Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Image/Signal Processing and Machine Vision in Sensing Applications

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (10 May 2023) | Viewed by 23136

Share This Special Issue

Special Issue Editors

Dr. Xinyue Zhao

E-Mail Website
Guest Editor

School of Mechanical Engineering, Zhejiang University, Hangzhou, China
Interests: machine vision; pattern recognition; image processing
Special Issues, Collections and Topics in MDPI journals

Dr. Dong Liang

E-Mail Website
Guest Editor

College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Interests: pattern recognition systems

Dr. Guoliang Lu

E-Mail Website
Guest Editor

School of Mechanical Engineering, Shandong University, Jinan 250061, China
Interests: machine vision for inspection and measurement in industrial applications

Prof. Dr. Long Chen

E-Mail Website
Guest Editor

School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200001, China
Interests: integrated design; machine vision; robotics and intelligent manufacturing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine vision encompasses all industrial and non-industrial applications in which a combination of hardware and software provides operational guidance to devices in the execution of their functions based on the capture and processing of images. Machine vision and image processing technologies are widely employed in sensor science and technology.

This Special Issue intends to provide a timely opportunity for scientists, researchers, as well as engineers to discuss and summarize the latest signal/image processing and machine vision methods in sensing applications. We invite papers that include but are not exclusive to the following topics: artificial intelligence; pattern recognition/analysis technologies in human analysis; behavior understanding and image processing in chemical, biological and physical sensors; measurement compensation and calibration; sensor applications in robotics and intelligent systems; non-destructive testing and evaluation; precision measurements and metrology; and remote sensing methods. Both theoretical and experimental studies are welcome, are comprehensive review and survey papers.

Dr. Xinyue Zhao
Dr. Dong Liang
Dr. Guoliang Lu
Prof. Dr. Long Chen
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

image and signal processing
machine vision
sensor science and technology
image processing in chemical, biological and physical sensors
remote sensing
sensor-based industrial inspection

Published Papers (10 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

24 pages, 23589 KiB

Open AccessArticle

YOLO-Weld: A Modified YOLOv5-Based Weld Feature Detection Network for Extreme Weld Noise

by Ang Gao, Zhuoxuan Fan, Anning Li, Qiaoyue Le, Dongting Wu and Fuxin Du

Sensors 2023, 23(12), 5640; https://doi.org/10.3390/s23125640 - 16 Jun 2023

Viewed by 1758

Abstract

Weld feature point detection is a key technology for welding trajectory planning and tracking. Existing two-stage detection methods and conventional convolutional neural network (CNN)-based approaches encounter performance bottlenecks under extreme welding noise conditions. To better obtain accurate weld feature point locations in high-noise environments, we propose a feature point detection network, YOLO-Weld, based on an improved You Only Look Once version 5 (YOLOv5). By introducing the reparameterized convolutional neural network (RepVGG) module, the network structure is optimized, enhancing detection speed. The utilization of a normalization-based attention module (NAM) in the network enhances the network’s perception of feature points. A lightweight decoupled head, RD-Head, is designed to improve classification and regression accuracy. Furthermore, a welding noise generation method is proposed, increasing the model’s robustness in extreme noise environments. Finally, the model is tested on a custom dataset of five weld types, demonstrating better performance than two-stage detection methods and conventional CNN approaches. The proposed model can accurately detect feature points in high-noise environments while meeting real-time welding requirements. In terms of the model’s performance, the average error of detecting feature points in images is 2.100 pixels, while the average error in the world coordinate system is 0.114 mm, sufficiently meeting the accuracy needs of various practical welding tasks. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

19 pages, 6979 KiB

Open AccessArticle

Dynamic Yarn-Tension Detection Using Machine Vision Combined with a Tension Observer

by Yue Ji, Jiedong Ma, Zhanqing Zhou, Jinyi Li and Limei Song

Sensors 2023, 23(8), 3800; https://doi.org/10.3390/s23083800 - 07 Apr 2023

Cited by 1 | Viewed by 1641

Abstract

Machine vision can prevent additional stress on yarn caused by contact measurement, as well as the risk of hairiness and breakage. However, the speed of the machine vision system is limited by image processing, and the tension detection method based on the axially moving model does not take into account the disturbance on yarn caused by motor vibrations. Thus, an embedded system combining machine vision with a tension observer is proposed. The differential equation for the transverse dynamics of the string is established using Hamilton’s principle and then solved. A field-programmable gate array (FPGA) is used for image data acquisition, and the image processing algorithm is implemented using a multi-core digital signal processor (DSP). To obtain the yarn vibration frequency in the axially moving model, the brightest centreline grey value of the yarn image is put forward as a reference to determine the feature line. The calculated yarn tension value is then combined with the value obtained using the tension observer based on an adaptive weighted data fusion method in a programmable logic controller (PLC). The results show that the accuracy of the combined tension is improved compared with the original two non-contact methods of tension detection at a faster update rate. The system alleviates the problem of inadequate sampling rate using only machine vision methods and can be applied to future real-time control systems. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

