Object Image Classification Research Articles

Computer Vision Application Analysis based on Object Detection

Object detection is a computer vision method that allows for the identification and localization of specific classes of objects in images or videos. It goes beyond simple object classification and helps provide a better understanding of the object in question. Object detection has numerous applications, including automating business processes like inventory management in retail [1]. It can detect objects that occupy between 2% and 60% of an image's area and clusters of objects as a single entity. Additionally, it can localize objects at high speeds, typically greater than 15 frames per second. Vehicle detection is a crucial component in the development of autonomous vehicles, enabling them to identify and perceive objects in their environment. It involves identifying and locating vehicles in image or video frames and has various applications in surveillance and security systems. There are different techniques and models for object detection, including traditional image processing methods and modern deep learning networks. Traditional methods like Viola-Jones, SIFT, and histogram of oriented gradients do not require historical data for training and are unsupervised. Popular image processing tools like OpenCV can be used for these techniques. On the other hand, modern deep learning networks like CNN, RCNN, YOLO, ResNet, RetinaNet, and MANet are supervised and efficient for object detection. Key Words: Deep learning, OpenCV, object detection

Computer Vision Applications In Construction And Asset Management Phases: A Literature Review

Recent advances in digital photography and unmanned aerial vehicle (UAV) platforms make visual data from construction project sites more accessible to project teams. To semi-automatically or automatically obtain the essential information, evaluate the ongoing activities or operations, and address project-level challenges, researchers have focused on applying various computer vision (CV)-based methods to process and interpret the acquired visual data. This research developed a framework to summarize the vision-based methods that have been applied to construction/asset management operations through a systematic literature review. The reviewed literature was composed of 103 journal papers from 2011 to 2020. All the reviewed journal papers were from the Ei Compendex database with specific search criteria. The developed framework consisted of two parts: use cases and CV domains. Use cases contained five aspects: safety monitoring, productivity improvement, progress monitoring, infrastructure inspection, and robotic application. CV domains contained six aspects: image processing, object classification, object detection, object tracking, pose estimation, and 3D reconstruction. All eleven aspects were integrated from the reviewed papers. For each reviewed paper, the general workflow of applied vision-based approaches was described and categorized into each use case. A trending timeline was developed to analyze the popularity of the identified use cases and CV domains within the reviewed time period. Both the quantity and variety of construction use cases and CV domains have increased. Challenges and limitations of applying CV-based methods in the construction industry were also identified. This paper provides readers with a summary of how CV-based methods have been used in the construction industry and serve as a reference for future research and development.

Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion

To identify and classify objects on images obtained using UAV imaging and orbital-based imaging, a neural network classification model based on the use of an autoencoder and built on the architecture of an ensemble of multilayer perceptrons is proposed. Additionally, at the stage of highlighting informative features, is added a color information, which is based on the per-channel histograms and is invariant to the scale and rotations of the image. The model is implemented using the Keras library. The use of the proposed model for classification into four classes: “Fire”, “Smoke”, “Vegetation” and “Buildings”, allows to achieve a classification accuracy above 99%.

Achieving Lightweight and Privacy-Preserving Object Detection for Connected Autonomous Vehicles

Connected autonomous vehicles (CAVs) are capable of capturing high-definition images from onboard sensors, which can be used to facilitate the detection of objects in the vicinity. Such images may, however, contain sensitive information (e.g., human faces and license plates) as well as the indirect location of CAVs. To protect the object privacy of images shared by CAVs, this article proposes a privacy-preserving object detection (P2OD) framework. Specifically, we propose multiple secure computing protocols designed to construct a privacy-preserving Faster <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> -convolutional neural network (CNN) model to securely extract features and bounding-boxes of objects in an image. By leveraging edge computing (with higher performance computation and lower latency, in comparison to cloud-based solutions), CAVs randomly split the captured images and upload them to two noncollusive edge servers. Both servers will then perform the P2OD framework cooperatively to directly detect objects over random image shares without exposing sensitive information. The theoretical analysis demonstrates the security, correctness, and efficiency of the P2OD framework, and the experimental findings show that the P2OD framework can effectively protect the classification and location privacy of image objects for CAVs. Compared with the original Faster R-CNN model, the classification and regression errors of the P2OD framework can be controlled within 10−12 and 10−14, respectively.

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

With the development of deep learning techniques, convolutional neural networks (CNN) are increasingly being used in image recognition for marine surveys and underwater object classification. Automatic recognition of targets on side-scan sonar (SSS) images using CNN can improve recognition accuracy and efficiency. However, the vast selection of CNN models makes it challenging to select models for target recognition in SSS images. Therefore, this paper aims to compare different CNN models’ prediction accuracy and computational performance comprehensively. First, four traditional CNN models were applied to train and predict the same submarine SSS dataset using both the original model and models with transfer learning methods. Then, we examined and studied the prediction accuracy and computation performance of four CNN models. Results showed that transfer learning enhances the accuracy of all CNN models, with lesser improvements for AlexNet and VGG-16 and greater improvements for GoogleNet and ResNet101. GoogleNet has the highest prediction of accuracy (100% in the train dataset and 94.27% in the test dataset) and good computational difficulty. The findings of this work are useful for future model selection in target recognition in SSS images.

АЛГОРИТМ ФОРМУВАННЯ НАБОРУ АПРІОРНИХ ДАНИХ НЕЙРОННОЇ МЕРЕЖІ ДЛЯ ОБРОБКИ ЦИФРОВИХ АЕРОЗНІМКІВ

Analysis of the use of unmanned aerial systems in the combat zone indicates a constant increase in the requirements for intelligence data. One of the ways to increase the effectiveness of UaV application is the use of artificial intelligence methods. The basis for building a reliable neural network model is a large amount of various data, which helps to more accurately summarize information about the given task. The article considers an approach for increasing the accuracy of object image classification by convolutional neural networks based on data augmentation, which differs from existing ones in its adaptation to shooting factors and the specificity of aerial reconnaissance objects. An important and most time-consuming step in building an accurate machine learning model is finding and annotating the data that will be used to train and test the accuracy of the neural network. The accuracy and stability of the network in real conditions depends on the amount of collected data. To date, such methods of object image augmentation as geometric transformations, color correction, and spatial image filtering have been well described and analyzed. The possibilities of optimal combinations of data augmentation methods to achieve the desired generalization of poorly visible invariant features of objects remain unexplored at the moment. Taking into account the conducted research, an approach was proposed for the formation of a set of a priori data of a neural network for object recognition on digital aerial photographs, which will significantly reduce the complexity of the process of collecting the necessary data and replace it with magnification methods that are much simpler, consume less computing resources, and increase the accuracy of work convolutional neural networks, simulation of the use of the proposed approach was carried out. Keywords: unmanned aerial vehicle; convolutional neural network; data augmentation; automated processing of digital aerial photographs.

AWGN Removal Using Modified Steering Kernel and Image Matching

Image noise occurs during acquisition and transmission and adversely affects processes, such as image segmentation and object recognition and classification. Various techniques are being studied for noise removal, and with the recent development of hardware and image processing algorithms, noise removal techniques that combine non-local techniques are attracting attention. However, one disadvantage of this method is that blurring occurs in the edges and boundary line of the resulting image. In this study, we proposed a modified local steering kernel based on image matching to improve these shortcomings. The proposed technique uses image matching to differentiate the weight obtained by the steering kernel according to the local characteristics of the image and calculates the weight of the filter based on the similarity between the center window and the matching window. The resulting images were quantitatively evaluation and enlargement of images were used and compared with the existing noise removal algorithms. The proposed algorithm showed clearer contrast in the enlarged images and better results than the conventional image restoration techniques in the quantitative evaluation using peak signal-to-noise ratio and structural similarity index.

Computer Vision: Classification of Images Based On Deep Learning with the CNN Architecture Model

Deep learning is a scientific field in Machine Learning (ML) that is developing with various applications, one of which is visual image processing technology. With the excellent capabilities of computer vision, image processing from computer visuals is used to duplicate the human ability to understand object information in the image. One of the Machine Learning (ML) methods that can be used for object classification in images is the Convolution Neural Network (CNN) method. The two core stages when processing object classification in the image, the first stage is image classification using feedforward, and the second stage applies the backpropagation method. In this study, before the classification stage, this method was first carried out through preprocessing, which is useful as an image separation to focus on the object to be classified. Furthermore, it is carried out by conducting pre-training using the feedforward method with the bias weights, which are updated after every training process. The observations of this study, the results of image classification training with a degree of ambiguity, resulted in a good average accuracy validation value of 0.91 in a confidence interval with a range of 0-1. So, it can be concluded that applying the Convolution Neural Network (CNN) method to distinguish objects in an image can classify them well.

Ship Classification in Synthetic Aperture Radar Images Based on Multiple Classifiers Ensemble Learning and Automatic Identification System Data Transfer Learning

With the continuous development of earth observation technology, space-based synthetic aperture radar (SAR) has become an important source of information for maritime surveillance, and ship classification in SAR images has also become a hot research direction in the field of maritime ship monitoring. In recent years, the remote sensing community has proposed several solutions to the problem of ship object classification in SAR images. However, it is difficult to obtain an adequate amount of labeled SAR samples for training classifiers, which limits the application of machine learning, particularly deep learning methods, in SAR image ship object classification. In contrast, as a real-time automatic tracking system for monitoring ships at sea, a ship automatic identification system (AIS) can provide a large amount of relatively easy-to-obtain labeled ship samples. Therefore, to solve the problem of SAR image ship classification and improve the classification performance of learning models with limited samples, we proposed a SAR image ship classification method based on multiple classifiers ensemble learning (MCEL) and AIS data transfer learning. The core idea of our method is to transfer the MCEL model trained on AIS data to SAR image ship classification, which mainly includes three steps: first, we use the acquired global space-based AIS data to build a dataset for ship object classification models training; then, the ensemble learning model is constructed by combining multiple base classifiers; and finally, the trained classification model is transferred to SAR images for ship type prediction. Experiments show that the proposed method achieves a classification accuracy of 85.00% for the SAR ship classification, which is better than the performance of each base classifier. This proves that AIS data transfer learning can effectively solve the problem of SAR ship classification with limited samples, and has important application value in maritime surveillance.

ID-NET:INCEPTION DECONVOLUTIONAL NEURAL NETWORK FOR MULTI-CLASS CLASSIFICATION IN RETINAL FUNDUS IMAGE

Micro-aneurysms, hemorrhages, and hard exudates are the early lesions of diabetic retinopathy, with micro-aneurysms and small hemorrhages appearing as small and multi-size objects in the retinal fundus image. Though it is essentially a promising technique for object classification in images, the deep learning method needs specific investigation for dealing with retinal fundus images. To this, we propose an inception deconvolutional network, dubbed ID-Net, for multi-class object classification. The ID-Net consists of two inception modules, one with a series of convolutional filters used for extracting multi-scale features and the other with a stack of deconvolutional filters for recovering the features and thus increasing the feature representation capability. As a result, the proposed network succeeds in overcoming the under-fitting and representational bottlenecks, two challenges caused by imbalanced data of retinal fundus images. Experimental results show that the ID-Net can accurately classify early lesions, and achieves higher sensitivity and accuracy than the state-of-the-art evaluation on the public database.

Virtual Underwater Datasets for Autonomous Inspections

Underwater Vehicles have become more sophisticated, driven by the off-shore sector and the scientific community’s rapid advancements in underwater operations. Notably, many underwater tasks, including the assessment of subsea infrastructure, are performed with the assistance of Autonomous Underwater Vehicles (AUVs). There have been recent breakthroughs in Artificial Intelligence (AI) and, notably, Deep Learning (DL) models and applications, which have widespread usage in a variety of fields, including aerial unmanned vehicles, autonomous car navigation, and other applications. However, they are not as prevalent in underwater applications due to the difficulty of obtaining underwater datasets for a specific application. In this sense, the current study utilises recent advancements in the area of DL to construct a bespoke dataset generated from photographs of items captured in a laboratory environment. Generative Adversarial Networks (GANs) were utilised to translate the laboratory object dataset into the underwater domain by combining the collected images with photographs containing the underwater environment. The findings demonstrated the feasibility of creating such a dataset, since the resulting images closely resembled the real underwater environment when compared with real-world underwater ship hull images. Therefore, the artificial datasets of the underwater environment can overcome the difficulties arising from the limited access to real-world underwater images and are used to enhance underwater operations through underwater object image classification and detection.

Improvement of Multiclass Classification of Pavement Objects Using Intensity and Range Images

Automated recognition of road surface objects is vital for efficient and reliable road condition assessment. Despite recent advances in developing computer vision algorithms, it is still challenging to analyze road images due to the low contrast, background noises, object diversity, and variety of lighting conditions. Motivated by the need for an improved pavement objects classification, we present Dual Attention Convolutional Neural Network (DACNN) to improve the performance of multiclass classification using intensity and range images collected with 3D laser imaging devices. DACNN fuses heterogeneous information in intensity and range images to enhance distinguishing foreground from background, as well as to improve object classification in noisy images under various illumination conditions. DACNN also leverages multiscale input images by capturing contextual information for object classification with different sizes and shapes. DACNN contains an attention mechanism that (i) considers semantic interdependencies in spatial and channel dimensions and (ii) adaptively fuses scale-specific and mode-specific features so that each feature has its own level of contribution to the final decision. As a practical engineering project, dataset are collected from road surfaces using 3D laser imaging. DACNN is compared with four deep classifiers that are widely used in transportation applications. Experiments show that DACNN consistently outperforms the baselines by 22–35% on average in terms of the F-score. A comprehensive discussion is also presented regarding computational costs and how robustly the investigated classifiers perform on each road object.

Using a neural network in the second stage of the ensemble classifier to improve the quality of classification of objects in images

Object recognition in images is used in many areas of practical use. Very often, progress in its application largely depends on the ratio of the quality of object recognition and the required amount of calculations. Recent advances in recognition are related to the development of neural network architectures with a very significant amount of computing that are trained on large data sets over a very long time on state-of-the-art computers. For many practical applications, it is not possible to collect such large datasets for training and only computing machines with limited computing power can be used. Therefore, the search for solutions that meet these practical restrictions is relevant. This paper reports an ensemble classifier, which uses stacking in the second stage. The use of significantly different classifiers in the first stage and the multilayer perceptron in the second stage has made it possible to significantly improve the ratio of the quality of classification and the required volume of calculations when training on small data sets. The current study showed that the use of a multilayer perceptron in the second stage makes it possible to reduce the error compared to the use of the second stage of majority voting. On the MNIST dataset, the error reduction was 29‒39 %. On the CIFAR-10 dataset, the error reduction was 13‒17 %. A comparison of the proposed architecture of the ensemble classifier with the architecture of the transformer-type classifier demonstrated a decrease in the volume of calculations while reducing the error. For the CIFAR-10 dataset, an error reduction of 8 % was achieved with a calculation volume of less than 22 times. For the MNIST dataset, the error reduction was 62 % when winning by the volume of calculations by 50 times

OBJECT-BASED APPROACHES FOR LAND USE-LAND COVER CLASSIFICATION USING HIGH RESOLUTION QUICK BIRD SATELLITE IMAGERY (A CASE STUDY: KERBELA, IRAQ)

Land Use / Land Cover (LULC) classification is considered one of the basic tasks that decision makers and map makers rely on to evaluate the infrastructure, using different types of satellite data, despite the large spectral difference or overlap in the spectra in the same land cover in addition to the problem of aberration and the degree of inclination of the images that may be negatively affect rating performance. The main objective of this study is to develop a working method for classifying the land cover using high-resolution satellite images using object based method. Maximum likelihood pixel based supervised as well as object approaches were examined on QuickBird satellite image in Karbala, Iraq. This study illustrated that use of textural data during the object image classification approach can considerably enhance land use classification performance. Moreover, the results showed higher overall accuracy (86.02%) in the o object based method than pixel based (79.06%) in urban extractions. The object based performed much more capabilities than pixel based.

U19-Net: a deep learning approach for obstacle detection in self-driving cars

Development of self-driving cars aims to drive safely from one point to another in a coordinated system where an on-board system should react and possibly alert drivers about the driving environments and possible collisions that may arise between drivers and obstacles. There are many deep learning approaches available for obstacle detection especially convolutional neural networks (CNNs) with improvement accuracy, and encoder–decoder networks are CNNs with a current attraction for researchers mainly because these models provide better results than classical statistical models for image segmentation and object classification tasks. This work proposes U19-Net an encoder–decoder deep model that explores the deep layers of a VGG19 model as an encoder following a symmetrical approach with an U-Net decoder designed for pixel-wise classifications. The U19-Net has end-to-end learning successfully effectiveness for the vehicle and pedestrian detection within the open-source Udacity dataset showing an IoU score of 87.08 and 78.18%, respectively. The proposed U19-Net is compared with five recent CNN networks using the AP metric, obtaining near results (less than 5%) for the faster R-CNN, one of the most commonly used networks for object detection.

Classification of objects in images with distortions based on a two-stage topological analysis

The authors propose a method for automatic classification of spatial objects in images under conditions of a limited data set. The stability of the method to distortions appearing in images due to natural phenomena and partial overlap of urban infrastructure objects is investigated. High classification accuracy, when using existing approaches, requires a large training sample, including data sets with distortions, which significantly increases computational complexity. The paper proposes a method for a two-step topological analysis of images. Topological features are initially extracted by analyzing the image in the brightness range from 0 to 255, and then from 255 to 0. These features complement each other and reflect the topological structure of the object. Under certain deformations and distortions, the object preserves its structure in the form of extracted features. The advantage of the method is a small number of patterns, which reduces the computational complexity of training compared to neural networks. The proposed method is investigated and compared with the modern neural network approach. The study was performed on a DOTA dataset (Dataset for Object deTection in Aerial images) containing images of spatial objects of several classes. In the absence of distortion in the image, the neural network approach showed a classification accuracy of over 98 %, while the proposed method achieved about 82 %. Further distortions such as 90 degree rotation, 50 % narrowing and 50 % edge truncation and their combinations were applied in the experiment. The proposed method showed its robustness and outperformed the neural network approach. In the most difficult combination of the test, the decrease in classification accuracy of the neural network was 46 %, while the described method showed 12 %. The proposed method can be applied in cases with a high probability of distortion in the images. Such distortions arise in the field of geoinformatics when analyzing objects of various scales, under different weather conditions, partial overlap of one object with another, in the presence of shadows, etc. It is possible to use the proposed method in vision systems of industrial enterprises for automatic classification of the parts that belong to superimposed objects.

Feature Balance for Fine-Grained Object Classification in Aerial Images

Fine-grained object classification (FGOC) focuses on identifying subcategories of objects, which is crucial in military and civilian. Existing FGOC methods primarily focus on high-resolution aerial images, limiting their application on low-resolution (LR) FGOC that is a more realistic setting, especially on resource-constrained satellite devices. It is more challenging to deal with LR FGOC since objects’ details are blurred or missing. Addressing this issue, we make the first attempt to explore LR FGOC and propose a novel pipeline based on two technical insights: 1) feature balance strategy discriminatively integrates super-resolution weak and strong detailed presentations into coarse features of LR aerial images, achieving a feature balance to avoid that the weak detailed presentations are inhibited by the strong ones and 2) iterative interaction mechanism alternately refines feature details of the discriminative ship regions and optimizes the performance of FGOC. Moreover, we build a low-resolution fine-grained object (LFS) dataset to promote further study and evaluation. Extensive experiments on the proposed LFS dataset and the other three object datasets of DOTA, FS23, and HRSC2016 demonstrate that our method outperforms state-of-the-art algorithms. Dataset and code are publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/wdzhao123/FBNet</uri> .

Survey on deep learning applications in digital image security

In the digital era, sharing pictures on social media has become a common privacy issue. To prevent private images from being eavesdropped on and destroyed, developing secure and efficient image steganography, image cryptography, and image authentication has been difficult. Deep learning provides a solution for digital image security. First, we make an overall conclusion on deep learning applications in image steganography to generate five aspects: the cover image, stego-image, embedding change probabilities, coverless steganography, and steganalysis. Second, we also combine and compare deep learning methods used in six aspects: image cryptography from image compression, image resolution improvement, image object detection and classification, key generation, end-to-end image encryption, and image cryptoanalysis. Third, we collect deep learning methods in image authentication from five perspectives: image forgery detection, watermarked image generation, image watermark extraction and detection, image watermarking attack, and image watermark removal. Finally, we summarize future research directions of deep learning utilization in image steganography, image cryptography, and image authentication.

To the question about remote sensing of the earth for precision farming tasks and assessment of the consequences of techno-environmental events

Some issues of the use of unmanned aircraft and space vehicles in monitoring the consequences of technical and environmental events and precision farming are considered. The proposed technology is aimed at improving the recognition accuracy of infrastructure objects with obtaining the numerical values of their 3D coordinates. The aim of the research is to improve the quality of monitoring using neural network identification and classification of objects in multi-zone satellite images obtained from unmanned aerial vehicles (UAV). Research includes both theoretical research and applied problem solving. The mathematical basis of image processing is the image recognition computer. Practical research is based on experimentation, software implementation, testing of algorithms and technology. An effective method of video surveillance of the territory has been improved. The task of the authors' research is to improve the accuracy of objects recognition on the earth's surface (specific infrastructure objects, the sky, the state of vegetation of agricultural land). The authors have experience in this area. The solution to this problem occurs simultaneously in two directions. The first direction: the technical result is ensured by the fact that the technology offers the use of a UAV equipped with two video cameras. The second direction is the use of scientific idea consisting in the development of a method for joint computer processing of digital and analog images obtained from UAVs, as well as quasi-simultaneous and reusable multi-zone satellite images. A new result of the research is the developed data structure for storing the model of the recognition process, which allows to jointly save dissimilar characteristics and membership functions of different types in the same tables

Deep Learning for Convolution Neural Networks and Recurrent Neural Networks: A Review

Many with computational models that allow deep learning representations to learn to make processing layers. Summary of multiple levels with information. These methods have dramatically improved many fields like speech recognition, visual material detection, substance recognition and drug discovery, and genetics. (1) Deep machine learning uses back-propagation algorithms to understand how the wild machine detects complexity structures in large data sets. Deep transformation networks exist advances have come in image processing, video, speech, and sound, while continuous networks. Deep learning is the latest, cutting-edge technology Image processing and data analysis, reliable results and large capacity. Deep learning has been successfully used in various domains, including recently agricultural sector as well. In this paper, we review 40 research initiatives using Deep learning techniques are applied to various agricultural and food production challenges. (2) We examine specific agricultural study problems, the specific models and frameworks used as sources, the nature and data pre processing used, and the metrics used to measure overall performance as stated of each study task. A subset of deep learning algorithms are machine learning algorithms that are distributed representations with multilevel detection. Recently, contribute challenges to more than 210 recent research papers. (3) This book describes advances in implementing deep neural networks for automatic feature extraction in applications including image and video face recognition, programmatic video highlighting, and image segmentation and object classification. (4)Image recognition is a popular idea in transfer learning and its beginnings. Basically pre-trained models can be some type of reproducible classification applications using images on small datasets. We practice different architectures learning only a small number of calculations weights and residuals. Ideally, the network's weights can predict 95% accuracy without loss. (5) Apart from these and other findings, in this article, the authors present define surface and deep learning and describe observed system. Learning outcome taxonomy is used to assess depth.