Research

13 pages, 3150 KiB

Open AccessArticle

Multispectral Remote Sensing Image Change Detection Based on Twin Neural Networks

by Wenhao Mo, Yuanpeng Tan, Yu Zhou, Yanli Zhi, Yuchang Cai and Wanjie Ma

Electronics 2023, 12(18), 3766; https://doi.org/10.3390/electronics12183766 - 06 Sep 2023

Cited by 1 | Viewed by 662

Remote sensing image change detection can effectively show the change information of land surface features such as roads and buildings at different times, which plays an indispensable role in application fields such as updating building information and analyzing urban evolution. At present, multispectral [...] Read more.

Remote sensing image change detection can effectively show the change information of land surface features such as roads and buildings at different times, which plays an indispensable role in application fields such as updating building information and analyzing urban evolution. At present, multispectral remote sensing images contain more and more information, which brings new development opportunities to remote sensing image change detection. However, this information is difficult to use effectively in change detection. Therefore, a change-detection method of multispectral remote sensing images based on a Siamese neural network is proposed. The features of dual-temporal remote sensing images were extracted based on the ResNet-18 network. In order to capture the semantic information of different scales and improve the information perception and expression ability of the algorithm for the input image features, an attention module network structure is designed to further enhance the extracted feature maps. Facing the problem of false alarms in change detection, an adaptive threshold comparison loss function is designed to make the threshold more sensitive to the remote sensing images in the data set and improve the robustness of the algorithm model. Moreover, the threshold segmentation method of the measurement module is used to determine the change area to obtain a better change-detection map domain. Finally, our experimental tests show that the proposed method achieves excellent performance on the multispectral OSCD detection data sets. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

16 pages, 6723 KiB

Open AccessArticle

Study on Parking Space Recognition Based on Improved Image Equalization and YOLOv5

by Xin Zhang, Wen Zhao and Yueqiu Jiang

Electronics 2023, 12(15), 3374; https://doi.org/10.3390/electronics12153374 - 07 Aug 2023

Cited by 1 | Viewed by 1021

Abstract

Parking space recognition is an important part in the process of automatic parking, and it is also a key issue in the research field of automatic parking technology. The parking space recognition process was studied based on vision and the YOLOv5 target detection [...] Read more.

Parking space recognition is an important part in the process of automatic parking, and it is also a key issue in the research field of automatic parking technology. The parking space recognition process was studied based on vision and the YOLOv5 target detection algorithm. Firstly, the fisheye camera around the body was calibrated using the Zhang Zhengyou calibration method, and then the corrected images captured by the camera were top-view transformed; then, the projected transformed images were stitched and fused in a unified coordinate system, and an improved image equalization processing fusion algorithm was used in order to improve the uneven image brightness in the parking space recognition process; after that, the fused images were input to the YOLOv5 target detection model for training and validation, and the results were compared with those of two other algorithms. Finally, the contours of the parking space were extracted based on OpenCV. The simulations and experiments proved that the brightness and sharpness of the fused images meet the requirements after image equalization, and the effectiveness of the parking space recognition method was also verified. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

19 pages, 9416 KiB

Open AccessArticle

GMDNet: An Irregular Pavement Crack Segmentation Method Based on Multi-Scale Convolutional Attention Aggregation

by Yawei Qi, Fang Wan, Guangbo Lei, Wei Liu, Li Xu, Zhiwei Ye and Wen Zhou

Electronics 2023, 12(15), 3348; https://doi.org/10.3390/electronics12153348 - 04 Aug 2023

Cited by 1 | Viewed by 957

Abstract

Pavement cracks are the primary type of distress that cause road damage, and deep-learning-based pavement crack segmentation is a critical technology for current pavement maintenance and management. To address the issues of segmentation discontinuity and poor performance in the segmentation of irregular cracks [...] Read more.

Pavement cracks are the primary type of distress that cause road damage, and deep-learning-based pavement crack segmentation is a critical technology for current pavement maintenance and management. To address the issues of segmentation discontinuity and poor performance in the segmentation of irregular cracks faced by current semantic segmentation models, this paper proposes an irregular pavement crack segmentation method based on multi-scale convolutional attention aggregation. In this approach, GhostNet is first introduced as the model backbone network for reducing parameter count, with dynamic convolution enhancing GhostNet’s feature extraction capability. Next, a multi-scale convolutional attention aggregation module is proposed to cause the model to focus more on crack features and thus improve the segmentation effect on irregular cracks. Finally, a progressive up-sampling structure is used to enrich the feature information by gradually fusing feature maps of different depths to enhance the continuity of segmentation results. The experimental results on the HGCrack dataset show that GMDNet has a lighter model structure and higher segmentation accuracy than the mainstream semantic segmentation algorithms, achieving 75.16% of MIoU and 84.43% of F1 score, with only 7.67 M parameters. Therefore, the GMDNet proposed in this paper can accurately and efficiently segment irregular cracks on pavements that are more suitable for pavement crack segmentation scenarios in practical applications. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

13 pages, 4241 KiB

Open AccessArticle

Stereo SLAM in Dynamic Environments Using Semantic Segmentation

by Yongbao Ai, Qianchong Sun, Zhipeng Xi, Na Li, Jianmeng Dong and Xiang Wang

Electronics 2023, 12(14), 3112; https://doi.org/10.3390/electronics12143112 - 18 Jul 2023

Cited by 1 | Viewed by 1217

Abstract

As we all know, many dynamic objects appear almost continuously in the real world that are immensely capable of impairing the performance of the majority of vision-based SLAM systems based on the static-world assumption. In order to improve the robustness and accuracy of [...] Read more.

As we all know, many dynamic objects appear almost continuously in the real world that are immensely capable of impairing the performance of the majority of vision-based SLAM systems based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in high-dynamic environments, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken the influence of dynamic content, the moving-object detection method was put forward in our visual odometry, and then the semantic segmentation network was combined in our stereo SLAM to extract pixel-level contours of dynamic objects. Then, the influences of dynamic objects were significantly weakened and the performance of our system increased markedly in dynamic, complex, and crowed city spaces. Following experiments with both the KITTI Odometry dataset and in a real-life scene, the results showed that our method could dramatically decrease the tracking error or drift, and improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

17 pages, 3343 KiB

Open AccessArticle

Building Change Detection in Remote Sensing Imagery with Focal Self-Attention and Multi-Level Feature Fusion

by Peiquan Shen, Liye Mei, Zhaoyi Ye, Ying Wang, Qi Zhang, Bo Hong, Xiliang Yin and Wei Yang

Electronics 2023, 12(13), 2796; https://doi.org/10.3390/electronics12132796 - 24 Jun 2023

Viewed by 1075

Abstract

Accurate and intelligent building change detection greatly contributes to effective urban development, optimized resource management, and informed decision-making in domains such as urban planning, land management, and environmental monitoring. Existing methodologies face challenges in effectively integrating local and global features for accurate building [...] Read more.

Accurate and intelligent building change detection greatly contributes to effective urban development, optimized resource management, and informed decision-making in domains such as urban planning, land management, and environmental monitoring. Existing methodologies face challenges in effectively integrating local and global features for accurate building change detection. To address these challenges, we propose a novel method that uses focal self-attention to process the feature vector of input images, which uses a “focusing” mechanism to guide the calculation of the self-attention mechanism. By focusing more on critical areas when processing image features in different regions, focal self-attention can better handle both local and global information, and is more flexible and adaptive than other methods, improving detection accuracy. In addition, our multi-level feature fusion module groups the features and then constructs a hierarchical residual structure to fuse the grouped features. On the LEVIR-CD and WHU-CD datasets, our proposed method achieved F1-scores of 91.62% and 89.45%, respectively. Compared with existing methods, ours performed better on building change detection tasks. Our method therefore provides a framework for solving problems related to building change detection, with some reference value and guiding significance. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

15 pages, 6441 KiB

Open AccessArticle

Visual Multitask Real-Time Model in an Automatic Driving Scene

by Xinwang Zheng, Chengyu Lu, Peibin Zhu and Guangsong Yang

Electronics 2023, 12(9), 2097; https://doi.org/10.3390/electronics12092097 - 04 May 2023

Cited by 3 | Viewed by 1520

Abstract

In recent years, automatic driving technology has developed rapidly, and environmental perception is one of the important aspects of the technology of automatic driving. To design a real-time automatic driving perception system with limited computational resources, we first proposed a network with faster [...] Read more.

In recent years, automatic driving technology has developed rapidly, and environmental perception is one of the important aspects of the technology of automatic driving. To design a real-time automatic driving perception system with limited computational resources, we first proposed a network with faster reasoning speed and fewer parameters by using multitask learning and vision-based recognition technology, which can target the three tasks of traffic target detection, drivable road segmentation, and lane detection that need to be performed simultaneously. Based on the Apollo Scape dataset, the experiment results show that our network is superior to the baseline network in terms of accuracy and reasoning speed and can perform various challenging tasks. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

15 pages, 630 KiB

Open AccessArticle

A Multi-User Collaborative Access Control Scheme Based on New Hash Chain

by Zetian Wang, Yunfa Li, Guanxu Liu and Di Zhang

Electronics 2023, 12(8), 1792; https://doi.org/10.3390/electronics12081792 - 10 Apr 2023

Viewed by 843

Abstract

As the threats to the Internet of Things (IoT) continue to increase, access control is widely used in various IoT information systems. However, due to the shortcomings of IoT devices such as low computing power, it is impossible to use high-performance methods to [...] Read more.

As the threats to the Internet of Things (IoT) continue to increase, access control is widely used in various IoT information systems. However, due to the shortcomings of IoT devices such as low computing power, it is impossible to use high-performance methods to control user access. Although the emergence of the blockchain provides another way of thinking for access control, the implementation based on the blockchain requires the device to complete the proof of work (PoW) and requires the device to have high computing power. At the same time, most access control schemes existing today are intended for users to use alone, which cannot be applied to the field of multi-user coordinated access. Therefore, this paper proposes a multi-user collaborative access control scheme based on a new hash chain, which uses the identity information of multiple users as the seed value to construct the hash chain, and uses the hash chain as the PoW of the blockchain. An efficiency analysis showed that this method requires only a small amount of hash value calculation and can be applied to IoT systems with low computing power. The security analysis shows that the scheme can resist a variety of attack methods and has high security. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

12 pages, 3600 KiB

Open AccessArticle

Bust Portraits Matting Based on Improved U-Net

by Honggang Xie, Kaiyuan Hou, Di Jiang and Wanjie Ma

Electronics 2023, 12(6), 1378; https://doi.org/10.3390/electronics12061378 - 14 Mar 2023

Viewed by 1528

Abstract

Extracting complete portrait foregrounds from natural images is widely used in image editing and high-definition map generation. When making high-definition maps, it is often necessary to matte passers-by to guarantee their privacy. Current matting methods that do not require additional trimap inputs often [...] Read more.

Extracting complete portrait foregrounds from natural images is widely used in image editing and high-definition map generation. When making high-definition maps, it is often necessary to matte passers-by to guarantee their privacy. Current matting methods that do not require additional trimap inputs often suffer from inaccurate global predictions or blurred local details. Portrait matting, as a soft segmentation method, allows the creation of excess areas during segmentation, which inevitably leads to noise in the resulting alpha image as well as excess foreground information, so it is not necessary to keep all the excess areas. To overcome the above problems, this paper designed a contour sharpness refining network (CSRN) that modifies the weight of the alpha values of uncertain regions in the prediction map. It is combined with an end-to-end matting network for bust matting based on the U-Net target detection network containing Residual U-blocks. An end-to-end matting network for bust matting is designed. The network can effectively reduce the image noise without affecting the complete foreground information obtained by the deeper network, thus obtaining a more detailed foreground image with fine edge details. The network structure has been tested on the PPM-100, the RealWorldPortrait-636, and a self-built dataset, showing excellent performance in both edge refinement and global prediction for half-figure portraits. Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

17 pages, 5051 KiB

Open AccessArticle

Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection

by Chuan Xu, Qi Zhang, Liye Mei, Sen Shen, Zhaoyi Ye, Di Li, Wei Yang and Xiangyang Zhou

Electronics 2023, 12(4), 898; https://doi.org/10.3390/electronics12040898 - 10 Feb 2023

Cited by 4 | Viewed by 1689

Abstract

Road damage detection is essential to the maintenance and management of roads. The morphological road damage contains a large number of multi-scale features, which means that existing road damage detection algorithms are unable to effectively distinguish and fuse multiple features. In this paper, [...] Read more.

Road damage detection is essential to the maintenance and management of roads. The morphological road damage contains a large number of multi-scale features, which means that existing road damage detection algorithms are unable to effectively distinguish and fuse multiple features. In this paper, we propose a dense multiscale feature learning Transformer embedding cross-shaped attention for road damage detection (DMTC) network, which can segment the damage information in road images and improve the effectiveness of road damage detection. Our DMTC makes three contributions. Firstly, we adopt a cross-shaped attention mechanism to expand the perceptual field of feature extraction, and its global attention effectively improves the feature description of the network. Secondly, we use the dense multi-scale feature learning module to integrate local information at different scales, so that we are able to overcome the difficulty of detecting multiscale targets. Finally, we utilize a multi-layer convolutional segmentation head to generalize the previous feature learning and get a final detection result. Experimental results show that our DMTC network could segment pavement pothole patterns more accurately and effectively than other methods, achieving an F1 score of 79.39% as well as an OA score of 99.83% on the cracks-and-potholes-in-road-images-dataset (CPRID). Full article

(This article belongs to the Special Issue Computer Vision for Modern Vehicles)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Computer Vision for Modern Vehicles

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI