Research

22 pages, 8429 KiB

Open AccessArticle

Infrared Ship Target Detection Based on Dual Channel Segmentation Combined with Multiple Features

by Dongming Lu, Jiangyun Tan, Mengke Wang, Longyin Teng, Liping Wang and Guohua Gu

Appl. Sci. 2023, 13(22), 12247; https://doi.org/10.3390/app132212247 - 12 Nov 2023

Viewed by 641

In infrared images of the sea surface, apart from the complex background of the sea surface, there are often sky and island backgrounds. The disturbances caused by sea wind and the reflection of intense sunlight on the sea surface increase the complexity of [...] Read more.

In infrared images of the sea surface, apart from the complex background of the sea surface, there are often sky and island backgrounds. The disturbances caused by sea wind and the reflection of intense sunlight on the sea surface increase the complexity of the background, which seriously hinders the detection of targets. To achieve the detection of dark-polarity ship targets in such environments, a dual-channel threshold segmentation method based on local low-gray region detection and geometric features judgment is proposed in this paper. In one channel, adaptive threshold segmentation is performed on the low-gray regions of the acquired image and combined with geometric features to obtain a finer segmentation result. In the other channel, adaptive segmentation is performed on the preprocessed image, and potential backgrounds that may be finely segmented as targets are filtered out based on an area threshold. Finally, the results of the two channels are multiplied and fused to obtain an accurate segmentation result. Experimental results demonstrate that the proposed algorithm outperforms the comparison algorithm in subjective and objective evaluations. The proposed algorithm in this paper not only achieves a low false alarm rate but also exhibits a higher detection rate, and the average detection rate in the test sequence surpasses 95%. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

13 pages, 4716 KiB

Open AccessArticle

Low-Light Image Enhancement Algorithm Based on Deep Learning and Retinex Theory

by Chenyu Lei and Qichuan Tian

Appl. Sci. 2023, 13(18), 10336; https://doi.org/10.3390/app131810336 - 15 Sep 2023

Viewed by 2088

Abstract

To address the challenges of low-light images, such as low brightness, poor contrast, and high noise, a network model based on deep learning and Retinex theory is proposed. The model consists of three modules: image decomposition, illumination enhancement, and color restoration. In the [...] Read more.

To address the challenges of low-light images, such as low brightness, poor contrast, and high noise, a network model based on deep learning and Retinex theory is proposed. The model consists of three modules: image decomposition, illumination enhancement, and color restoration. In the image decomposition module, dilated convolutions and residual connections are employed to mitigate the issue of detail loss during the decomposition process. The illumination enhancement module utilizes a set of mapping curves to enhance the illumination map. The color restoration module employs a weighted fusion of a 3D lookup table (3DLUT) to mitigate color distortion in the images. The experimental results demonstrate that the proposed algorithm effectively improves the brightness and contrast of low-light images while addressing the issues of detail loss and color distortion. Compared to other algorithms, it achieves better subjective and objective evaluations. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

14 pages, 1775 KiB

Open AccessArticle

Action Recognition via Adaptive Semi-Supervised Feature Analysis

by Zengmin Xu, Xiangli Li, Jiaofen Li, Huafeng Chen and Ruimin Hu

Appl. Sci. 2023, 13(13), 7684; https://doi.org/10.3390/app13137684 - 29 Jun 2023

Viewed by 649

Abstract

This study presents a new semi-supervised action recognition method via adaptive feature analysis. We assume that action videos can be regarded as data points in embedding manifold subspace, and their matching problem can be quantified through a specific Grassmannian kernel function while integrating [...] Read more.

This study presents a new semi-supervised action recognition method via adaptive feature analysis. We assume that action videos can be regarded as data points in embedding manifold subspace, and their matching problem can be quantified through a specific Grassmannian kernel function while integrating feature correlation exploration and data similarity measurement into a joint framework. By maximizing the intra-class compactness based on labeled data, our algorithm can learn multiple features and leverage unlabeled data to enhance recognition. We introduce the Grassmannian kernels and the Projected Barzilai–Borwein (PBB) method to train a subspace projection matrix as a classifier. Experiment results show our method has outperformed the compared approaches when a few labeled training samples are available. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

21 pages, 7625 KiB

Open AccessArticle

Super-Resolution Reconstruction of Depth Image Based on Kriging Interpolation

by Tingsheng Huang, Xinjian Wang, Chunyang Wang, Xuelian Liu and Yanqing Yu

Appl. Sci. 2023, 13(6), 3769; https://doi.org/10.3390/app13063769 - 15 Mar 2023

Cited by 1 | Viewed by 1601

Abstract

The super-resolution of depth images is a research hotspot. In this study, the classical Kriging algorithm is applied to the spatial interpolation of depth images, together with the fractional-order differential method for edge recognition, to realise the super-resolution reconstruction of depth images. The [...] Read more.

The super-resolution of depth images is a research hotspot. In this study, the classical Kriging algorithm is applied to the spatial interpolation of depth images, together with the fractional-order differential method for edge recognition, to realise the super-resolution reconstruction of depth images. The resulting interpolation model improves the edge performance of Kriging interpolation by harnessing the superior characteristics of fractional-order differential edge recognition and effectively solving the edge blurring problem in super-resolution interpolation of depth images. Experimental results show that, compared with the classical algorithms, the super-resolution reconstruction based on Kriging interpolation is greatly improved in terms of visual effects and the peak signal-to-noise ratio of the depth image. In particular, edge recognition based on fractional-order differentiation solves the image blurring problem at the edges of the depth images. Inspection of the point clouds of the depth images shows that the output of the proposed interpolation model has obvious fractal characteristics. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

16 pages, 10990 KiB

Open AccessCommunication

Efficient Re-Parameterization Residual Attention Network for Nonhomogeneous Image Dehazing

by Erkang Chen, Tian Ye, Jingxia Jiang, Lihan Tong and Qiubo Ye

Appl. Sci. 2023, 13(6), 3739; https://doi.org/10.3390/app13063739 - 15 Mar 2023

Cited by 1 | Viewed by 1132

Abstract

Real-world nonhomogeneous haze brings challenges to image restoration. More efforts are needed to remove dense haze and thin haze simultaneously and efficiently. However, most existing dehazing methods do not pay attention to the complex distributions of haze and usually suffer from a low [...] Read more.

Real-world nonhomogeneous haze brings challenges to image restoration. More efforts are needed to remove dense haze and thin haze simultaneously and efficiently. However, most existing dehazing methods do not pay attention to the complex distributions of haze and usually suffer from a low runtime speed. To tackle such problems, we present an efficient re-parameterization residual attention network (RRA-Net), whose design has three key aspects. Firstly, we propose a training-time multi-branch residual attention block (MRAB), where multi-scale convolutions in different branches cope with the nonuniformity of haze and are converted into a single-path convolution during inference. It also features local residual learning with improved spatial attention and channel attention, allowing dense and thin haze to be attended to differently. Secondly, our lightweight network structure cascades six MRABs followed by a long skip connection with attention and a fusion tail. Overall, our RRA-Net only has about 0.3M parameters. Thirdly, two new loss functions, namely the Laplace pyramid loss and the color attenuation loss, help train the network to recover details and colors. The experimental results show that the proposed RRA-Net performs favorably against state-of-the-art dehazing methods on real-world image datasets, including both nonhomogeneous haze and dense homogeneous haze. A runtime comparison under the same hardware setup also demonstrates the superior efficiency of the proposed network. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

23 pages, 7972 KiB

Open AccessArticle

Deep Visual Waterline Detection for Inland Marine Unmanned Surface Vehicles

by Shijun Chen, Jing Huang, Hengfeng Miao, Yaoqing Cai, Yuanqiao Wen and Changshi Xiao

Appl. Sci. 2023, 13(5), 3164; https://doi.org/10.3390/app13053164 - 01 Mar 2023

Cited by 1 | Viewed by 1184

Abstract

Waterline usually plays as an important visual cue for the autonomous navigation of marine unmanned surface vehicles (USVs) in specific waters. However, the visual complexity of the inland waterline presents a significant challenge for the development of highly efficient computer vision algorithms tailored [...] Read more.

