Grayscale Research Articles

Study on the Influence of Carbonation on the Microstructure of Cement-based Materials Based on BSE Technique

Background: The influence of carbonation on the interfacial transition zone (ITZ) microstructure of cement-based materials was significant. However, the width of ITZ is about tens of microns, and studying its micro-characteristics (such as porosity, hydration products, content of unhydrated cement, etc.) by macro test was difficult. Methods: Backscattered electron (BSE) imaging technology and gray scale analysis method were used to analyze the cement-based materials with water-binder (W/B) ratios of 0.53 and 0.35, respectively. Results: BSE and gray scale analysis showed that in the ITZ, the porosity of 0.53P (Portland cement paste), 0.35P (Portland cement paste), 0.53F (fly ash), and 0.35F (fly ash) decreased by 24.1%, 28.9%, 49.5%, and 64.2% respectively, whereas the content of hydration products increases after carbonation, and the matrix also shows the same rule. At the same time, the smaller W/B ratio, the greater the porosity reduction, and the filling effect of carbonation on the specimens with supplementary cementitious material (SCM) was more significant than that of pure cement specimens. Conclusion: The porosity of the ITZ decreased after carbonation, however it remained higher than that of the matrix. Consequently, the ITZ remained a vulnerable zone with a greater diffusion rate of CO2 compared to the matrix even after carbonation.

Multi-spectral Remote Sensing Image Fusion Method Based on Gradient Moment Matching

Image fusion is a popular research direction in the field of computer vision. Traditional image fusion algorithms can achieve good results in fusing grayscale images, but it is difficult to achieve ideal results in processing multi-spectral images. To address the shortcomings of multi-spectral image fusion, this study proposes a low computational complexity and low latency multi-spectral image fusion model by utilizing a multi-step degree moment matching algorithm and a generative adversarial network for fusion. Through experiments, it was found that the F1 score of the GAN-MMN model on the TinyPerson dataset was 89.79%, with an average recall rate of 89.76%. The GAN-MMN performance was higher than that of the control model. Meanwhile, the GAN-MMN model also exhibited superior performance in high-frequency feature extraction and time delay compared to the control model. According to the experimental results, the proposed multi-spectral remote sensing image fusion model had a high feature extraction effect, and its recall rate and F1 score were better than the control model, so the research model had a certain progressiveness. The proposal of this model gives a new approach for the processing of multi-spectral remote sensing images, effectively promoting the development of the computer vision industry.

An efficient convolutional neural network for adversarial training against adversarial attack

Convolutional neural networks (CNN) are widely used by researchers due to their extensive advantages over various applications. However, images are highly susceptible to malicious attacks using perturbations that are unrecognized even under human intervention. This causes significant security perils and challenges to CNN-related applications. In this article, an efficient adversarial training model against malevolent attacks is demonstrated. This model is highly robust to black-box malicious examples, it is processed with different malicious samples. Initially, malicious training models like fast gradient descent (FGS), recursive-FGSM (I-FGS), Deep-Fool, and Carlini and Wagner (CW) techniques are utilized that generate adversarial input by means of the CNN acknowledged to the attacker. In the experimentation process, the MNIST dataset comprising 60K and 10K training and testing grey-scale images are utilized. In the experimental section, the adversarial training model reduces the attack accuracy rate (ASR) by an average of 29.2% for different malicious inputs, when preserving the accuracy of 98.9% concerning actual images in the MNIST database. The simulation outcomes show the preeminence of the model against adversarial attacks.

Image-based finite element model stiffness and vBMD by single and dual energy CT reconstruction kernel

Single-energy quantitative computed tomography (SEQCT) provides volumetric bone mineral density (vBMD) measures for bone analysis and input to image-based finite element models (FEMs). Dual-energy CT (DECT) improves vBMD by accounting for voxel-specific material variations utilizing scans at multiple x-ray energies. vBMD is also altered by reconstruction kernel that cannot be accounted for using calibration phantoms. This study compared vBMD and FEM stiffness derived from SEQCT and DECT images reconstructed with two common kernels. SEQCT and DECT images of cadaveric shoulders (n = 10) were collected using standard (STD) and boneplus (BONE) kernels. Hounsfield Units were converted to vBMD using specimen-specific calibrations. DECT STD and BONE images were generated using an established material decomposition method with 40 and 90 keV simulated monochromatic images. A proximal humerus bone section below the anatomic neck was used for vBMD analysis and FEM generation. FEMs were loaded to 1 % apparent strain for stiffness measurements.Between STD and BONE kernel images, average vBMD differed 0.9 mgK2HPO4/cc and 4.1 mg K2HPO4/cc, in SEQCT and DECT images, respectively. Significant differences occurred in DECT images (p = 0.001). BONE reconstructed images produced higher vBMD measures across both SEQCT and DECT images. The difference between STD and BONE in both SEQCT- and DECT-based FEMs persisted, with larger estimated stiffness in BONE models. For six of the models DECT-based had higher stiffness than SEQCT-based models using the same kernel, although these models differed between STD and BONE kernels. Differences in stiffness between STD and BONE derived models were similar across image types (DECT: 17.5 kN/mm; SEQCT: 19.0 kN/mm). Stiffness values were significantly different within SECT kernels and between SEQCT BONE and DECT STD models. This study shows important differences in vBMD and FEM stiffness that occur due to CT-based imaging parameters alone. These results indicate that consistent imaging parameters should be used for vBMD analysis and FEM input to avoid systematic measurement errors.

An Ensemble Framework Augmenting Surveillance Cameras for Detecting Intruder Clusters as Potential Mobs

<p>Many developing nations around the world curtail crimes through video surveillance technology, but the crime rate is still high. This is compounded by short-staffed security operatives and a deficiency of security infrastructure to assist security operatives with knowledge-driven decision support systems in the low-resource constraint environment. In a public environment, it is challenging to detect intruder clusters accurately as potential mobs for early warning. Previous research investigated some classical techniques, but their recommendations were insufficient. This research develops a Machine Learning (ML) 3-tiers Ensemble framework, which integrates Gray Level Co-occurrence Matrices (GLCM) principles to enhance the capabilities of surveillance cameras and security operatives to effectively discern and respond to potential mob formations. The University of California San Diego (UCSD) pedestrian datasets that are publicly available were used for the experiments. With an improved overall average precision of 0.98, recall of 0.98, and accuracy of 98.52% on the UCSD dataset, the suggested framework outperforms the widely used methods for the detection of intruder clusters. The reduction in computational time on processors showcases the framework's significant advancements as a promising solution for robust real-time threat assessment applications.</p>

Classification of Liver Lesion Stages using pyRadiomics Features Combined with 3D-CNN in 3D-CT and US Images

Objectives: The goal of this study is to identify the various stages in liver diseases employing pyRadiomics features by analyzing the 3-dimensional CT and US images. Methods: The study uses Gray level Run Length Matrix for feature extraction and 3D-CNN for classification and compared with methods like Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes (NB) classifiers to assess the efficiency of the proposed model. The suggested algorithm is implemented using the library functions in Tensorflow and Keras packages in Python. Findings: The study utilizes radiomic feature extraction and two-phase classification to detect and classify liver disorders. In the first phase, binary classification is used to classify US and CT images as normal or abnormal, with accuracy rates of 95.4% and 97.9%. This is followed by the second phase classification, which classifies the lesion stages for both US and CT aberrant images. CT images have been shown to be more accurate in categorizing lesion stages than US imaging. CT images have a much lower misclassification rate at each step than US images. Finally, the effectiveness of the 3D-CNN model is compared with SVM, RF, and NB and the suggested method outperforms the other methods. Novelty: The suggested architecture employs radionics feature extraction with two-phase CNN for classification and the suggested method is found to be more efficient than SVM, RF, and NB. Keywords: Radiomics; Feature Extraction; Convolutional Neural Networks (CNN); Classification; Liver Diseases

Visibility of alveolar bone thicknesses on CBCT images-a study on minimum bone requirements using various reconstruction techniques, viewing modes, and resolutions.

To evaluate at which thickness marginal bone becomes visible to the observer on cone-beam computed tomography (CBCT) images and how reconstruction technique and viewing mode affect assessment. Fourteen anterior teeth from six human mandibles were examined with two CBCT resolution protocols: standard- and high-resolution. Distance from the cementoenamel junction to the visible marginal bone level (MBL) was measured in three groups of reconstructed CBCT images: multiplanar reformation (MPR) with grey scale, MPR with inverted grey scale, and 3D rendering. These measurements were used to identify the bone level where marginal bone width should be measured on histological photographs of sliced teeth. Gold standards comprised measurements of bone thickness at the superior MBL on histological photographs. MPR grey scale images exposed at high-resolution settings yielded highest validity: bone widths of 0.173mm (buccal) and 0.356mm (lingual) were necessary for visibility on a CBCT image. 3D-rendered lingual surfaces exposed with high-resolution settings had lowest validity. Intra-observer agreement for all CBCT and histological measurements was high. The best CBCT resolution protocol, reconstruction technique, and viewing mode for analyzing buccal and lingual surfaces of the alveolar bone margin are images exposed with a high-resolution protocol, reconstructed using MPR, and viewed in grey scale. Bone thickness required to be visualized was twice lingually compared to buccally. The visualization of bone thickness in CBCT requires a greater thickness on the lingual side compared to the buccal side. 3D-rendered reconstructions should be avoided when evaluating thin bony structures.

The optimal energy level of virtual monochromatic imaging in Dual-energy CT arthrography of the wrist.

To suggest an optimal energy level of virtual monochromatic images (VMIs) in dual-energy CT arthrography of the wrist. This retrospective study included 53 patients with wrist CT arthrography. Conventional polychromatic images and VMIs at four energy levels (40 to 70 keV at 10 keV intervals) were obtained. Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured, and qualitative analysis of image quality and diagnostic confidence was performed. For each patient, an energy level with the best image quality was chosen by consensus. Comparisons of quantitative and qualitative parameters between VMI sets were performed. The image noise of bone and muscle were increased with decreasing energy level (p < 0.001). The noise of contrast was highest on 60 keV VMI. SNR and CNR (between contrast and muscle) were increased with decreasing energy level and were markedly increased between 60 and 50 keV (p < 0.001). The 60 keV VMI demonstrated the highest image quality and diagnostic confidence, chosen as the best diagnostic image (n = 31/53). Given that the attenuation of the contrast material was low on the conventional image, the optimal energy level of the best VMI tended to be low. Wrist dual-energy CT arthrography with VMIs at 60 keV or less could improve image quality and diagnostic performance by increasing SNR and CNR in cases with low contrast attenuation. Wrist dual-energy CT arthrography with VMIs at variable keV could be utilised to enhance SNR and CNR, thereby achieving diagnostic images of high quality.

Double-gate metal–oxide TFT pixel circuit for improved luminance uniformity of mobile OLED display

The small subthreshold swing (SS) of metal–oxide (MOx) thin-film transistors (TFTs) reduces the data voltage (VDAT) range of the organic light-emitting diode (OLED) display pixel circuit. This leads to a large OLED current error when a small change occurs in the gate-to-source voltage (VGS) of the driving TFT in the pixel. Therefore, we propose a new pixel circuit adopting a double-gate TFT structure for the driving TFT, which is mainly driven by the bottom gate with a thicker gate insulator to provide a wide VDAT range. The proposed pixel circuit further expands the VDAT range by employing threshold voltage (VTH) modulation effect depending on the gray level. It also allows for flexible adjustment of the VTH extraction time to reduce OLED current error at low gray levels. SPICE simulation and measured results verify that the proposed pixel circuit reduces the OLED current error rate to less than 10% even with a VTH variation of ±0.5 V or SS variation of ±5% for the current level from 0.1 nA to 30 nA.

Computer-Aided Diagnosis of Early-Stage Retinopathy of Prematurity in Neonatal Fundus Images Using Artificial Intelligence.

Retinopathy of Prematurity (ROP) is a retinal disorder affecting preterm babies, which can lead to permanent blindness without treatment. Early-stage ROP diagnosis is vital in providing optimal therapy for the neonates. The proposed study predicts early-stage ROP from neonatal fundus images using Machine Learning (ML) classifiers and Convolution Neural Networks (CNN) based pre-trained networks. The characteristic demarcation lines and ridges in early stage ROP are segmented utilising a novel Swin U-Net. 2000 Scale Invariant Feature Transform (SIFT) descriptors were extracted from the segmented ridges and are dimensionally reduced to 50 features using Principal Component Analysis (PCA). Seven ROP-specific features, including six Gray Level Co-occurrence Matrix (GLCM) and ridge length features, are extracted from the segmented image and are fused with the PCA reduced 50 SIFT features. Finally, three ML classifiers, such as Support Vector Machine (SVM), Random Forest (RF), and k- Nearest Neighbor (k-NN), are used to classify the 50 features to predict the early-stage ROP from Normal images. On the other hand, the raw retinal images are classified directly into normal and early-stage ROP using six pre-trained classifiers, namely ResNet50, ShuffleNet V2, EfficientNet, MobileNet, VGG16, and DarkNet19. It is seen that the ResNet50 network outperformed all other networks in predicting early-stage ROP with 89.5% accuracy, 87.5% sensitivity, 91.5% specificity, 91.1% precision, 88% NPV and an Area Under the Curve (AUC) of 0.92. Swin U-Net Convolutional Neural Networks (CNN) segmented the ridges and demarcation lines with an accuracy of 89.7% with 80.5% precision, 92.6% recall, 75.76% IoU, and 0.86 as the Dice coefficient. The SVM classifier using the 57 features from the segmented images achieved a classification accuracy of 88.75%, sensitivity of 90%, specificity of 87.5%, and an AUC of 0.91. The system can be utilised as a point-of-care diagnostic tool for ROP diagnosis of neonates in remote areas.

An experimental study on the diagnostic advantage of dual-energy computed tomography over single-energy scan to evaluate the treatment effect following transcatheter arterial chemoembolization.

We assessed the diagnostic advantage of dual-energy computed tomography (DECT) over single-energy computed tomography (SECT) to evaluate lipiodol accumulation in target lesions following transcatheter arterial chemoembolization (TACE). TACE was performed in 10 rabbits in whom the VX2 tumor was implanted in their left liver lobes. The miriplatin-lipiodol mixture was injected into the common hepatic artery. All rabbits were sacrificed 2 days after TACE, and the liver was harvested. CT was performed using both single-energy and dual-energy scan modes. The specimen was stained with Oil Red O to evaluate lipiodol accumulation; this was considered the reference standard. Mutual information (MI) was used to evaluate the significance of radiological-pathological correlation. Estimated iodine content values on iodine material density images were compared with actual values obtained using mass spectroscopy. Mean MI values were 0.69, 0.32, 0.83, 0.72, 0.65, and 0.58 for single-energy scan; iodine density images; and virtual monoenergetic images for energy levels of 40, 60, 80, and 100 keV, respectively. The MI value of the monochromatic image (40 keV) was the highest among all sequences. However, this was not significant compared with the single-energy scan (p = 0.81). A significant correlation was observed between the estimated and actual values of iodine content (Pearson's product moment coefficient = 0.70, p = 0.023). More accurate and quantitative lipiodol evaluation in targeted tumors after TACE can be achieved by applying DECT rather than SECT.

Abstract 4135968: Radiomic features of skeletal muscle on prostate T1-Weighted MRI associated with MACE outcomes in prostate cancer patients undergoing hormonal therapy

Background: Patients with high-risk prostate cancer (PC) who undergo hormonal therapy(HT) frequently die of major adverse cardiovascular events (MACE). Skeletal muscle on abdominal T1-weighted MRI (T1W) has been shown to be associated with cardiovascular fitness. Aims: To quantify heterogeneity associated with skeletal muscle tissue composition on prostate MRI patients undergoing HT using computationally derived radiomic features and identify their association with MACE. Methods: Cohort of N=58 men diagnosed with PC who underwent a 3 Tesla pre-treatment multi-parametric MRI followed by HT and followed up for MACE events were identified. MACE is defined as a composite of cardiovascular death, atrial fibrillation, myocardial infarction, ischemic stroke, heart failure, coronary artery disease, and peripheral vascular disease. Regions of interest (ROI) of skeletal muscle, including the obturator externus, pectineus, and the adductor group of muscles, were delineated on axial T1W under the guidance of an experienced radiologist. A set of 120 radiomic features, including gray level statistics, co-occurrence, wavelet, and texture energy-based features, were extracted within the ROI which quantifies underlying subvisual texture-based heterogeneity. Radiomics associated with MACE events were identified using the Wilcoxon rank-sum test and univariate Cox-regression (p&lt;0.05). Results: Of the N=58 patients included in this study, 18 experienced MACE. The most common MACE event was AF (8.6%). Median-time-to-MACE event was 7.3 years (6.2-8.2). 3 radiomic features (Table 1) quantifying the heterogeneity of skeletal muscle on prostate T1W were observed to be associated with MACE. Specifically, we observe that first order features have a lower response and wavelet features have a lower response in MACE patients which suggests a higher degree of local deformations and heterogeneity in skeletal tissue compared to non-MACE patients. Conclusions: Results from our study suggest that radiomics quantified texture characteristics of skeletal muscle tissue may indicate cardiovascular fitness, reflecting the likelihood of experiencing MACE following initiation of HT in PC men. Pre-treatment identification of PC patients at high risk of MACE may allow for alternative treatment options improving cardiovascular outcomes. Future studies will involve exploring larger, multi-site cohorts and machine learning modeling to determine cardiovascular risk.

SURG-33. INTRAOPERATIVE ULTRASSOUND X SODIUM FLUORESCEIN FOR GLIOMA SURGERY: WHICH IS BETTER?

Abstract BACKGROUND Improve quality of life with a maximum surgical resection is the main goal of neurosurgeons. A better delimitation of intrinsic brain tumors are required for achieving a maximum tumor removal. There are several technologies that may help. Considering two of them that have an easier access and are cheaper, we compared a high definition ultrasound (BK 3000) and sodium fluorescein (SF) during glioma surgeries. METHODS Adult patients with main radiological hypothesis of low or high grade glioma were included in a PhD study previously approved by ethics committee. 3-5mg/kg of SF was administered by intravenous infusion during anesthetic induction. An specific craniotomy transducer was used in all cases. All procedures were guided by the same neurosurgeon. RESULTS High definition ultrasound allows an excellent tumor delimitation in high and low grade tumors. However the gray scale and distinction of brain structures and residual lesion was difficult for surgeons who are not habituated to ultrasound use. SF did not help low grade glioma removal, and in these cases ultrasound were superior. Increased fluorescence is easily detected when compared to ultrasound information’s. For small residual tumor, SF helps more than US. For both technologies, when the surgical site had blood, the evaluation about grade of resection is not accurate because in ultrasound appears a posterior shadow and considering SF it seems that there are not further tumor because blood does not have increased fluorescence. CONCLUSIONS US showed superiority for low grade gliomas resection. Considering high grade, both technologies helps in different moments during the surgery and are complimentary. We used an specific probe for neurosurgery that has high quality and allowed detailed evaluations. These technologies helps surgeons take quick decision and optimized brain tumor removal. The neurosurgeon should be more familiar to US images because provide a real time evaluation with low cost. KEY WORDS: ultrasound; fluorescein; gliomas; brain tumors

Nanograting-Based Dynamic Structural Colors Using Heterogeneous Materials.

Dynamic structural colors can change in response to different environmental stimuli. This ability remains effective even when the size of the species responsible for the structural color is reduced to a few micrometers, providing a promising sensing mechanism for solving microenvironmental sensing problems in micro-robotics and microfluidics. However, the lack of dynamic structural colors that can encode rapidly, easily integrate, and accurately reflect changes in physical quantities hinders their use in microscale sensing applications. Herein, we present a 2.5-dimensional dynamic structural color based on nanogratings of heterogeneous materials, which were obtained by interweaving a pH-responsive hydrogel with an IP-L photoresist. Transverse gratings printed with pH-responsive hydrogels elongated the period of longitudinal grating in the swollen state, resulting in pH-tuned structural colors at a 45° incidence. Moreover, the patterned encoding and array printing of dynamic structural colors were achieved using grayscale stripe images to accurately encode the periods and heights of the nanogrid structures. Overall, dynamic structural color networks exhibit promising potential for applications in information encryption and in situ sensing for microfluidic chips.

Medical Image, Analysis and Visualization using Image Processing

This project presents an automated approach for detecting brain tumor using Magnetic Resonance Imaging (MRI) and image processing techniques. Traditional methods rely on human inspection, which can be error-prone and time consuming. Our framework consists of several modules: acquiring MRI images, preprocessing to enhance image quality (including noise reduction and edge detection), and segmenting the tumor using the Watershed algorithm. We extract texture features from the segmented images using the Gray Level Co-occurrence Matrix (GLCM), focusing on metrics like energy, contrast, correlation, and homogeneity. Finally, we classify the MRI images as normal or abnormal using a Multilayer Perceptron (MLP) model. This automated detection process improves the efficiency of tumor identification, providing insights into the size, shape, and position of the tumor while alleviating the workload of radiologists.

A GRAPH CONVOLUTIONAL NETWORK APPROACH FOR PREDICTING NETWORK ROBUSTNESS

Network robustness, which includes controllability robustness and connectivity robustness, reflects the ability of a network system to withstand attacks. In this paper, a Graph Convolutional Network (GCN) approach is proposed for predicting network robustness. In contrast to the existing Convolutional Neural Network (CNN) approach, the network topology and the node characteristics are directly used as GCN input without being converted into a grayscale image. Due to the reduction in the number of feature maps, the model size of a GCN is greatly reduced to only 1% of a CNN. Extensive experimental studies on four representative networks and six real networks have proven that the proposed approach can achieve better predictive performance with less training and running time.

Automatic Defects Recognition of Lap Joint of Unequal Thickness Based on X-Ray Image Processing

It is difficult to automatically recognize defects using digital image processing methods in X-ray radiographs of lap joints made from plates of unequal thickness. The continuous change in the wall thickness of the lap joint workpiece causes very different gray levels in an X-ray background image. Furthermore, due to the shape and fixturing of the workpiece, the distribution of the weld seam in the radiograph is not vertical which results in an angle between the weld seam and the vertical direction. This makes automatic defect detection and localization difficult. In this paper, a method of X-ray image correction based on invariant moments is presented to solve the problem. In addition, a novel background removal method based on image processing is introduced to reduce the difficulty of defect recognition caused by variations in grayscale. At the same time, an automatic defect detection method combining image noise suppression, image segmentation, and mathematical morphology is adopted. The results show that the proposed method can effectively recognize the gas pores in an automatic welded lap joint of unequal thickness, making it suitable for automatic detection.

Attention-enhanced multimodal feature fusion network for clothes-changing person re-identification

Clothes-Changing Person Re-Identification is a challenging problem in computer vision, primarily due to the appearance variations caused by clothing changes across different camera views. This poses significant challenges to traditional person re-identification techniques that rely on clothing features. These challenges include the inconsistency of clothing and the difficulty in learning reliable clothing-irrelevant local features. To address this issue, we propose a novel network architecture called the Attention-Enhanced Multimodal Feature Fusion Network (AE-Net). AE-Net effectively mitigates the impact of clothing changes on recognition accuracy by integrating RGB global features, grayscale image features, and clothing-irrelevant features obtained through semantic segmentation. Specifically, global features capture the overall appearance of the person; grayscale image features help eliminate the interference of color in recognition; and clothing-irrelevant features derived from semantic segmentation enforce the model to learn features independent of the person’s clothing. Additionally, we introduce a multi-scale fusion attention mechanism that further enhances the model’s ability to capture both detailed and global structures, thereby improving recognition accuracy and robustness. Extensive experimental results demonstrate that AE-Net outperforms several state-of-the-art methods on the PRCC and LTCC datasets, particularly in scenarios with significant clothing changes. On the PRCC and LTCC datasets, AE-Net achieves Top-1 accuracy rates of 60.4% and 42.9%, respectively.

Enhancing Black-and-White Image Colorization Using Cycle GAN: A Study on Unpaired Image Translation

Abstract. This paper explores the application of Cycle-Consistent Generative Adversarial Network (Cycle GAN) for the colorization of black-and-white images, addressing the challenges in image to the image translation and it was not requiring paired datasets. Cycle GAN, a generative adversarial network, uses cycle consistency loss to map grayscale images to color, effectively preserving structural integrity. The model is trained on unpaired datasets containing black-and-white and color images, enabling it to generate colorized versions from grayscale inputs. Performance evaluation is conducted using Two significant evaluation metrics: Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Results demonstrate that Cycle GAN effectively preserves image structure and detail, achieving high PSNR and SSIM values, particularly in scenes with distinct color boundaries. However, challenges arise in complex and low-resolution scenes where color accuracy and detail reconstruction may degrade. Additionally, this paper assesses the impact of different loss functions, learning rate schedules, and training strategies on the models output quality. Future work will focus on addressing these limitations by incorporating attention mechanisms and other advanced techniques to improve Cycle GAN's ability to handle intricate image features and complex scenes.

An algorithm for lane detection based on RIME optimization and optimal threshold

In order to address the challenges of low lane line detection rates caused by complex road conditions,we propose a novel algorithm that integrates frost and ice optimisation with optimal thresholding. A pre-processing model based on Retinex theory is used to reduce noise and preserve grey scale detail. The optimal OTSU threshold is determined for segmentation, which is enhanced by tent mapping. To further enhance the precision of the detection process, the binarized image is transformed into a bird’s-eye view, and the lane line pixel features are identified through the use of an adaptive sliding window. Ultimately, the RANSAC algorithm is utilized in conjunction with a parabolic model for lane line fitting. The experimental results demonstrate that, in comparison to similar image segmentation algorithms, the proposed method exhibits a notable advantage in terms of threshold calculation error and computational efficiency. Moreover, in comparison to analogous line detection algorithms, the detection accuracy rate reaches 93.87%, effectively reducing the impact of interference factors and demonstrating remarkable robustness that surpasses the traditional Hough Transform, which has an accuracy of 43.2%, and sliding window and Hough transform, with an accuracy of 89.16%. The code of our research work is publicly available at: https://github.com/zx2000430/rime.