16 pages, 8732 KiB

Open AccessArticle

Just Noticeable Difference Model for Images with Color Sensitivity

by Zhao Zhang, Xiwu Shang, Guoping Li and Guozhong Wang

Sensors 2023, 23(5), 2634; https://doi.org/10.3390/s23052634 - 27 Feb 2023

Cited by 1 | Viewed by 2325

Abstract

The just noticeable difference (JND) model reflects the visibility limitations of the human visual system (HVS), which plays an important role in perceptual image/video processing and is commonly applied to perceptual redundancy removal. However, existing JND models are usually constructed by treating the color components of three channels equally, and their estimation of the masking effect is inadequate. In this paper, we introduce visual saliency and color sensitivity modulation to improve the JND model. Firstly, we comprehensively combined contrast masking, pattern masking, and edge protection to estimate the masking effect. Then, the visual saliency of HVS was taken into account to adaptively modulate the masking effect. Finally, we built color sensitivity modulation according to the perceptual sensitivities of HVS, to adjust the sub-JND thresholds of Y, Cb, and Cr components. Thus, the color-sensitivity-based JND model (CSJND) was constructed. Extensive experiments and subjective tests were conducted to verify the effectiveness of the CSJND model. We found that consistency between the CSJND model and HVS was better than existing state-of-the-art JND models. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

18 pages, 782 KiB

Open AccessArticle

Analysis of Microalgal Density Estimation by Using LASSO and Image Texture Features

by Linh Nguyen, Dung K. Nguyen, Thang Nguyen, Binh Nguyen and Truong X. Nghiem

Sensors 2023, 23(5), 2543; https://doi.org/10.3390/s23052543 - 24 Feb 2023

Cited by 3 | Viewed by 1881

Abstract

Monitoring and estimating the density of microalgae in a closed cultivation system is a critical task in culturing algae since it allows growers to optimally control both nutrients and cultivating conditions. Among the estimation techniques proposed so far, image-based methods, which are less invasive, nondestructive, and more biosecure, are practically preferred. Nevertheless, the premise behind most of those approaches is simply averaging the pixel values of images as inputs of a regression model to predict density values, which may not provide rich information of the microalgae presenting in the images. In this work, we propose to exploit more advanced texture features extracted from captured images, including confidence intervals of means of pixel values, powers of spatial frequencies presenting in images, and entropies accounting for pixel distribution. These diverse features can provide more information of microalgae, which can lead to more accurate estimation results. More importantly, we propose to use the texture features as inputs of a data-driven model based on L1 regularization, called least absolute shrinkage and selection operator (LASSO), where their coefficients are optimized in a manner that prioritizes more informative features. The LASSO model was then employed to efficiently estimate the density of microalgae presenting in a new image. The proposed approach was validated in real-world experiments monitoring the Chlorella vulgaris microalgae strain, where the obtained results demonstrate its outperformance compared with other methods. More specifically, the average error in the estimation obtained by the proposed approach is 1.54, whereas those obtained by the Gaussian process and gray-scale-based methods are 2.16 and 3.68, respectively Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

19 pages, 5073 KiB

Open AccessArticle

An Integrated Fusion Engine for Early Threat Detection Demonstrated in Public-Space Trials

by Henri Bouma, Maria Luisa Villani, Arthur van Rooijen, Pauli Räsänen, Johannes Peltola, Sirra Toivonen, Antonio De Nicola, Massimiliano Guarneri, Cristiano Stifini and Luigi De Dominicis

Sensors 2023, 23(1), 440; https://doi.org/10.3390/s23010440 - 31 Dec 2022

Cited by 4 | Viewed by 2151

Abstract

Counter terrorism is a huge challenge for public spaces. Therefore, it is essential to support early detection of threats, such as weapons or explosives. An integrated fusion engine was developed for the management of a plurality of sensors to detect threats without disrupting the flow of commuters. The system improves security of soft targets (such as airports, undergrounds and railway stations) by providing security operators with real-time information of the threat combined with image and position data of each person passing the monitored area. This paper describes the results of the fusion engine in a public-space trial in a metro station in Rome. The system consists of 2D-video tracking, person re-identification, 3D-video tracking, and command and control (C&C) formulating two co-existing data pipelines: one for visualization on smart glasses and another for hand-over to another sensor. Over multiple days, 586 commuters participated in the trial. The results of the trial show overall accuracy scores of 97.4% and 97.6% for the visualization and hand-over pipelines, respectively, and each component reached high accuracy values (2D Video = 98.0%, Re-identification = 100.0%, 3D Video = 99.7% and C&C = 99.5%). Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

16 pages, 9082 KiB

Open AccessArticle

Object Pose Estimation Using Edge Images Synthesized from Shape Information

by Atsunori Moteki and Hideo Saito

Sensors 2022, 22(24), 9610; https://doi.org/10.3390/s22249610 - 08 Dec 2022

Viewed by 1966

Abstract

This paper presents a method for estimating the six Degrees of Freedom (6DoF) pose of texture-less objects from a monocular image by using edge information. The deep learning-based pose estimation method needs a large dataset containing pairs of an image and ground truth pose of objects. To alleviate the cost of collecting a dataset, we focus on the method using a dataset made by computer graphics (CG). This simulation-based method prepares a thousand images by rendering the computer-aided design (CAD) data of the object and trains a deep-learning model. As an inference stage, a monocular RGB image is entered into the model, and the object’s pose is estimated. The representative simulation-based method, Pose Interpreter Networks, uses silhouette images as the input, thereby enabling common feature (contour) extraction from RGB and CG images. However, estimating rotation parameters is less accurate. To overcome this problem, we propose a method to use edge information extracted from the object’s ridgelines for training the deep learning model. Since edge distribution changes largely according to the pose, the estimation of rotation parameters becomes more robust. Through an experiment with simulation data, we quantitatively proved the accuracy improvement compared to the previous method (error rate decreases at a certain condition are translation 22.9% and rotation: 43.4%). Moreover, through an experiment with physical data, we clarified the issues of this method and proposed an effective solution by fine-tuning (error rate decrease at a certain condition are translation 20.1% and rotation 57.7%). Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

31 pages, 12390 KiB

Open AccessArticle

Three-Stage Pavement Crack Localization and Segmentation Algorithm Based on Digital Image Processing and Deep Learning Techniques

by Zhen Yang, Changshuang Ni, Lin Li, Wenting Luo and Yong Qin

Sensors 2022, 22(21), 8459; https://doi.org/10.3390/s22218459 - 03 Nov 2022

Cited by 15 | Viewed by 2598

Abstract

The image of expressway asphalt pavement crack disease obtained by a three-dimensional line scan laser is easily affected by external factors such as uneven illumination distribution, environmental noise, occlusion shadow, and foreign bodies on the pavement. To locate and extract cracks accurately and efficiently, this article proposes a three-stage asphalt pavement crack location and segmentation method based on traditional digital image processing technology and deep learning methods. In the first stage of this method, the guided filtering and Retinex methods are used to preprocess the asphalt pavement crack image. The processed image removes redundant noise information and improves the brightness. At the information entropy level, it is 63% higher than the unpreprocessed image. In the second stage, the newly proposed YOLO-SAMT target detection model is used to locate the crack diseases in asphalt pavement. The model is 5.42 percentage points higher than the original YOLOv7 model on mAP@0.5, which enhances the recognition and location ability of crack diseases and reduces the calculation amount for the extraction of crack contour in the next stage. In the third stage, the improved k-means clustering algorithm is used to extract cracks. Compared with the traditional k-means clustering algorithm, this method improves the accuracy by 7.34 percentage points, the true rate by 6.57 percentage points, and the false positive rate by 18.32 percentage points to better extract the crack contour. To sum up, the method proposed in this article improves the quality of the pavement disease image, enhances the ability to identify and locate cracks, reduces the amount of calculation, improves the accuracy of crack contour extraction, and provides a new solution for highway crack inspection. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

16 pages, 9970 KiB

Open AccessArticle

Robust Template Matching Using Multiple-Layered Absent Color Indexing

by Guodong Wei, Ying Tian, Shun’ichi Kaneko and Zhengang Jiang

Sensors 2022, 22(17), 6661; https://doi.org/10.3390/s22176661 - 03 Sep 2022

Cited by 1 | Viewed by 1647

Abstract

Color is an essential feature in histogram-based matching. This can be extracted as statistical data during the comparison process. Although the applicability of color features in histogram-based techniques has been proven, position information is lacking during the matching process. We present a conceptually simple and effective method called multiple-layered absent color indexing (ABC-ML) for template matching. Apparent and absent color histograms are obtained from the original color histogram, where the absent colors belong to low-frequency or vacant bins. To determine the color range of compared images, we propose a total color space (TCS) that can determine the operating range of the histogram bins. Furthermore, we invert the absent colors to obtain the properties of these colors using threshold

h_{T}

. Then, we compute the similarity using the intersection. A multiple-layered structure is proposed against the shift issue in histogram-based approaches. Each layer is constructed using the isotonic principle. Thus, absent color indexing and multiple-layered structure are combined to solve the precision problem. Our experiments on real-world images and open data demonstrated that they have produced state-of-the-art results. Moreover, they retained the histogram merits of robustness in cases of deformation and scaling. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

18 pages, 12141 KiB

Open AccessArticle

Model-Based 3D Contact Geometry Perception for Visual Tactile Sensor

by Jingjing Ji, Yuting Liu and Huan Ma

Sensors 2022, 22(17), 6470; https://doi.org/10.3390/s22176470 - 28 Aug 2022

Cited by 2 | Viewed by 2496

Abstract

Tactile sensing plays an important role for robots’ perception, but the existing tactile technologies have multiple limitations. Visual-tactile sensor (VTS) is a newly developed tactile detector; it perceives the contacting surface shape, or even more refined texture, by way of the contact deformation image captured by a camera. A conventional visual perception is usually formulated as a data processing. It suffers issues of cumbersome training set and complicated calibration procedures. A novel model-based depth perceptual scheme is proposed where a mapping from the image intensity to the contact geometry is mathematically formulated with an associated tailored fast solver. The hardware calibration requires single image only, leading to an outstanding algorithmic robustness. The non-uniformity of the illumination condition is embodied by the stereo model, resulting in a robust depth perception precision. Compression tests on a prototype VTS showed the method’s capability in high-quality geometry reconstruction. Both contacting shape and texture were captured at a root-mean-square error down to a sub-millimeter level. The feasibility of the proposed in a pose estimation application is further experimentally validated. The associated tests yielded estimation errors that were all less than 3° in terms of spatial orientation and all less than 1mm in terms of translation. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Figure 1

17 pages, 1315 KiB

Open AccessArticle

Two-Stream Mixed Convolutional Neural Network for American Sign Language Recognition

by Ying Ma, Tianpei Xu and Kangchul Kim

Sensors 2022, 22(16), 5959; https://doi.org/10.3390/s22165959 - 09 Aug 2022

Cited by 12 | Viewed by 3338

Abstract

The Convolutional Neural Network (CNN) has demonstrated excellent performance in image recognition and has brought new opportunities for sign language recognition. However, the features undergo many nonlinear transformations while performing the convolutional operation and the traditional CNN models are insufficient in dealing with the correlation between images. In American Sign Language (ASL) recognition, J and Z with moving gestures bring recognition challenges. This paper proposes a novel Two-Stream Mixed (TSM) method with feature extraction and fusion operation to improve the correlation of feature expression between two time-consecutive images for the dynamic gestures. The proposed TSM-CNN system is composed of preprocessing, the TSM block, and CNN classifiers. Two consecutive images in the dynamic gesture are used as inputs of streams, and resizing, transformation, and augmentation are carried out in the preprocessing stage. The fusion feature map obtained by addition and concatenation in the TSM block is used as inputs of the classifiers. Finally, a classifier classifies images. The TSM-CNN model with the highest performance scores depending on three concatenation methods is selected as the definitive recognition model for ASL recognition. We design 4 CNN models with TSM: TSM-LeNet, TSM-AlexNet, TSM-ResNet18, and TSM-ResNet50. The experimental results show that the CNN models with the TSM are better than models without TSM. The TSM-ResNet50 has the best accuracy of 97.57% for MNIST and ASL datasets and is able to be applied to a RGB image sensing system for hearing-impaired people. Full article

(This article belongs to the Special Issue Image/Signal Processing and Machine Vision in Sensing Applications)

► Show Figures

Journal Menu

Journal Browser

Image/Signal Processing and Machine Vision in Sensing Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI