Mathematics

Research

Jump to: Review

17 pages, 12394 KiB

Open AccessArticle

TensorTrack: Tensor Decomposition for Video Object Tracking

by Yuntao Gu, Pengfei Zhao, Lan Cheng, Yuanjun Guo, Haikuan Wang, Wenjun Ding and Yu Liu

Mathematics 2025, 13(4), 568; https://doi.org/10.3390/math13040568 - 8 Feb 2025

Viewed by 569

Abstract

Video Object Tracking (VOT) is a critical task in computer vision. While Siamese-based and Transformer-based trackers are widely used in VOT, they struggle to perform well on the OTB100 benchmark due to the lack of dedicated training sets. This challenge highlights the difficulty [...] Read more.

Video Object Tracking (VOT) is a critical task in computer vision. While Siamese-based and Transformer-based trackers are widely used in VOT, they struggle to perform well on the OTB100 benchmark due to the lack of dedicated training sets. This challenge highlights the difficulty of effectively generalizing to unknown data. To address this issue, this paper proposes an innovative method that utilizes tensor decomposition, an underexplored concept in object-tracking research. By applying L1-norm tensor decomposition, video sequences are represented as four-mode tensors, and a real-time background subtraction algorithm is introduced, allowing for effective modeling of the target–background relationship and adaptation to environmental changes, leading to accurate and robust tracking. Additionally, the paper integrates an improved multi-kernel correlation filter into a single frame, locating and tracking the target by comparing the correlation between the target template and the input image. To further enhance localization precision and robustness, the paper also incorporates Tucker2 decomposition to integrate appearance and motion patterns, generating composite heatmaps. The method is evaluated on the OTB100 benchmark dataset, showing significant improvements in both performance and speed compared to traditional methods. Experimental results demonstrate that the proposed method achieves a 15.8% improvement in AUC and a ten-fold increase in speed compared to typical deep learning-based methods, providing an efficient and accurate real-time tracking solution, particularly in scenarios with similar target–background characteristics, high-speed motion, and limited target movement. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

16 pages, 4136 KiB

Open AccessArticle

A Teacher-Learning-Based Optimization Approach for Blur Detection in Defocused Images

by Sana Munir Khan and Muhammad Tariq Mahmood

Mathematics 2025, 13(2), 187; https://doi.org/10.3390/math13020187 - 8 Jan 2025

Viewed by 597

Abstract

Defocus blur is often encountered in images taken with optical imaging equipment. It might be unwanted, but it might also be a deliberate artistic effect, which means it might help how we see the scenario in an image. In specific applications like image [...] Read more.

Defocus blur is often encountered in images taken with optical imaging equipment. It might be unwanted, but it might also be a deliberate artistic effect, which means it might help how we see the scenario in an image. In specific applications like image restoration or object detection, there may be a need to divide a partially blurred image into its blurred and sharp regions. The effectiveness of blur detection is influenced by how features are combined. In this paper, we propose a parameter-free metaheuristic optimization strategy known as teacher-learning-based optimization (TLBO) to find an optimal weight vector for the combination of blur maps. First, we compute multi-scale blur maps, i.e., features using an LBP-based blur metric. Then, we apply a regularization scheme to refine the initial blur maps. This results in a smooth, edge-preserving blur map that leverages structural information for improved segmentation. Lastly, TLBO is used to find the optimal weight vectors of each refined blur map for the linear feature combination. The proposed model is validated through extensive experiments on two benchmark datasets, and its performance is comparable against five state-of-the-art methods. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

22 pages, 9540 KiB

Open AccessArticle

A New Local Optimal Spline Wavelet for Image Edge Detection

by Dujuan Zhou, Zizhao Yuan, Zhanchuan Cai, Defu Zhu and Xiaojing Shen

Mathematics 2025, 13(1), 42; https://doi.org/10.3390/math13010042 - 26 Dec 2024

Cited by 1 | Viewed by 821

Abstract

Wavelet-based edge detection methods have evolved significantly over the years, contributing to advances in image processing, computer vision, and pattern recognition. This paper proposes a new local optimal spline wavelet (LOSW) and the dual wavelet of the LOSW. Then, a pair of dual [...] Read more.

Wavelet-based edge detection methods have evolved significantly over the years, contributing to advances in image processing, computer vision, and pattern recognition. This paper proposes a new local optimal spline wavelet (LOSW) and the dual wavelet of the LOSW. Then, a pair of dual filters can be obtained, which can provide distortion-free signal decomposition and reconstruction, while having stronger denoising and feature capture capabilities. The coefficients of the pair of dual filters are calculated for image edge detection. We propose a new LOSW-based edge detection algorithm (LOSW-ED), which introduces a structural uncertainty–aware modulus maxima (SUAMM) to detect highly uncertain edge samples, ensuring robustness in complex and noisy environments. Additionally, LOSW-ED unifies multi-structure morphology and modulus maxima to fully exploit the complementary properties of low-frequency (LF) and high-frequency (HF) components, enabling multi-stage differential edge refinement. The experimental results show that the proposed LOSW and LOSW-ED algorithm has better performance in noise suppression and edge structure preservation. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

23 pages, 6763 KiB

Open AccessArticle

Research on Surface Defect Positioning Method of Air Rudder Based on Camera Mapping Model

by Zeqing Yang, Kangni Xu, Mingxuan Zhang, Yingshu Chen, Ning Hu, Yi Zhang, Yi Jin and Yali Lv

Mathematics 2024, 12(20), 3191; https://doi.org/10.3390/math12203191 - 11 Oct 2024

Viewed by 1066

Abstract

(1) Background: Air rudders are used to control the flight attitude of aircraft, and their surface quality directly affects flight accuracy and safety. (2) Method: Traditional positioning methods can only obtain defect location information at the image level but cannot determine the defect’s [...] Read more.

(1) Background: Air rudders are used to control the flight attitude of aircraft, and their surface quality directly affects flight accuracy and safety. (2) Method: Traditional positioning methods can only obtain defect location information at the image level but cannot determine the defect’s physical surface position on the air rudder, which lacks guidance for subsequent defect repair. We propose a defect physical surface positioning method based on a camera mapping model. (3) Results: Repeated positioning experiments were conducted on three typical surface defects of the air rudder, with a maximum absolute error of 0.53 mm and a maximum uncertainty of 0.26 mm. Through hardware systems and software development, the real-time positioning function for surface defects on the air rudder was realized, with the maximum axial positioning error for real-time defect positioning being 0.38 mm. (4) Conclusions: The proposed defect positioning method meets the required accuracy, providing a basis for surface defect repair in the air rudder manufacturing process. It also offers a new approach for surface defect positioning in similar products, with engineering application value. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

23 pages, 3898 KiB

Open AccessArticle

Enhanced Classification of Human Fall and Sit Motions Using Ultra-Wideband Radar and Hidden Markov Models

by Thottempudi Pardhu, Vijay Kumar, Andreas Kanavos, Vassilis C. Gerogiannis and Biswaranjan Acharya

Mathematics 2024, 12(15), 2314; https://doi.org/10.3390/math12152314 - 24 Jul 2024

Cited by 1 | Viewed by 1534

Abstract

In this study, we address the challenge of accurately classifying human movements in complex environments using sensor data. We analyze both video and radar data to tackle this problem. From video sequences, we extract temporal characteristics using techniques such as motion history images [...] Read more.

In this study, we address the challenge of accurately classifying human movements in complex environments using sensor data. We analyze both video and radar data to tackle this problem. From video sequences, we extract temporal characteristics using techniques such as motion history images (MHI) and Hu moments, which capture the dynamic aspects of movement. Radar data are processed through principal component analysis (PCA) to identify unique detection signatures. We refine these features using k-means clustering and employ them to train hidden Markov models (HMMs). These models are tailored to distinguish between distinct movements, specifically focusing on differentiating sitting from falling motions. Our experimental findings reveal that integrating video-derived and radar-derived features significantly improves the accuracy of motion classification. Specifically, the combined approach enhanced the precision of detecting sitting motions by over 10% compared to using single-modality data. This integrated method not only boosts classification accuracy but also extends the practical applicability of motion detection systems in diverse real-world scenarios, such as healthcare monitoring and emergency response systems. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

20 pages, 2540 KiB

Open AccessArticle

Feature Fusion-Based Re-Ranking for Home Textile Image Retrieval

by Ziyi Miao, Lan Yao, Feng Zeng, Yi Wang and Zhiguo Hong

Mathematics 2024, 12(14), 2172; https://doi.org/10.3390/math12142172 - 11 Jul 2024

Viewed by 1016

Abstract

In existing image retrieval algorithms, negative samples often appear at the forefront of retrieval results. To this end, in this paper, we propose a feature fusion-based re-ranking method for home textile image retrieval, which utilizes high-level semantic similarity and low-level texture similarity information [...] Read more.

In existing image retrieval algorithms, negative samples often appear at the forefront of retrieval results. To this end, in this paper, we propose a feature fusion-based re-ranking method for home textile image retrieval, which utilizes high-level semantic similarity and low-level texture similarity information of an image and strengthens the feature expression via late fusion. Compared with single-feature re-ranking, the proposed method combines the ranking diversity of multiple features to improve the retrieval accuracy. In our re-ranking process, Markov random walk is used to update the similarity metrics, and we propose local constraint diffusion based on contextual similarity. Finally, the fusion–diffusion algorithm is used to optimize the sorted list via combining multiple similarity metrics. We set up a large-scale home textile image dataset, which contains

89 k

home textile product images from

12 k

categories, and evaluate the image retrieval performance of the proposed model with the Recall@k and mAP@K metrics. The experimental results show that the proposed re-ranking method can effectively improve the retrieval results and enhance the performance of home textile image retrieval. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

11 pages, 2609 KiB

Open AccessArticle

Transfer Learning with ResNet3D-101 for Global Prediction of High Aerosol Concentrations

by Dušan P. Nikezić, Dušan S. Radivojević, Ivan M. Lazović, Nikola S. Mirkov and Zoran J. Marković

Mathematics 2024, 12(6), 826; https://doi.org/10.3390/math12060826 - 12 Mar 2024

Cited by 3 | Viewed by 1466

Abstract

In order to better predict the high aerosol concentrations associated with air pollution and climate change, a machine learning model was developed using transfer learning and the segmentation process of global satellite images. The main concept of transfer learning lies on convolutional neural [...] Read more.

In order to better predict the high aerosol concentrations associated with air pollution and climate change, a machine learning model was developed using transfer learning and the segmentation process of global satellite images. The main concept of transfer learning lies on convolutional neural networks and works by initializing the already trained model weights to better adapt the weights when the network is trained on a different dataset. The transfer learning technique was tested with the ResNet3D-101 model pre-trained from a 2D ImageNet dataset. This model has performed well for contrail detection to assess climate impact. Aerosol distributions can be monitored via satellite remote sensing. Satellites can monitor some aerosol optical properties like aerosol optical thickness. Aerosol optical thickness snapshots were the input dataset for the model and were obtained from NASA’s Terra-Modis satellite; the output images were segmented by comparing the pixel values with a threshold value of 0.8 for aerosol optical thickness. Hyperparameter optimization finds a tuple of hyperparameters that yields an optimal model that minimizes a predefined loss function on given independent data. The model structure was adjusted in order to improve the performance of the model by applying methods and hyperparameter optimization techniques such as grid search, batch size, threshold, and input length. According to the criteria defined by the authors, the distance domain criterion and time domain criterion, the developed model is capable of generating adequate data and finding patterns in the time domain. As observed from the comparison of relative coefficients for the criteria metrics proposed by the authors, ddc and dtc, the deep learning model based on ConvLSTM layers developed in our previous studies has better performance than the model developed in this study with transfer learning. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

17 pages, 1635 KiB

Open AccessArticle

EEG-BCI Features Discrimination between Executed and Imagined Movements Based on FastICA, Hjorth Parameters, and SVM

by Tat’y Mwata-Velu, Armando Navarro Rodríguez, Yanick Mfuni-Tshimanga, Richard Mavuela-Maniansa, Jesús Alberto Martínez Castro, Jose Ruiz-Pinales and Juan Gabriel Avina-Cervantes

Mathematics 2023, 11(21), 4409; https://doi.org/10.3390/math11214409 - 24 Oct 2023

Cited by 3 | Viewed by 1742

Abstract

Brain–Computer Interfaces (BCIs) communicate between a given user and their nearest environment through brain signals. In the case of device handling, an accurate control-based BCI depends essentially on how the user performs corresponding mental tasks. In the BCI illiteracy-related literature, one subject could [...] Read more.

Brain–Computer Interfaces (BCIs) communicate between a given user and their nearest environment through brain signals. In the case of device handling, an accurate control-based BCI depends essentially on how the user performs corresponding mental tasks. In the BCI illiteracy-related literature, one subject could perform a defined paradigm better than another. Therefore, this work aims to identify recorded Electroencephalogram (EEG) signal segments related to the executed and imagined motor tasks for BCI system applications. The proposed approach implements pass-band filters and the Fast Independent Component Analysis (FastICA) algorithm to separate independent sources from raw EEG signals. Next, EEG features of selected channels are extracted using Hjorth parameters. Finally, a Support Vector Machines (SVMs)-based classifier identifies executed and imagined motor features. Concretely, the Physionet dataset, related to executed and imagined motor EEG signals, provided training, testing, and validating data. The numerical results let us discriminate between executed and imagined motor tasks accurately. Therefore, the proposed method offers a reliable alternative to extract EEG features for BCI based on executed and imagined movements. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Figure 1

Review

Jump to: Research

52 pages, 29859 KiB

Open AccessReview

2D Object Detection: A Survey

by Emanuele Malagoli and Luca Di Persio

Mathematics 2025, 13(6), 893; https://doi.org/10.3390/math13060893 - 7 Mar 2025

Viewed by 1222

Abstract

Object detection is a fundamental task in computer vision, aiming to identify and localize objects of interest within an image. Over the past two decades, the domain has changed profoundly, evolving into an active and fast-moving field while simultaneously becoming the foundation for [...] Read more.

Object detection is a fundamental task in computer vision, aiming to identify and localize objects of interest within an image. Over the past two decades, the domain has changed profoundly, evolving into an active and fast-moving field while simultaneously becoming the foundation for a wide range of modern applications. This survey provides a comprehensive review of the evolution of 2D generic object detection, tracing its development from traditional methods relying on handcrafted features to modern approaches driven by deep learning. The review systematically categorizes contemporary object detection methods into three key paradigms: one-stage, two-stage, and transformer-based, highlighting their development milestones and core contributions. The paper provides an in-depth analysis of each paradigm, detailing landmark methods and their impact on the progression of the field. Additionally, the survey examines some fundamental components of 2D object detection such as loss functions, datasets, evaluation metrics, and future trends. Full article

(This article belongs to the Special Issue Advanced Research in Image Processing and Optimization Methods)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Advanced Research in Image Processing and Optimization Methods

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI