Problem In Computer Vision Research Articles

Transforming image descriptions as a set of descriptors to construct classification features

<span>The article develops methods to solve a fundamental problem in computer vision: image recognition of visual objects. The results of the research on the construction of modifications for the space of classification features based on the application of the transformation of the structural description through the decomposition in the orthogonal basis and the implementation of the distance matrix model between the components of the description are presented. The application of the system of orthogonal functions as an apparatus for the transformation of the description showed the possibility of a significant gain in the speed of processing while maintaining high indicators of classification accuracy and interference resistance. The synthesized feature systems’ effectiveness has been confirmed in terms of a significant increase in the rate of codes and a sufficient level of efficiency. An experimental example showed that the time spent calculating the relevance of descriptions according to their modified presentation is more than ten times shorter than for traditional metric approaches. The developed classification features can be used in applied tasks where the time of visual objects’ identification is critical.</span>

Multiscale Deep Learning for Detection and Recognition: A Comprehensive Survey.

Recently, the multiscale problem in computer vision has gradually attracted people's attention. This article focuses on multiscale representation for object detection and recognition, comprehensively introduces the development of multiscale deep learning, and constructs an easy-to-understand, but powerful knowledge structure. First, we give the definition of scale, explain the multiscale mechanism of human vision, and then lead to the multiscale problem discussed in computer vision. Second, advanced multiscale representation methods are introduced, including pyramid representation, scale-space representation, and multiscale geometric representation. Third, the theory of multiscale deep learning is presented, which mainly discusses the multiscale modeling in convolutional neural networks (CNNs) and Vision Transformers (ViTs). Fourth, we compare the performance of multiple multiscale methods on different tasks, illustrating the effectiveness of different multiscale structural designs. Finally, based on the in-depth understanding of the existing methods, we point out several open issues and future directions for multiscale deep learning.

A Contour-Based Feature Extraction Algorithm

Human body recognition is a common problem in computer vision. Currently, most artificial intelligence methods are dependent on the scale of the extracted feature values from the target images during classification, thereby limiting the image size. However, in image recognition, the object’s contour alone is sufficient for humans to distinguish image content. This paper proposes a feature extraction algorithm based on image contours. By utilizing only the contour features of the target image and combining them with machine learning algorithms for classification, it achieves good results even on relatively complex images.

EC-SfM: Efficient Covisibility-Based Structure-From-Motion for Both Sequential and Unordered Images

Structure-from-Motion is a technology used to obtain scene structure through image collection, which is a fundamental problem in computer vision. For unordered Internet images, SfM is very slow due to the lack of prior knowledge about image overlap. For sequential images, knowing the large overlap between adjacent frames, SfM can adopt a variety of acceleration strategies, which are only applicable to sequential data. To further improve the reconstruction efficiency and break the gap of strategies between these two kinds of data, this paper presents an efficient covisibility-based incremental SfM. Different from previous methods, we exploit covisibility and registration dependency to describe the image connection which is suitable to any kind of data. Based on this general image connection, we propose a unified framework to efficiently reconstruct sequential images, unordered images, and the mixture of these two. Experiments on the unordered images and mixed data verify the effectiveness of the proposed method, which is three times faster than the state-of-the-art on feature matching, and an order of magnitude faster on reconstruction without sacrificing the accuracy. The source code is publicly available at https://github.com/openxrlab/xrsfm.

AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes.

Multiobject tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender, hairstyle, body shape, and clothing features, which contain rich and high-level information, have been less explored. To address this gap, we propose a simple, effective, and generic method to predict pedestrian attributes to support general reidentification (Re-ID) embedding. We first introduce attribute multi-object tracking (AttMOT), a large, highly enriched synthetic dataset for pedestrian tracking, containing over 80k frames and six million pedestrian identity switches (IDs) with different times, weather conditions, and scenarios. To the best of authors' knowledge, AttMOT is the first MOT dataset with semantic attributes. Subsequently, we explore different approaches to fuse Re-ID embedding and pedestrian attributes, including attention mechanisms, which we hope will stimulate the development of attribute-assisted MOT. The proposed method attribute-assisted method (AAM) demonstrates its effectiveness and generality on several representative pedestrian MOT benchmarks, including MOT17 and MOT20, through experiments on the AttMOT dataset. When applied to the state-of-the-art trackers, AAM achieves consistent improvements in multi-object tracking accuracy (MOTA), higher order tracking accuracy (HOTA), association accuracy (AssA), IDs, and IDF1 scores. For instance, on MOT17, the proposed method yields a + 1.1 MOTA, + 1.7 HOTA, and + 1.8 IDF1 improvement when used with FairMOT. To further encourage related research, we release the data and code at https://github.com/HengLan/AttMOT.

Study on the explainability of deep learning models for time series analysis in sheet metal forming

In recent research, force signals have been utilized to estimate the wear of tool components in sheet metal processing using, e.g., artificial neural networks (ANNs). ANNs learn predictive models from raw time series signals without requiring prior knowledge and manual feature engineering. However, ANNs are black-box models. Existing research on explainable AI provides methods to increase the transparency of ANNs, but mainly focusses on computer vision problems. This publication proposes an approach to learn explainable ANNs for time series data. The presented approach is applied to a tool wear prediction task using force signals from a fine blanking machine.

Understanding Adversarial Atmospheric Features Interpretation, Analysis, and Standardization for Tackling the Computer Vision Problems in Videos

Understanding Adversarial Atmospheric Features Interpretation, Analysis, and Standardization for Tackling the Computer Vision Problems in Videos

Exploring the Application of Large-Scale Pre-Trained Models on Adverse Weather Removal.

Image restoration under adverse weather conditions (e.g., rain, snow, and haze) is a fundamental computer vision problem that has important implications for various downstream applications. Distinct from early methods that are specially designed for specific types of weather, recent works tend to simultaneously remove various adverse weather effects based on either spatial feature representation learning or semantic information embedding. Inspired by various successful applications incorporating large-scale pre-trained models (e.g., CLIP), in this paper, we explore their potential benefits for leveraging large-scale pre-trained models in this task based on both spatial feature representation learning and semantic information embedding aspects: 1) spatial feature representation learning, we design a Spatially Adaptive Residual (SAR) encoder to adaptively extract degraded areas. To facilitate training of this model, we propose a Soft Residual Distillation (CLIP-SRD) strategy to transfer spatial knowledge from CLIP between clean and adverse weather images; 2) semantic information embedding, we propose a CLIP Weather Prior (CWP) embedding module to enable the network to adaptively respond to different weather conditions. This module integrates the sample-specific weather priors extracted by the CLIP image encoder with the distribution-specific information (as learned by a set of parameters) and embeds these elements using a cross-attention mechanism. Extensive experiments demonstrate that our proposed method can achieve state-of-the-art performance under various and severe adverse weather conditions. The code will be made available.

SEF-UNet: advancing abdominal multi-organ segmentation with SEFormer and depthwise cascaded upsampling.

The abdomen houses multiple vital organs, which are associated with various diseases posing significant risks to human health. Early detection of abdominal organ conditions allows for timely intervention and treatment, preventing deterioration of patients' health. Segmenting abdominal organs aids physicians in more accurately diagnosing organ lesions. However, the anatomical structures of abdominal organs are relatively complex, with organs overlapping each other, sharing similar features, thereby presenting challenges for segmentation tasks. In real medical scenarios, models must demonstrate real-time and low-latency features, necessitating an improvement in segmentation accuracy while minimizing the number of parameters. Researchers have developed various methods for abdominal organ segmentation, ranging from convolutional neural networks (CNNs) to Transformers. However, these methods often encounter difficulties in accurately identifying organ segmentation boundaries. MetaFormer abstracts the framework of Transformers, excluding the multi-head Self-Attention, offering a new perspective for solving computer vision problems and overcoming the limitations of Vision Transformers and CNN backbone networks. To further enhance segmentation effectiveness, we propose a U-shaped network, integrating SEFormer and depthwise cascaded upsampling (dCUP) as the encoder and decoder, respectively, into the UNet structure, named SEF-UNet. SEFormer combines Squeeze-and-Excitation modules with depthwise separable convolutions, instantiating the MetaFormer framework, enhancing the capture of local details and texture information, thereby improving edge segmentation accuracy. dCUP further integrates shallow and deep information layers during the upsampling process. Our model significantly improves segmentation accuracy while reducing the parameter count and exhibits superior performance in segmenting organ edges that overlap each other, thereby offering potential deployment in real medical scenarios.

Suspicious Activity Detection

Abstract: Unpredictable activities is guessing a person's physical location or joint activity based on images or videos. The project will require the use of neural networks to detect human activities from CCTV images. Human behavior is one of the fundamental problems in computer vision and has been studied for over 15 years. This is important because the number of applications that can benefit from the search function is huge. For example, it is used in applications such as human prediction, video analysis, animal analysis and behavior understanding, language recognition, human relations-computer, and characters are less powerful. While low-cost depth sensors have limitations such as being limited to indoor use, their low-noise data and low depth make it difficult to estimate humans from depth images. Therefore, we plan to use neural networks to solve these problems. Analyzing human activity through image analysis is an active area of research in image processing and computer vision. Thanks to visual monitoring, human activities in public places such as bus stops, train stations, airports, banks, shopping malls, schools, parking lots and roads can be monitored in order to prevent attacks, theft, accidents, illegal parking, violence, fights and chain events. purse snatching etc. illegal and other activities. It is very difficult to monitor public places regularly, so there is a need for intelligent video surveillance that can monitor people's activities in real time and divide them into tasks, normal and abnormal activities; and can generate an alarm. Often research is done with images rather than video. Also, none of the published articles attempt to use CNNs to detect suspicious activity.

Shape classification using a new shape descriptor and multi-view learning

Shape classification is considered as a vital task in solving many computer vision problems. Different factors such as affine transformations, scaling, rotations, variation in perspective, noise and occlusion have made the shape classification problem to be a hard problem. This work investigates a new shape descriptor that extracts different features from each boundary pixel. This makes it to be more informative and discriminant in comparison with other descriptors. After feature extraction, the “bag-of-features (BoF)” model is employed to construct the final representation for each image. To enhance the functionality of the BoF model, a novel codebook generation approach is presented. The proposed approach tends to derive a more meaningful visual codebook. Consequently, the produced feature vectors can handle inter- and intra-class variations more effectively. Comprehensive experiments conducted on the various complicated shape datasets show the supremacy of our approach compared to other methods.

Multimodel fore-/background alignment for seam-based parallax-tolerant image stitching

Image stitching with large parallax is a challenging computer vision problem. Although existing seam-based approaches were proposed to achieve pleasing results, issues like object dislocation, disappearance, and duplication can still occur. In this paper, to alleviate these problems, we propose a novel seam-based parallax-tolerant image stitching method, which relies on accurately aligning background and foreground regions using multiple warping models. To estimate various spatially smooth models based on feature correspondences from depth-varying objects, we introduce an iterative algorithm that selects inliers and solves the mesh warping model by assigning weights to data. Additionally, we construct matching confidences of foreground pixels based on selecting and grouping unaligned feature pairs, thus penalizing the duplication of seam cuts. To further improve alignment, we refine the models by minimizing pixel-level errors. We then choose the best seam among multiple candidate alignment and seam finding solutions. Finally, we re-estimate the warping model by sampling and weighting points near the seam to achieve a natural-looking stitching result. Experimental results on real-world images demonstrate the effectiveness and superiority of our proposed method over other state-of-the-arts.

DetTrack: An Algorithm for Multiple Object Tracking by Improving Occlusion Object Detection

Multi-object tracking (MOT) is an important problem in computer vision that has a wide range of applications. Currently, object occlusion detecting is still a serious challenge in multi-object tracking tasks. In this paper, we propose a method to simultaneously improve occluded object detection and occluded object tracking, as well as propose a tracking method for when the object is completely occluded. First, motion track prediction is utilized to improve the upper limit of occluded object detection. Then, the spatio-temporal feature information between the object and the surrounding environment is used for multi-object tracking. Finally, we use the hypothesis frame to continuously track the completely occluded object. Our study shows that we achieve competitive performances compared to the current state-of-the-art methods on popular multi-object tracking benchmarks such as MOT16, MOT17, and MOT20.

Detection of Fake Currency Using Machine Learning Models

The goal of this research is to determine whether a given cash sample is genuine or counterfeit. Based on the colours, widths, and serial numbers described, several conventional procedures and methods exist for identifying counterfeit cash. Image processing proposes a number of machine learning techniques with a false-identity detection success rate of 99.9 percent for paper cash in today's era of modern computing. In algorithm-based techniques for detection and identification, various entities such as color, form, paper width, and image filtering on the note play a crucial role. This research proposes the application of K-Nearest Neighbors (KNN) followed by image processing as an effective method for spotting counterfeit money. KNN is favored for use in computer vision problems due to its outstanding accuracy, particularly when dealing with small datasets. This approach leverages the strengths of KNN in handling limited data to enhance the precision and reliability of counterfeit money detection. The accurate facts and information on entities and attributes associated to currency have been compiled in this banknote authentication dataset, which was developed using advanced computational and mathematical methodologies. AI calculations and picture handling are utilized for information handling and information extraction to accomplish an elevated degree of exactness and accuracy.

Управление строительством с иcпользованием компьютерного зрения на строительной площадке

The article presents algorithms for solving the problem of computer vision to control the implementation of rules and requirements for the performance of work on a construction site. A general approach to algorithm development is described, including the structure and method used to collect construction site image data, the structure of the training image data set, the method of enlarging the image data set and the basic artificial intelligence model used for training. The developed and tested object recognition models will be applied to real construction sites, which will reduce the number of accidents involving construction workers, and use resources efficiently.

Averaging data on the unit hypersphere

Averaging data on the unit sphere S d (also called a unit hypersphere) is a common problem in computer vision, robotics and other fields, with applications ranging from motion planning to DNA modelling. In this paper, we introduce a new method for averaging data represented as points on the unit sphere S d−1 using the d-dimensional generalized Kuramoto model. Our method is verified on a range of benchmark data sets and compared with common data averaging algorithms. Also, we showcase the applicability of this method for solving rotation averaging problem.

Coarse-to-Fine Task-Driven Inpainting for Geoscience Images

The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases, the geoscience images might contain occlusions during the image acquisition. This problem actually implies the image inpainting problem in computer vision and multimedia. As far as we know, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but not good enough for geoscience images, and they never consider the following gescience task when developing inpainting methods. This paper aims to repair the occluded regions for a better geoscience task performance and advanced visualization quality simultaneously, without changing the current deployed deep learning based geoscience models. Because of the complex context of geoscience images, we propose a coarse-to-fine encoder-decoder network with the help of designed coarse-to-fine adversarial context discriminators to reconstruct the occluded image regions. Due to the limited data of geoscience images, we propose a MaskMix based data augmentation method, which augments inpainting masks instead of augmenting original images, to exploit the limited geoscience image data. The experimental results on three public geoscience datasets for remote sensing scene recognition, cross-view geolocation and semantic segmentation tasks respectively show the effectiveness and accuracy of the proposed method. The code is available at: https://github.com/HMS97/Task-driven-Inpainting.

Recovering 3D Human Mesh From Monocular Images: A Survey.

Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining well-aligned and physically plausible mesh results, two paradigms have been developed to overcome challenges in the 2D-to-3D lifting process: i) an optimization-based paradigm, where different data terms and regularization terms are exploited as optimization objectives; and ii) a regression-based paradigm, where deep learning techniques are embraced to solve the problem in an end-to-end fashion. Meanwhile, continuous efforts are devoted to improving the quality of 3D mesh labels for a wide range of datasets. Though remarkable progress has been achieved in the past decade, the task is still challenging due to flexible body motions, diverse appearances, complex environments, and insufficient in-the-wild annotations. To the best of our knowledge, this is the first survey that focuses on the task of monocular 3D human mesh recovery. We start with the introduction of body models and then elaborate recovery frameworks and training objectives by providing in-depth analyses of their strengths and weaknesses. We also summarize datasets, evaluation metrics, and benchmark results. Open issues and future directions are discussed in the end, hoping to motivate researchers and facilitate their research in this area. A regularly updated project page can be found at https://github.com/tinatiansjz/hmr-survey.

Global Refinement Algorithm for 3D Scene Reconstruction from a Sequence of Point Clouds

Point cloud registration is a central problem in many computer vision problems. However, ensuring global consistency of the results of pairwise registration of point clouds is still a challenge when there are multiple clouds because different scans should be converted to a common coordinate system. This paper describes a global refinement algorithm that first estimates rotations and then estimates parallel translations. For global refinement of rotations, a closed-form algorithm based on matrices is used. For global refinement of parallel translations, a closed-form algorithm is also used. The proposed algorithm is compared with other global refinement algorithms.

Advances of the Scientific School of V.L. Arlazarov in Dataset Creation and Training Sample Synthesis for Solving Modern Computer Vision Problems

Advances of the Scientific School of V.L. Arlazarov in Dataset Creation and Training Sample Synthesis for Solving Modern Computer Vision Problems