Search Results (25)

Accurately classifying road signs is crucial for autonomous driving due to the high stakes involved in ensuring safety and compliance. As Convolutional Neural Networks (CNNs) have largely replaced traditional Machine Learning models in this domain, the demand for substantial training data has increased. This study aims to compare the performance of classical Machine Learning (ML) models and Deep Learning (DL) models under varying amounts of training data, particularly focusing on altered signs to mimic real-world conditions. We evaluated three classical models: Support Vector Machine (SVM), Random Forest, and Linear Discriminant Analysis (LDA), and one Deep Learning model: Convolutional Neural Network (CNN). Using the German Traffic Sign Recognition Benchmark (GTSRB) dataset, which includes approximately 40,000 German traffic signs, we introduced digital alterations to simulate conditions such as environmental wear or vandalism. Additionally, the Histogram of Oriented Gradients (HOG) descriptor was used to assist classical models. Bayesian optimization and k-fold cross-validation were employed for model fine-tuning and performance assessment. Our findings reveal a threshold in training data beyond which accuracy plateaus. Classical models showed a linear performance decrease under increasing alteration, while CNNs, despite being more robust to alterations, did not significantly outperform classical models in overall accuracy. Ultimately, classical Machine Learning models demonstrated performance comparable to CNNs under certain conditions, suggesting that effective road sign classification can be achieved with less computationally intensive approaches. Full article

Due to the detrimental impact of fog on image quality, dehazing maritime images is essential for applications such as safe maritime navigation, surveillance, environmental monitoring, and marine research. Traditional dehazing techniques, which are dependent on presupposed conditions, often fail to perform effectively, particularly when processing sky regions within marine fog images in which these conditions are not met. This study proposes an adaptive sky area segmentation dark channel prior to the marine image dehazing method. This study effectively addresses challenges associated with traditional marine image dehazing methods, improving dehazing results affected by bright targets in the sky area and mitigating the grayish appearance caused by the dark channel. This study uses the grayscale value of the region boundary’s grayscale discontinuity characteristics, takes the grayscale value with the least number of discontinuity areas in the grayscale histogram as a segmentation threshold adapted to the characteristics of the sea fog image to segment bright areas such as the sky, and then uses grayscale gradients to identify grayscale differences in different bright areas, accurately distinguishing boundaries between sky and non-sky areas. By comparing the area parameters, non-sky blocks are filled; this adaptively eliminates interference from other bright non-sky areas and accurately locks the sky area. Furthermore, this study proposes an enhanced dark channel prior approach that optimizes transmittance locally within sky areas and globally across the image. This is achieved using a transmittance optimization algorithm combined with guided filtering technology. The atmospheric light estimation is refined through iterative adjustments, ensuring consistency in brightness between the dehazed and original images. The image reconstruction employs calculated atmospheric light and transmittance values through an atmospheric scattering model. Finally, the use of gamma-correction technology ensures that images more accurately replicate natural colors and brightness levels. Experimental outcomes demonstrate substantial improvements in the contrast, color saturation, and visual clarity of marine fog images. Additionally, a set of foggy marine image data sets is developed for monitoring purposes. Compared with traditional dark channel prior dehazing techniques, this new approach significantly improves fog removal. This advancement enhances the clarity of images obtained from maritime equipment and effectively mitigates the risk of maritime transportation accidents. Full article

Ship detection is a significant issue in remote sensing based on Synthetic Aperture Radar (SAR). This paper combines the advantages of a steady constant false alarm rate (CFAR) detector and a knowledge-oriented Gradient Boosting Decision Tree (GBDT) classifier to achieve the location and the classification of ship candidates. The steady CFAR detector smooths the image by a moving-average filter and models the probability distribution of the smoothed clutter as a Gaussian distribution. The mean and the standard deviation of the Gaussian distribution are estimated according to the left half of the histogram to remove the effect of land, ships, and other targets. From the Gaussian distribution and a preset constant false alarm rate, a threshold is obtained to segment land, ships, and other targets from the clutter. Then, a series of morphological operations are introduced to eliminate land and extract ships and other targets, and an active contour algorithm is utilized to refine ships and other targets. Finally, ships are recognized from other targets by a knowledge-oriented GBDT classifier. Based on the brain-like ship-recognition process, we change the way of the decision-tree generation and achieve a higher classification performance than the original GBDT. The results on the AIRSARShip-1.0 dataset demonstrate that this scheme has a competitive performance against deep learning, especially in the detection of offshore ships. Full article

Pedestrian crossings are an essential part of the urban landscape, providing safe passage for pedestrians to cross busy streets. While some are regulated by timed signals and are marked with signs and lights, others are simply marked on the road and do not have additional infrastructure. Nevertheless, the markings undergo wear and tear due to traffic, weather, and road maintenance activities. If pedestrian crossing markings are excessively worn, drivers may not be able to see them, which creates road safety issues. This paper presents a study of computer vision techniques that can be used to identify and classify pedestrian crossings. It first introduces the related concepts. Then, it surveys related work and categorizes existing solutions, highlighting their key features, strengths, and limitations. The most promising techniques are identified and described: Convolutional Neural Networks, Histogram of Oriented Gradients, Maximally Stable Extremal Regions, Canny Edge, and thresholding methods. Their performance is evaluated and compared on a custom dataset developed for this work. Insights on open issues and research opportunities in the field are also provided. It is shown that managers responsible for road safety, in the context of a smart city, can benefit from computer vision approaches to automate the process of determining the wear and tear of pedestrian crossings. Full article

Infrared small target detection plays a crucial role in maritime security. However, detecting small targets within heavy sea clutter environments remains challenging. Existing methods often fail to deliver satisfactory performance in the presence of substantial clutter interference. This paper analyzes the spatial–temporal appearance characteristics of small targets and sea clutter. Based on this analysis, we propose a novel detection method based on the appearance stable isotropy measure (ASIM). First, the original images are processed using the Top-Hat transformation to obtain the salient regions. Next, a preliminary threshold operation is employed to extract the candidate targets from these salient regions, forming a candidate target array image. Third, to distinguish between small targets and sea clutter, we introduce two characteristics: the gradient histogram equalization measure (GHEM) and the local optical flow consistency measure (LOFCM). GHEM evaluates the isotropy of the candidate targets by examining their gradient histogram equalization, while LOFCM assesses their appearance stability based on local optical flow consistency. To effectively combine the complementary information provided by GHEM and LOFCM, we propose ASIM as a fusion characteristic, which can effectively enhance the real target. Finally, a threshold operation is applied to determine the final targets. Experimental results demonstrate that our proposed method exhibits superior comprehensive performance compared to baseline methods. Full article

To solve the drawbacks of the Otsu image segmentation algorithm based on traditional butterfly optimization, such as slow convergence speed and poor segmentation accuracy, this paper proposes hybrid fractional-order butterfly optimization with the Otsu image segmentation algorithm. G-L-type fractional-order differentiation is combined with the algorithm’s global search to improve the position-updating method, which enhances the algorithm’s convergence speed and prevents it from falling into local optima. The sine-cosine algorithm is introduced in the local search step, and Caputo-type fractional-order differentiation is used to avoid the disadvantages of the sine-cosine algorithm and to improve the optimization accuracy of the algorithm. By dynamically converting the probability, the ratio of global search to local search is changed to attain high-efficiency and high-accuracy optimization. Based on the 2-D grayscale gradient distribution histogram, the trace of discrete matrices between classes is chosen as the fitness function, the best segmentation threshold is searched for, image segmentation is processed, and three categories of images are chosen to proceed with the segmentation test. The experimental results show that, compared with traditional butterfly optimization, the convergence rate of hybrid fractional-order butterfly optimization with the Otsu image segmentation algorithm is improved by about 73.38%; meanwhile, it has better segmentation accuracy than traditional butterfly optimization. Full article

The aim of this research was to develop a solution based on existing methods and tools that would allow the automatic classification of selected images of cast iron microstructures. As part of the work, solutions based on artificial intelligence were tested and modified. Their task is to assign a specific class in the analyzed microstructure images. In the analyzed set, the examined samples appear in various zoom levels, photo sizes and colors. As is known, the components of the microstructure are different. In the examined photo, there does not have to be only one type of precipitate in each photo that indicates the correct microstructure of the same type of alloy, different shapes may appear in different amounts. This article also addresses the issue of data preparation. In order to isolate one type of structure element, the possibilities of using methods such as HOG (histogram of oriented gradients) and thresholding (the image was transformed into black objects on a white background) were checked. In order to avoid the slow preparation of training data, our solution was proposed to facilitate the labeling of data for training. The HOG algorithm combined with SVM and random forest were used for the classification process. In order to compare the effectiveness of the operation, the Faster R-CNN and Mask R-CNN algorithms were also used. The results obtained from the classifiers were compared to the microstructure assessment performed by experts. Full article

During the service process of high-rise buildings, hollowing defects may be produced in the decorative layer, which not only affect the appearance, but also create a safety hazard of wall covering and shattered plaster peeling. Numerous studies have shown that hollowing can be detected using infrared thermal imagery under normal conditions. However, it is difficult to detect the edge and calculate the area of the hollowing on an exterior facade accurately because of the low contrast and fuzzy boundaries of the obtained infrared thermal images. To address these problems, a method for extracting the contours of building facade hollowing defects using polarization thermal images based on an improved Canny algorithm has been proposed in this paper. Firstly, the principle of thermal polarization imaging was introduced for hollowing detection. Secondly, considering the shortcomings of the Canny edge detection algorithm and the features of polarization thermal images, an improved Canny edge detection algorithm is proposed, including adaptive bilateral filtering to improve noise reduction ability while ensuring defect edges are not virtualized, Laplacian sharpening and histogram equalization to achieve contour sharpening and contrast enhancement, and eight-direction gradient templates for calculating image gradients, which make interpolation with non-maximum suppression more accurate, and the Tsallis entropy threshold segmentation algorithm based on the OTSU algorithm verification makes the image contour information more complete and accurate. Finally, a long-wave infrared polarization thermal imaging experimental platform was established and validation experiments were conducted. The experimental results demonstrate that the distinct, smooth, and precise location edges of the hollowing polarization infrared thermal images can be obtained, and the average error of the detected hollowing area is about 10% using the algorithm proposed in this paper. Full article

A brain tumor refers to an abnormal growth of cells in the brain that can be either benign or malignant. Oncologists typically use various methods such as blood or visual tests to detect brain tumors, but these approaches can be time-consuming, require additional human effort, and may not be effective in detecting small tumors. This work proposes an effective approach to brain tumor detection that combines segmentation and feature fusion. Segmentation is performed using the mayfly optimization algorithm with multilevel Kapur’s threshold technique to locate brain tumors in MRI scans. Key features are achieved from tumors employing Histogram of Oriented Gradients (HOG) and ResNet-V2, and a bidirectional long short-term memory (BiLSTM) network is used to classify tumors into three categories: pituitary, glioma, and meningioma. The suggested methodology is trained and tested on two datasets, Figshare and Harvard, achieving high accuracy, precision, recall, F1 score, and area under the curve (AUC). The results of a comparative analysis with existing DL and ML methods demonstrate that the proposed approach offers superior outcomes. This approach has the potential to improve brain tumor detection, particularly for small tumors, but further validation and testing are needed before clinical use. Full article

Tire defects are crucial for safe driving. Specialized experts or expensive tools such as stereo depth cameras and depth gages are usually used to investigate these defects. In image processing, feature extraction, reduction, and classification are presented as three challenging and symmetric ways to affect the performance of machine learning models. This paper proposes a hybrid system for cracked tire detection based on the adaptive selection of correlation features and deep belief neural networks. The proposed system has three steps: feature extraction, selection, and classification. First, the oriented gradient histogram extracts features from the tire images. Second, the proposed adaptive correlation feature selection selects important features with a threshold value adapted to the nature of the images. The last step of the system is to predict the image category based on the deep belief neural networks technique. The proposed model is tested and evaluated using real images of cracked and normal tires. The experimental results show that the proposed solution performs better than the current studies in effectively classifying tire defect images. The proposed hybrid cracked tire detection system based on adaptive correlation feature selection and Deep Belief Neural Networks’ performance provided better classification accuracy (88.90%) than that of Belief Neural Networks (81.6%) and Convolution Neural Networks (85.59%). Full article

Aiming at the problems of the blurred image defect contour and the surface texture of the aluminum strip suppressing defect feature extraction when collecting photos online in the air cushion furnace production line, we propose an algorithm for the surface defect enhancement and detection of aluminum strips based on the Retinex theory and Gobar filter. The Retinex algorithm can enhance the information and detail part of the image, while the Gobar algorithm can maintain the integrity of the defect edges well. The method first improves the high-frequency information of the image using a multi-scale Retinex based on a Laplacian filter, scales the original image and the enhanced image, and enhances the contrast of the image by adaptive histogram equalization. Then, the image is denoised, and texture suppressed using median filtering and morphological operations. Finally, Gobar edge detection is performed on the obtained sample images by convolving the sinusoidal plane wave and the Gaussian kernel function in the null domain and performing double-threshold segmentation to extract and refine the edges. The algorithm in this paper is compared with histogram equalization and the Gaussian filter-based MSR algorithm, and the surface defects of aluminum strips are significantly enhanced for the background. The experimental results show that the information entropy of the aluminum strip material defect image is improved from 5.03 to 7.85 in the original image, the average gradient of the image is improved from 3.51 to 9.51 in the original image, the contrast between the foreground and background is improved from 16.66 to 117.53 in the original image, the peak signal-to-noise ratio index is improved to 24.50 dB, and the integrity of the edges is well maintained while denoising. This paper’s algorithm effectively enhances and detects the surface defects of aluminum strips, and the edges of defect contours are clearer and more complete. Full article

Early evaluation of patients who require special care and who have high death-expectancy in COVID-19, and the effective determination of relevant biomarkers on large sample-groups are important to reduce mortality. This study aimed to reveal the routine blood-value predictors of COVID-19 mortality and to determine the lethal-risk levels of these predictors during the disease process. The dataset of the study consists of 38 routine blood-values of 2597 patients who died (n = 233) and those who recovered (n = 2364) from COVID-19 in August–December, 2021. In this study, the histogram-based gradient-boosting (HGB) model was the most successful machine-learning classifier in detecting living and deceased COVID-19 patients (with squared F1 metrics F1² = 1). The most efficient binary combinations with procalcitonin were obtained with D-dimer, ESR, D-Bil and ferritin. The HGB model operated with these feature pairs correctly detected almost all of the patients who survived and those who died (precision > 0.98, recall > 0.98, F1² > 0.98). Furthermore, in the HGB model operated with a single feature, the most efficient features were procalcitonin (F1² = 0.96) and ferritin (F1² = 0.91). In addition, according to the two-threshold approach, ferritin values between 376.2 μg/L and 396.0 μg/L (F1² = 0.91) and procalcitonin values between 0.2 μg/L and 5.2 μg/L (F1² = 0.95) were found to be fatal risk levels for COVID-19. Considering all the results, we suggest that many features combined with these features, especially procalcitonin and ferritin, operated with the HGB model, can be used to achieve very successful results in the classification of those who live, and those who die from COVID-19. Moreover, we strongly recommend that clinicians consider the critical levels we have found for procalcitonin and ferritin properties, to reduce the lethality of the COVID-19 disease. Full article

The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients (HOG) are extracted from the segmented traffic. Furthermore, a multi-class support vector machine classifier is employed to categorize different traffic vehicle types, including passenger cars, passenger trucks, motorcycles, buses, and small and large utility trucks. It handles multiple vehicle detections through an iterative k-means clustering over-segmentation process. The proposed algorithm reduced the processed data by an average of 40%. Compared to recent techniques, it showed an average improvement of 15% in segmentation accuracy, and it is 55% faster than the compared segmentation techniques on average. Moreover, a comparative analysis of 23 different deep learning architectures is presented. The resulting algorithm outperformed the compared deep learning algorithms for the quality of vehicle classification accuracy. Furthermore, the timing analysis showed that it could operate in real-time scenarios. Full article

The article discusses the problem of detecting sick or mechanically damaged potatoes using machine learning methods. We proposed an algorithm and developed a system for the rapid detection of damaged tubers. The system can be installed on a conveyor belt in a vegetable store, and it consists of a laptop computer and an action camera, synchronized with a flashlight system. The algorithm consists of two phases. The first phase uses the Viola-Jones algorithm, applied to the filtered action camera image, so it aims to detect separate potato tubers on the conveyor belt. The second phase is the application of a method that we choose based on video capturing conditions. To isolate potatoes infected with certain types of diseases (dry rot, for example), we use the Scale Invariant Feature Transform (SIFT)—Support Vector Machine (SVM) method. In case of inconsistent or weak lighting, the histogram of oriented gradients (HOG)—Bag-of-Visual-Words (BOVW)—neural network (BPNN) method is used. Otherwise, Otsu’s threshold binarization—a convolutional neural network (CNN) method is used. The first phase’s result depends on the conveyor’s speed, the density of tubers on the conveyor, and the accuracy of the video system. With the optimal setting, the result reaches 97%. The second phase’s outcome depends on the method and varies from 80% to 97%. When evaluating the performance of the system, it was found that it allows to detect and classify up to 100 tubers in one second, which significantly exceeds the performance of most similar systems. Full article

Photovoltaic monitoring data are the primary source for studying photovoltaic plant behavior. In particular, performance loss and remaining-useful-lifetime calculations rely on trustful input data. Furthermore, a regular stream of high quality is the basis for pro-active operation and management activities which ensure a smooth operation of PV plants. The raw data under investigation are electrical measurements and usually meteorological data such as in-plane irradiance and temperature. Usually, performance analyses follow a strict pattern of checking input data quality followed by the application of appropriate filter, choosing a key performance indicator and the application of certain methodologies to receive a final result. In this context, this paper focuses on four main objectives. We present common photovoltaics monitoring data quality issues, provide visual guidelines on how to detect and evaluate these, provide new data imputation approaches, and discuss common filtering approaches. Data imputation techniques for module temperature and irradiance data are discussed and compared to classical approaches. This work is intended to be a soft introduction into PV monitoring data analysis discussing best practices and issues an analyst might face. It was seen that if a sufficient amount of training data is available, multivariate adaptive regression splines yields good results for module temperature imputation while histogram-based gradient boosting regression outperforms classical approaches for in-plane irradiance transposition. Based on tested filtering procedures, it is believed that standards should be developed including relatively low irradiance thresholds together with strict power-irradiance pair filters. Full article