Waterline usually plays as an important visual cue for the autonomous navigation of marine unmanned surface vehicles (USVs) in specific waters. However, the visual complexity of the inland waterline presents a significant challenge for the development of highly efficient computer vision algorithms tailored for waterline detection in a complicated inland water environment that marine USVs face. This paper attempts to find a solution to guarantee the effectiveness of waterline detection for the USVs with a general digital camera patrolling variable inland waters. To this end, a general deep-learning-based paradigm for inland marine USVs, named DeepWL, is proposed, which consists of two cooperative deep models (termed WLdetectNet and WLgenerateNet, respectively). They afford a continuous waterline image-map estimation from a single video stream captured on board. Experimental results demonstrate the effectiveness and superiority of the proposed approach via qualitative and quantitative assessment on the concerned performances. Moreover, due to its own generality, the proposed approach has the potential to be applied to the waterline detection tasks of other water areas such as coastal waters. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

13 pages, 797 KiB

Open AccessArticle

A Lightweight YOLOv5 Optimization of Coordinate Attention

by Jun Wu, Jiaming Dong, Wanyu Nie and Zhiwei Ye

Appl. Sci. 2023, 13(3), 1746; https://doi.org/10.3390/app13031746 - 30 Jan 2023

Cited by 6 | Viewed by 3332

Abstract

As Machine Learning technologies evolve, there is a desire to add vision capabilities to all devices within the IoT in order to enable a wider range of artificial intelligence. However, for most mobile devices, their computing power and storage space are affected by [...] Read more.

As Machine Learning technologies evolve, there is a desire to add vision capabilities to all devices within the IoT in order to enable a wider range of artificial intelligence. However, for most mobile devices, their computing power and storage space are affected by factors such as cost and the tight supply of relevant chips, making it impossible to effectively deploy complex network models to small processors with limited resources and to perform efficient real-time detection. In this paper, YOLOv5 is studied to achieve the goal of lightweight devices by reducing the number of original network channels. Then detection accuracy is guaranteed by adding a detection head and CA attention mechanism. The YOLOv5-RC model proposed in this paper is 30% smaller and lighter than YOLOv5s, but still maintains good detection accuracy. YOLOv5-RC network models can achieve a good balance between detection accuracy and detection speed, with potential for its widespread use in industry. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

16 pages, 5299 KiB

Open AccessArticle

Normalized Weighting Schemes for Image Interpolation Algorithms

by Olivier Rukundo

Appl. Sci. 2023, 13(3), 1741; https://doi.org/10.3390/app13031741 - 29 Jan 2023

Cited by 3 | Viewed by 1673

Abstract

Image interpolation algorithms pervade many modern image processing and analysis applications. However, when their weighting schemes inefficiently generate very unrealistic estimates, they may negatively affect the performance of the end-user applications. Therefore, in this work, the author introduced four weighting schemes based on [...] Read more.

Image interpolation algorithms pervade many modern image processing and analysis applications. However, when their weighting schemes inefficiently generate very unrealistic estimates, they may negatively affect the performance of the end-user applications. Therefore, in this work, the author introduced four weighting schemes based on some geometric shapes for digital image interpolation operations. Moreover, the quantity used to express the extent of each shape’s weight was the normalized area, especially when the sums of areas exceeded a unit square size. The introduced four weighting schemes are based on the minimum side-based diameter (MD) of a regular tetragon, hypotenuse-based radius (HR), the virtual pixel length-based height for the area of the triangle (AT), and the virtual pixel length for hypotenuse-based radius for the area of the circle (AC). At the smaller scaling ratio, the image interpolation algorithm based on the HR scheme scored the highest at 66.6% among non-traditional image interpolation algorithms presented. However, at the higher scaling ratio, the AC scheme-based image interpolation algorithm scored the highest at 66.6% among non-traditional algorithms presented, and, here, its image interpolation quality was generally superior or comparable to the quality of images interpolated by both non-traditional and traditional algorithms. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

22 pages, 10086 KiB

Open AccessArticle

Automatic Measurement of Inclination Angle of Utility Poles Using 2D Image and 3D Point Cloud

by Lei Chen, Jiazhen Chang, Jinli Xu and Zuowei Yang

Appl. Sci. 2023, 13(3), 1688; https://doi.org/10.3390/app13031688 - 28 Jan 2023

Cited by 2 | Viewed by 1820

Abstract

The utility pole inclination angle is an important parameter for determining pole health conditions. Without depth information, the angle cannot be estimated from a 2D image, and without large labeled reference pole data, it is time consuming to locate the pole in the [...] Read more.

The utility pole inclination angle is an important parameter for determining pole health conditions. Without depth information, the angle cannot be estimated from a 2D image, and without large labeled reference pole data, it is time consuming to locate the pole in the 3D point cloud. Therefore, this paper proposes a method that processes the pole data from the 2D image and 3D point cloud to automatically measure the pole inclination angle. Firstly, the mask of the pole skeleton is obtained from an improved Mask R-CNN. Secondly, the pole point cloud is extracted from a PointNet that deals with the generated frustum from the pole skeleton mask and depth map fusion. Finally, the angle is calculated by fitting the central axis of the pole cloud data. ApolloSpace open dataset and laboratory data are used for evaluation. The experimental results show that the AP₇₅ of improved Mask R-CNN is 58.15%, the accuracy of PointNet is 92.4%, the average error of pole inclination is 0.66°, and the variance is 0.12°. It is proved that the method can effectively realize the automatic measurement of pole inclination. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

14 pages, 8261 KiB

Open AccessArticle

Panchromatic and Multispectral Image Fusion Combining GIHS, NSST, and PCA

by Lina Xu, Guangqi Xie and Sitong Zhou

Appl. Sci. 2023, 13(3), 1412; https://doi.org/10.3390/app13031412 - 20 Jan 2023

Cited by 3 | Viewed by 1097

Abstract

Spatial and spectral information are essential sources of information in remote sensing applications, and the fusion of panchromatic and multispectral images effectively combines the advantages of both. Due to the existence of two main classes of fusion methods—component substitution (CS) and multi-resolution analysis [...] Read more.

Spatial and spectral information are essential sources of information in remote sensing applications, and the fusion of panchromatic and multispectral images effectively combines the advantages of both. Due to the existence of two main classes of fusion methods—component substitution (CS) and multi-resolution analysis (MRA), which have different advantages—mixed approaches are possible. This paper proposes a fusion algorithm that combines the advantages of generalized intensity–hue–saturation (GIHS) and non-subsampled shearlet transform (NSST) with principal component analysis (PCA) technology to extract more spatial information. Therefore, compared with the traditional algorithms, the algorithm in this paper uses PCA transformation to obtain spatial structure components from PAN and MS, which can effectively inject spatial information while maintaining spectral information with high fidelity. First, PCA is applied to each band of low-resolution multispectral (MS) images and panchromatic (PAN) images to obtain the first principal component and to calculate the intensity of MS. Then, the PAN image is fused with the first principal component using NSST, and the fused image is used to replace the original intensity component. Finally, a fused image is obtained using the GIHS algorithm. Using the urban, plants and water, farmland, and desert images from GeoEye-1, WorldView-4, GaoFen-7 (GF-7), and Gaofen Multi-Mode (GFDM) as experimental data, this fusion method was tested using the evaluation mode with references and the evaluation mode without references and was compared with five other classic fusion algorithms. The results showed that the algorithms in this paper had better fusion performances in both spectral preservation and spatial information incorporation. Full article

(This article belongs to the Special Issue Recent Advances in Image Processing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Recent Advances in Image Processing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI