Article
Geochemistry & Geophysics
Zetao Wang, Gang Li, Le Yang
Summary: This letter introduces a novel method for dynamic hand gesture recognition based on micro-Doppler radar signatures. The method utilizes short-time Fourier transform to obtain time-frequency spectrograms and models them with a hidden Gauss-Markov model for recognition. Experimental results show strong generalization ability in radar gesture recognition, even in low SNR and unknown user scenarios.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Haoming Liu, Zhenyu Liu
Summary: This paper proposes a multimodal dynamic hand gesture recognition method based on a two-branch fusion deformable network with Gram matching. It effectively improves the adaptability of the classifier to complex environments and exhibits satisfactory robustness to multiple subjects.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Jun Xu, Hanchen Wang, Jianrong Zhang, Linqin Cai
Summary: This paper presents a robust RGB-D data-based recognition method for static and dynamic hand gestures, utilizing algorithms like Distance Transform and K-Curvature-Convex Defects Detection for gesture identification and feature vector construction, and proposing recognition algorithms. Additionally, a unifying feature descriptor is generated for dynamic gestures by combining Euclidean distance and skeleton feature ratios for recognition. Extensive experiments validate the real-time application of the gesture recognition algorithm.
Article
Computer Science, Artificial Intelligence
Carlos Puerto-Santana, Pedro Larranaga, Concha Bielza
Summary: This article introduces asymmetric hidden Markov models with feature saliencies, which are capable of simultaneously determining relevant variables/features and probabilistic relationships between variables during their learning phase. Comparing with other approaches, the proposed models have better or equal fitness and provide further data insights.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jun Ma, Xunhuan Ren, Hao Li, Wenzu Li, Viktar Yurevich Tsviatkou, Anatoliy Antonovich Boriskevich
Summary: This paper proposes a skeleton extraction framework to enhance the robustness of existing skeletonization methods against both inner and border noise. By using different scales of Gaussian filters to smooth the input image and obtaining multiple representations, followed by binarization and skeletonization to produce a series of binary and skeletal images, the most suitable skeleton is selected based on a measurement that considers both the changes in skeleton and binary images. Experimental results show that the proposed framework can reduce inner noise by approximately 92% and border noise by approximately 40% based on the measure of skeleton variation rate.
Article
Computer Science, Software Engineering
Janghun Kim, Sungkil Lee
Summary: This paper presents a model and rendering algorithm for Potentially Visible Hidden Volumes (PVHVs) used in multi-view image warping. PVHVs are 3D volumes that are occluded in known source views but potentially visible in novel views. The authors define PVHVs using the edges of foreground fragments from the known view and the boundaries of novel views. PVHVs can batch-test the visibility of source fragments and cull redundant fragments prior to warping.
ACM TRANSACTIONS ON GRAPHICS
(2023)
Article
Engineering, Electrical & Electronic
David Gonzalez Leon, Jade Groli, Sreenivasa Reddy Yeduri, Daniel Rossier, Romuald Mosqueron, Om Jee Pandey, Linga Reddy Cenkeramaddi
Summary: This article introduces a video hand gesture recognition method based on a depth camera and a lightweight convolutional neural network (CNN) model. By constructing a dataset and using this lightweight CNN model, hand movements can be efficiently detected and classified. Experimental results show high accuracy on the test dataset and short inference time for the model.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Guan Yuan, Xiao Liu, Qiuyan Yan, Shaojie Qiao, Zhixiao Wang, Li Yuan
Summary: This study introduces a novel data glove and proposes an improved deep feature fusion network, achieving good results in gesture recognition, especially in recognizing American Sign Language and Chinese Sign Language.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Ren C. Luo, Wei-Lung Hsu
Summary: The article proposes a histogram of oriented depth model (HODM) and its extraction approach, aiming to address the issue of poor localization accuracy in indoor service robots when the environment is rearranged. HODM estimates indoor primary structures and floor layouts through histogram-based model matching, achieving lower localization error compared to traditional methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Engineering, Electrical & Electronic
Firdaus Khatoon, Maryam Ravan, Reza K. Amineh, Armanda Byberi
Summary: Gesture recognition is a growing field in human-computer interaction technology. This study introduces a new sensing pad system that uses machine learning algorithms to recognize specific hand gestures. It achieves high accuracy in distinguishing gestures and is designed to be a non-contact apparatus.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Ren C. Luo, Wei-Lung Hsu
Summary: The article introduces a localization method based on Histogram of Oriented Depth Model (HODM) that reduces localization errors compared to traditional methods and has fast computational time.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Arturo Gomez Chavez, Andrea Ranieri, Davide Chiarelia, Andreas Birk
Summary: Underwater robotics require reliable and safe operations, especially when working in collaboration with divers. Possible applications of underwater human-robot collaboration include marine science, archeology, oil and gas production, handling of unexploded ordnance, and inspection and maintenance of marine infrastructure.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2021)
Article
Operations Research & Management Science
Kai Zheng, Yuying Li, Weidong Xu
Summary: The proposed SC-HMM is a novel method for accurate estimation of MRS models, especially suitable for HMMs with continuous observations. It utilizes spectral clustering for latent state identification and estimates conditional distribution statistics and transitional probabilities based on identified latent states.
ANNALS OF OPERATIONS RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Hao Liang, Lunke Fei, Shuping Zhao, Jie Wen, Shaohua Teng, Yong Xu
Summary: Hand gesture recognition is a challenging task in computer vision, and this paper proposes an end-to-end multiscale feature learning network for improving the effectiveness of hand gesture recognition. The network consists of a CNN-based backbone, a feature aggregation pyramid network, and three task-specific prediction branches. Experimental results show that the proposed method outperforms most state-of-the-art hand gesture recognition methods.
PATTERN RECOGNITION
(2024)
Article
Engineering, Electrical & Electronic
Francois Desbouvries, Yohan Petetin, Achille Salaun
Summary: In this paper, HMC and RNN are considered as generative models and embedded in a common GUM. The expressivity of these models is compared by assuming linearity and Gaussianity, and using structured covariance series to characterize the probability distributions.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Milosz Rajchel, Mariusz Oszust
Summary: The study introduces a new benchmark database and a new NR-IQA metric that uses a wide range of image features to address various distortions, achieving superior correlation results with human scores compared to state-of-the-art IQA methods.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Article
Chemistry, Analytical
Igor Stepien, Rafal Obuchowicz, Adam Piorkowski, Mariusz Oszust
Summary: A novel no-reference magnetic resonance image quality assessment method is proposed in this paper, which combines deep convolutional neural networks and support vector machine regression. Experimental results demonstrate that this method outperforms existing approaches in terms of correlation with subjective opinions of experienced radiologists.
Article
Mathematics
Grzegorz Sroka, Mariusz Oszust
Summary: This paper examines the upper approximation of the constant in a Markov-type inequality on a simplex using minimal polynomial and pluripotential theories. The complex equilibrium measure that solves the extreme problem by minimizing the energy integral is included. Examples of second degree polynomials are introduced, followed by formulating a challenging bilevel optimization problem using the polynomials for approximation. Three popular meta-heuristics were then applied to investigate the results.
Article
Computer Science, Information Systems
Mariusz Oszust, Grzegorz Sroka, Karol Cymerys
Summary: A novel hybridization approach is proposed in this paper to improve the performance of optimization algorithms by replacing worst solutions with predicted candidates. The approach is applied to ten state-of-the-art population-based algorithms and evaluated on multiple functions and engineering problems, showing the superiority of the hybrids over their counterparts.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Mariusz Oszust
Summary: The paper presents an improved MPA variant using a Local Escaping Operator (LEO) to address the premature convergence issue. Experimental results demonstrate the superiority of LEO-MPA over MPA and recent algorithms, showing the effectiveness of hybridizing meta-heuristics with LEO for optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Chemistry, Analytical
Michal Markiewicz, Leslaw Gniewek, Dawid Warchol
Summary: This paper introduces a new concept and definition of hierarchical structure for Fuzzy Interpreted Petri Net (FIPN), including the concept of macroplaces and their implementation in a computer simulator called HFIPN-SML.
Article
Chemistry, Analytical
Dawid Warchol, Mariusz Oszust
Summary: This paper proposes a method to improve the effectiveness of artificial samples in time series generation by introducing constraints and conducts experiments on eight AR datasets. The results show the superiority of the introduced method over related approaches.
Article
Environmental Sciences
Igor Stepien, Mariusz Oszust
Summary: This paper proposes a novel No-Reference Pan-Sharpening Image Quality Assessment method, which utilizes responses from two complementary network architectures as quality-aware information. The extracted PS image representations are processed to create a quality model, and experimental results show its superiority over other methods in terms of typical criteria.
Article
Automation & Control Systems
Igor Stepien, Mariusz Oszust
Summary: This study aims to provide a deep learning-based No-Reference MR Image Quality Assessment method for accurate quality prediction of MR images, which is essential for effective medical diagnostics.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Mariusz Oszust, Dawid Warchol
Summary: This paper proposes a method to improve the accuracy of human action recognition by augmenting time series data using deep learning classifiers. The method modifies the time scale of input time series and transforms them into compact sequences using PAA, leading to better performance of the deep learning model compared to popular augmentation methods. The source code of the method is available at https://marosz.kia.prz.edu.pl/Adder.html.
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tomasz Kapuscinski
Summary: This article introduces a vision-based method for handshape recognition, which uses a deep neural network and genetic algorithm to recognize the shape of the hand. A simple educational game is developed based on the algorithm to practice the use of finger alphabet.
INTELLIGENT TUTORING SYSTEMS, ITS 2022
(2022)
Article
Imaging Science & Photographic Technology
Igor Stepien, Mariusz Oszust
Summary: This study presents a survey on recently introduced NR-IQA methods for the assessment of MR images, covering typical distortions, popular NR methods, evaluation protocols, benchmark databases, emerging challenges, and trends towards accurate image prediction models.
JOURNAL OF IMAGING
(2022)
Proceedings Paper
Automation & Control Systems
Mariusz Oszust, Jakub Krupski
Summary: This paper presents an approach to isolated sign language recognition using data from a depth camera. By dividing depth map sequences of dynamic sign language gestures into smaller regions and using statistical information, the method improves gesture recognition performance with the NN classifier in combination with DTW technique.
KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS (KSE 2021)
(2021)