One of the major challenges of AI is the misuse of images generated by generative models. Advances in this field have reached a point where distinguishing between real and fake images can be impossible for humans and ...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
One of the major challenges of AI is the misuse of images generated by generative models. Advances in this field have reached a point where distinguishing between real and fake images can be impossible for humans and challenging even for machines. Although significant work has been done on detecting fake images, there is an ongoing competition between content generation and detection methods. However, a significant challenge for detection methods is their limitation to content generated by specific models. This study aims to enhance the generalization of fake image detection methods. Experimental results indicate that modifications made to the base model have contributed to improving its generalizability.
Today, classification of polarimetric images is an important topic where various statistical pattern recognition methods have been used to achieve the high accurate classification maps. In this work, weighting the pol...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
Today, classification of polarimetric images is an important topic where various statistical pattern recognition methods have been used to achieve the high accurate classification maps. In this work, weighting the polarimetric features according to their statistical behavior (the mean vector and variance values as the first and second statistics) is suggested to improve the PolSAR image classification. A weighted feature matrix is composed and applied to the popular classifiers such as maximum likelihood, K-nearest neighbor and support vector machine. The weighted feature matrix can be also implemented on other arbitrary classifiers to improve their discrimination ability. The experiments on the L-band AIRSAR dataset show appropriate classification results.
The polarimetric synthetic aperture radar (PolSAR) images contain fine characteristics and abstract spatial features, which attention to them can improve the classification accuracy. In this work, the residual convolu...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
The polarimetric synthetic aperture radar (PolSAR) images contain fine characteristics and abstract spatial features, which attention to them can improve the classification accuracy. In this work, the residual convolutional neural network with autoencoder based attention (RCNN-AA) is proposed for PolSAR image classification. The scaled difference of the convolutional autoencoder with the original input patch is used as the weight, which contains information about the fine spatial features. Multiplication of this normalized difference in the input patch provides the attention feature maps that can be concatenated with the original input and used as input of the RCNN. An ablation study is done, and also, the proposed RCNN-AA model is compared to some deep learning based models. The results show preference of the RCNN-AA with respect to the competitors.
In recent years, various deep learning frameworks have been developed for the classification of remotely sensed images. However, the network models proposed in these frameworks exhibit high complexity and do not yield...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
In recent years, various deep learning frameworks have been developed for the classification of remotely sensed images. However, the network models proposed in these frameworks exhibit high complexity and do not yield high classification accuracy when applied to unlabeled scenarios. This paper introduces a Multi spectral image (MSI) classification approach that combines the random patches network with self-supervised branch (RPSS) to extract informative deep features. The proposed method involves convolving image bands with random patches to obtain multi-level deep features. Subsequently, we use panchromatic image (PAN) to extract spatial features. The MS spectral features, the derived RPSS features and spatial features then merged to classify the MSI using a support vector machine (SVM) classifier. The experimental results on real remotely sensed images have been presented.
With the growth of editing and sharing images through the internet, the importance of protecting the images' authority has increased. Robust watermarking is a known approach to maintain copyright protection. Robus...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
With the growth of editing and sharing images through the internet, the importance of protecting the images' authority has increased. Robust watermarking is a known approach to maintain copyright protection. Robustness and imperceptibility are two factors that are tried to be maximized through watermarking. Usually, there is a trade-off between these two parameters. Increasing the robustness would lessen the imperceptibility of the watermarking. This paper proposes an adaptive method that determines the strength of the watermark embedding in different parts of the cover image regarding its texture and brightness. Adaptive embedding increases the robustness while preserving the quality of the watermarked image. Experimental results also show that the proposed method can effectively reconstruct the embedded payload in different kinds of common watermarking attacks. Our proposed method has shown good performance compared to a recent technique.
This paper introduces a vision-based dynamic positioning (DP) control system and develops a hardware-in-the-loop (HIL) platform to validate the performance of the controller applied to a work-class remotely operated v...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
This paper introduces a vision-based dynamic positioning (DP) control system and develops a hardware-in-the-loop (HIL) platform to validate the performance of the controller applied to a work-class remotely operated vehicle (ROV). The proposed platform consists of three main parts: hardware, imageprocessing part and controller. The hardware included a calibrated camera that was connected to a dedicated computer via USB 2.0. In the imageprocessing part after pre-processing a circular Hough transform was used to detect and determine the position of the target in the image plane. Furthermore, this paper proposed a feedforward proportional-integral-derivative (PID) controller. To evaluate the performance of the proposed controller, two scenarios were implemented. In the first scenario, the target was considered stationary and a disturbance was applied to the ROV in the simulation environment. In the second scenario, the target object has moved along a rectangular path, and the objective was to stabilize the ROV at the desired points. In both scenarios, the reference signal was acquired by a calibrated camera from the target and sent to the controller. The results showed the desirable performance of the proposed controller.
Classification of multispectral images in remote-sensing area having the capability to analyze and categorize diversified land cover. In this issue, extracting suitable spatial, spectral and even temporal features is ...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
Classification of multispectral images in remote-sensing area having the capability to analyze and categorize diversified land cover. In this issue, extracting suitable spatial, spectral and even temporal features is one of the main challenges. Also, the existence of sufficient data required for the classification training process is another challenge, because in many cases it may not be available and we may not even have a reliable classification map. The use of neural networks for simultaneous feature extraction and classification is very popular and significant progress has been made in this field, but these networks usually have a high computational cost and require significant training data in the training process. In this work we propose a neural network for multispectral image classification purpose which requires few training samples and less calculation without using filterbanks for spatial feature extraction and it can improve classification accuracy by fusion of spatial and spectral features. The simulations indicate that the proposed method shows an acceptable performance.
Single image Super-Resolution (SISR), which aims to recover a high-resolution (HR) image from a low-resolution (LR) one, is an ill-posed problem. Convolutional Neural Networks (CNNs) have been used in low-level vision...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
Single image Super-Resolution (SISR), which aims to recover a high-resolution (HR) image from a low-resolution (LR) one, is an ill-posed problem. Convolutional Neural Networks (CNNs) have been used in low-level vision tasks such as Super-Resolution (SR), and inspired by impressive results in high-level tasks. By choosing the proper structure, the methods can be improved significantly. In this case, selecting an appropriate loss function is essential for any deep learning task, especially in SISR. The exploited loss function impacts the quality of the images produced by the SISR algorithms. Some loss functions can make the output image look blurred or unnatural, which goes against the purpose of SR. To ensure that the output image retains the content of the original photo while also improving the structure and texture, it is essential to choose a loss that is well suited for the task. In this paper, various loss functions for SISR are reviewed. Then, we present an overall analysis of loss functions for SISR based on our exploration.
The proceedings contain 225 papers. The topics discussed include: a novel method for aerial detection of densely occluded small targets;segmenting sonar images with an enhanced OTSU algorithm;learning a residual fusio...
ISBN:
(纸本)9798350331417
The proceedings contain 225 papers. The topics discussed include: a novel method for aerial detection of densely occluded small targets;segmenting sonar images with an enhanced OTSU algorithm;learning a residual fusion network for SAR image despeckling;deep learning-based particle gradation detection of fillers;pre-training For mmWave radar object detection through masked image modeling;industrial inspection auxiliary system based on AR technology;metric-based few-shot learning method for driver distracted behaviors detection;exploration of lightweight neural network architectures for sentiment analysis;a solar irradiance prediction method based on signal decomposition and informer;an intelligent measurement method for air preheater clearance;helmet detection method of improved YOLOv7-tiny;and research on person object tracking method based on extended reality.
Change detection in multi-temporal remote sensing data enables crucial urban analysis and environmental monitoring applications. However, complex factors like illumination variance and occlusion make robust automated ...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
Change detection in multi-temporal remote sensing data enables crucial urban analysis and environmental monitoring applications. However, complex factors like illumination variance and occlusion make robust automated change interpretation challenging. We propose MaskChanger - a novel deep learning paradigm tailored for satellite image change detection. Our method adapts the segmentation-specialized Mask2Former architecture by incorporating Siamese networks to extract features separately from bi-temporal images, while retaining the original mask transformer decoder. To our knowledge, this is the first study in which change detection is converted from the existing per-pixel classification approach into a mask classification approach. Evaluated on the LEVIR-CD benchmark of over 600 very high-resolution image pairs exhibiting real-world rural and urban changes, MaskChanger achieves F1-Score of 91.96%, outperforming prior transformer-based change detection approaches.
暂无评论