost to predict object affordances. To the best of our knowledge, this is the first time that GCNs are applied to predict affordances for suction and gripper end effectors in an industrial bin-picking environment. Additionally, we designed a bin-picking oriented data preprocessing pipeline which contributes to ease the learning process and to create a flexible solution for any bin-picking application. To train our models, we created a highly accurate RGB-D/3D dataset which is openly available on demand. Finally, we benchmarked our method against a 2D Fully Convolutional Network based method, improving the top-1 precision score by 1.8% and 1.7% for suction and gripper respectively. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

20 pages, 6406 KiB  
Article
AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis
by Yufeng Yang, Yixiao Ma, Jing Zhang, Xin Gao and Min Xu
Sensors 2020, 20(19), 5455; https://doi.org/10.3390/s20195455 - 23 Sep 2020
Cited by 8 | Viewed by 3598
Abstract
Point set is a major type of 3D structure representation format characterized by its data availability and compactness. Most former deep learning-based point set models pay equal attention to different point set regions and channels, thus having limited ability in focusing on small [...] Read more.
Point set is a major type of 3D structure representation format characterized by its data availability and compactness. Most former deep learning-based point set models pay equal attention to different point set regions and channels, thus having limited ability in focusing on small regions and specific channels that are important for characterizing the object of interest. In this paper, we introduce a novel model named Attention-based Point Network (AttPNet). It uses attention mechanism for both global feature masking and channel weighting to focus on characteristic regions and channels. There are two branches in our model. The first branch calculates an attention mask for every point. The second branch uses convolution layers to abstract global features from point sets, where channel attention block is adapted to focus on important channels. Evaluations on the ModelNet40 benchmark dataset show that our model outperforms the existing best model in classification tasks by 0.7% without voting. In addition, experiments on augmented data demonstrate that our model is robust to rotational perturbations and missing points. We also design a Electron Cryo-Tomography (ECT) point cloud dataset and further demonstrate our model’s ability in dealing with fine-grained structures on the ECT dataset. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

29 pages, 4395 KiB  
Article
Correntropy-Induced Discriminative Nonnegative Sparse Coding for Robust Palmprint Recognition
by Kunlei Jing, Xinman Zhang and Guokun Song
Sensors 2020, 20(15), 4250; https://doi.org/10.3390/s20154250 - 30 Jul 2020
Cited by 2 | Viewed by 1920
Abstract
Palmprint recognition has been widely studied for security applications. However, there is a lack of in-depth investigations on robust palmprint recognition. Regression analysis being intuitively interpretable on robustness design inspires us to propose a correntropy-induced discriminative nonnegative sparse coding method for robust palmprint [...] Read more.
Palmprint recognition has been widely studied for security applications. However, there is a lack of in-depth investigations on robust palmprint recognition. Regression analysis being intuitively interpretable on robustness design inspires us to propose a correntropy-induced discriminative nonnegative sparse coding method for robust palmprint recognition. Specifically, we combine the correntropy metric and l1-norm to present a powerful error estimator that gains flexibility and robustness to various contaminations by cooperatively detecting and correcting errors. Furthermore, we equip the error estimator with a tailored discriminative nonnegative sparse regularizer to extract significant nonnegative features. We manage to explore an analytical optimization approach regarding this unified scheme and figure out a novel efficient method to address the challenging non-negative constraint. Finally, the proposed coding method is extended for robust multispectral palmprint recognition. Namely, we develop a constrained particle swarm optimizer to search for the feasible parameters to fuse the extracted robust features of different spectrums. Extensive experimental results on both contactless and contact-based multispectral palmprint databases verify the flexibility and robustness of our methods. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

13 pages, 1241 KiB  
Article
GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition
by Wensong Chan, Zhiqiang Tian and Yang Wu
Sensors 2020, 20(12), 3499; https://doi.org/10.3390/s20123499 - 21 Jun 2020
Cited by 23 | Viewed by 3373
Abstract
Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs). Many existing GCNs-based models only use the fixed hand-crafted adjacency matrix to describe the connections between human body joints. This omits the important implicit connections between joints, which [...] Read more.
Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs). Many existing GCNs-based models only use the fixed hand-crafted adjacency matrix to describe the connections between human body joints. This omits the important implicit connections between joints, which contain discriminative information for different actions. In this paper, we propose an action-specific graph convolutional module, which is able to extract the implicit connections and properly balance them for each action. In addition, to filter out the useless and redundant information in the temporal dimension, we propose a simple yet effective operation named gated temporal convolution. These two major novelties ensure the superiority of our proposed method, as demonstrated on three large-scale public datasets: NTU-RGB + D, Kinetics, and NTU-RGB + D 120, and also shown in the detailed ablation studies. Full article
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop