Detection of broken manhole cover using improved Hough and image contrast

The damage or loss of urban road manhole covers may cause great risk to residents＇ lives and property if they cannot be discovered in time. Most existing research recommendations for solving this problem are difficult to implement. This paper proposes an algorithm that combines the improved Hough transform and image comparison to identify the damage or loss of the manhole covers in complicated surface conditions by using existing urban road video images. Focusing on the pre-processed images, the edge contour tracking algorithm is applied to find all of the edges. Then with the improved Hough transformation, color recognition and image matching algorithm, the manhole cover area is found and the change rates of the manhole cover area are calculated. Based on the threshold of the change rates, it can be determined whether there is potential damage or loss in the manhole cover. Compared with the traditional Hough transform, the proposed method can effectively improve the processing speed and reduce invalid sampling and accumulation. Experimental results indicate that the proposed algorithm has the functions of effective positioning and early warning in the conditions of complex background, different perspectives, and different videoing time and conditions, such as when the target is partially covered.

Research on Wavelet-Based Algorithm for Image Contrast Enhancement

A novel wavelet-based algorithm for image enhancement is proposed in the paper. On the basis of multiscale analysis, the proposed algorithm solves efficiently the problem of noise over-enhancement, which commonly occurs in the traditional methods for contrast enhancement. The decomposed coefficients at same scales are processed by a nonlinear method, and the coefficients at different scales are enhanced in different degree. During the procedure, the method takes full advantage of the properties of Human visual system so as to achieve better performance. The simulations demonstrate that these characters of the proposed approach enable it to fully enhance the content in images, to efficiently alleviate the enhancement of noise and to achieve much better enhancement effect than the traditional approaches. Key words wavelet transform - image contrast enhancement - multiscale analysis CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (69931010)Biography: Wu Ying-qian (1974-), male, Ph. D, research direction: image processing, image compression and wavelet.

Influences of Atmospheric Turbulence on Image Resolution of Airborne and Space-Borne Optical Remote Sensing System

A new way is proposed to evaluate the influence of atmospheric turbulence on image resolution of airborne and space-borne optical remote sensing system, which is called as arrival angle-method. Applying this method, some engineering examples are selected to analyze the turbulence influences on image resolution based on three different atmospheric turbulence models quantificationally, for the airborne remote sensing system, the resolution errors caused by the atmospheric turbulence are less than 1 cm, and for the space-borne remote sensing system, the errors are around 1 cm. The results are similar to that obtained by the previous Friedmethod. Compared with the Fried-method, the arrival angle-method is rather simple and can be easily used in engineering fields.

Enhancement Technique of Image Contrast using New Histogram Transformation

This paper presents a preprocessing technique that can provide the improved quality of image robust to illumination changes. First, in order to enhance the image contrast, we proposed new adaptive histogram transformation combining histogram equalization and histogram specification. Here, by examining the characteristic of histogram distribution shape, we determine the appropriate target distribution. Next, applying the histogram equalization with an image histogram, we have obtained the uniform distribution of pixel values, and then we have again carried out the histogram transformation using an inverse of target distribution function. Finally we have conducted various experiments that can enhance the quality of image by applying our method with various standard images. The experimental results show that the proposed method can achieve moderately good image enhancement results.

RGB-guided hyperspectral image super-resolution with deep progressive learning

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

A Second-Order Image Denoising Model for Contrast Preservation

In this work,we propose a second-order model for image denoising by employing a novel potential function recently developed in Zhu(J Sci Comput 88:46,2021)for the design of a regularization term.Due to this new second-order derivative based regularizer,the model is able to alleviate the staircase effect and preserve image contrast.The augmented Lagrangian method(ALM)is utilized to minimize the associated functional and convergence analysis is established for the proposed algorithm.Numerical experiments are presented to demonstrate the features of the proposed model.

Image super‐resolution via dynamic network

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.

The co-effect of image resolution and crown size on deep learning for individual tree detection and delineation

Individual tree detection and delineation(ITDD)is an important subject in forestry and urban forestry.This study represents the first research to propose the concept of crown resolution to comprehensively evaluate the co-effect of image resolution and crown size on deep learning.Six images with different resolutions were derived from a DJI Unmanned Aerial Vehicle(UAV),and 1344 manually delineated Chinese fir(Cunninghamia lanceolata(Lamb)Hook)tree crowns were used for six training and validation mask region-based convolutional neural network(Mask R-CNN)models,while additional 476 delineated tree crowns were reserved for testing.The overall detection accuracy,the influence of different crown sizes,and crown resolutions were calculated to evaluate model performance accuracy with different image resolutions for ITDD.Results show that the highest accuracy was achieved when the crown resolution was between 800 and 12800 pixels/tree.The accuracy of ITDD was impacted by crown resolution,and it was unable to effectively identify Chinese fir when the crown resolution was less than 25 pixels/tree or higher than 12800 pixels/tree.The study highlights crown resolution as a critical factor affecting ITDD and suggests selecting the appropriate resolution based on the target detected crown size.

Robust and Discriminative Feature Learning via Mutual Information Maximization for Object Detection in Aerial Images

Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).

Research on Improved MobileViT Image Tamper Localization Model

As image manipulation technology advances rapidly,the malicious use of image tampering has alarmingly escalated,posing a significant threat to social stability.In the realm of image tampering localization,accurately localizing limited samples,multiple types,and various sizes of regions remains a multitude of challenges.These issues impede the model’s universality and generalization capability and detrimentally affect its performance.To tackle these issues,we propose FL-MobileViT-an improved MobileViT model devised for image tampering localization.Our proposed model utilizes a dual-stream architecture that independently processes the RGB and noise domain,and captures richer traces of tampering through dual-stream integration.Meanwhile,the model incorporating the Focused Linear Attention mechanism within the lightweight network(MobileViT).This substitution significantly diminishes computational complexity and resolves homogeneity problems associated with traditional Transformer attention mechanisms,enhancing feature extraction diversity and improving the model’s localization performance.To comprehensively fuse the generated results from both feature extractors,we introduce the ASPP architecture for multi-scale feature fusion.This facilitates a more precise localization of tampered regions of various sizes.Furthermore,to bolster the model’s generalization ability,we adopt a contrastive learning method and devise a joint optimization training strategy that leverages fused features and captures the disparities in feature distribution in tampered images.This strategy enables the learning of contrastive loss at various stages of the feature extractor and employs it as an additional constraint condition in conjunction with cross-entropy loss.As a result,overfitting issues are effectively alleviated,and the differentiation between tampered and untampered regions is enhanced.Experimental evaluations on five benchmark datasets(IMD-20,CASIA,NIST-16,Columbia and Coverage)validate the effectiveness of our proposed model.The meticulously calibrated FL-MobileViT model consistently outperforms numerous existing general models regarding localization accuracy across diverse datasets,demonstrating superior adaptability.

Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

Photoacoustic microscopy image resolution enhancement via directional total variation regularization

Photoacoustic microscopy （PAM） is recognized as a powerful tool for various microcirculation system studies. To improve the spatial resolution for the PAM images, the requirements of the system will always be increased correspondingly. Without additional cost of the system, we address the problem of improving the resolution of PAM images by integrating a deconvolution model with a directional total variation regularization. Additionally, we present a primal-dual-based algorithm to solve the associated optimization problem efficiently. Results from both test images and some PAM images studies validate the effectiveness of the proposed method in enhancing the spatial resolution. We expect the proposed technique to be an alternative resolution enhancement tool for some important biomedical applications.

Image Non-Uniformity Correction in 3T Gd-EOB-DTPA-Enhanced Magnetic Resonance Imaging: Comparison among Different Software Versions

Background: Non-uniformity in signal intensity occurs commonly in magnetic resonance (MR) imaging, which may pose substantial problems when using a 3T scanner. Therefore, image non-uniformity correction is usually applied. Purpose: To compare the correction effects of the phased-array uniformity enhancement (PURE), a calibration-based image non-uniformity correction method, among three different software versions in 3T Gd-EOB-DTPA-enhanced MR imaging. Material and Methods: Hepatobiliary-phase images of a total of 120 patients who underwent Gd-EOB-DTPA-enhanced MR imaging on the same 3T scanner were analyzed retrospectively. Forty patients each were examined using three software versions (DV25, DV25.1, and DV26). The effects of PURE were compared by visual assessment, histogram analysis of liver signal intensity, evaluation of the spatial distribution of correction effects, and evaluation of quantitative indices of liver parenchymal enhancement. Results: The visual assessment indicated the highest uniformity of PURE-corrected images for DV26, followed by DV25 and DV25.1. Histogram analysis of corrected images demonstrated significantly larger variations in liver signal for DV25.1 than for the other two versions. Although PURE caused a relative increase in pixel values for central and lateral regions, such effects were weaker for DV25.1 than for the other two versions. In the evaluation of quantitative indices of liver parenchymal enhancement, the liver-to-muscle ratio (LMR) was significantly higher for the corrected images than for the uncorrected images, but the liver-to-spleen ratio (LSR) showed no significant differences. For corrected images, the LMR was significantly higher for DV25 and DV26 than for DV25.1, but the LSR showed no significant differences among the three versions. Conclusion: There were differences in the effects of PURE among the three software versions in 3T Gd-EOB-DTPA-enhanced MR imaging. Even if the non-uniformity correction method has the same brand name, correction effects may differ depending on the software version, and these differences may affect visual and quantitative evaluations.

Image Contrast Inversion of a Solvent Cast SEBS Film

The image contrast inversion was investigated in detail when soft polymeric materials were imaged with tapping mode atomic force microscopy （TM-AFM）. Solvent cast film of polystyrene-block-poly（ethylene/butylene）block-polystyrene （SEBS） triblock copolymers was used as a model system in this study, which showed phase separation domains with a size of several tens of nanometers. AFM contrast reversal process, through positive image, to an intermediary and till negative image, could be clearly seen in height images of the soft block copolymer using different tapping force. The higher tapping force would lead to not only contrast inversion, but also the different size of the microdomains and different roughness of the images. Moreover, contrast inversion was explained on the basis of attractive and repulsive contributions to the tip-sample interaction and indentation of the soft domains.

Image enhancement and post-processing for low resolution compressed video

This research paper recommends the point spread function(PSF)forecasting technique based on the projection onto convex set(POCS)and regularization to acquire low resolution images.As the environment for the production of user created contents(UCC)videos(one of the contents on the Internet)becomes widespread,resolution reduction and image distortion occurs,failing to satisfy users who desire high quality images.Accordingly,this research neutralizes the coding artifact through POCS and regularization processes by:1)factoring the local characteristics of the image when it comes to the noise that results during the discrete cosine transform(DCT)and quantization process;and 2)removing the blocking and ring phenomena which are problems with the existing video compression.Moreover,this research forecasts the point spread function to obtain low resolution images using the above-mentioned methods.Thus,a method is suggested for minimizing the errors found among the forecasting interpolation pixels.Low-resolution image quality obtained through the experiment demonstrates that significant enhancement was made on the visual level compared to the original image.

Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network

Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.

Triplet Label Based Image Retrieval Using Deep Learning in Large Database

Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.

A Local Contrast Fusion Based 3D Otsu Algorithm for Multilevel Image Segmentation

To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.

THE HIGH RESOLUTION SEISMIC TOMOGRAPHIC IMAGE IN QINGHAI—TIBET PLATEAU AND ITS DYNAMIC IMPLICATIONS

The Qinghai—Tibet plateau and its surrounding areas including Indian subcontinent, Xinjiang, Mongolia, is a largest lithosphere convergence place in the world, which characterized by continent\|continent collision with a thick crust and lithosphere. The high resolution seismic surface wave tomographic inversion has been conducted for studying the 3D velocity structure of crust and upper mantle in those areas. The seismic surface waveform data are from the archives of the CDSN, GSN and GEOSCOPE. About 2400 long period surface waveform recordings are available for both dispersion and waveform tomographic inversion. The block inversion by grid 1°×1°in Qinghai—Tibet plateau and 2°×2°in the surrounding areas were adapted. The resulting maps show the high resolution 3D shear wave velocity variation from earth’s surface to 400km depth.

Asymmetric Loss Based on Image Properties for Deep Learning-Based Image Restoration

Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.