Article
Computer Science, Information Systems
Xin Liu, Guoying Zhao
Summary: The study focuses on gesture recognition using 3D skeleton-based representation, which offers invariance and sparse coding to address challenges in gesture comparison and classification. Experimental results demonstrate that the proposed method has achieved state-of-the-art performance in gesture recognition.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Michalis Lazarou, Bo Li, Tania Stathaki
Summary: This work introduces a novel shape matching methodology for real-time hand gesture recognition and demonstrates its superiority in accuracy and computational efficiency through comparison with other methods.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Automation & Control Systems
Gilde Vanel Tchane Djogdom, Martin J. -D. Otis, Ramy Meziane
Summary: The emerging needs of human beings have led manufacturing companies to shift from mass production to mass customization. This change has brought about a collaborative robotics scenario where robots work alongside humans in the same workspace. While wearable sensors using IMU are widely used to capture upper body gestures, this study focuses on foot gesture recognition using an insole-based sensor system. The system achieves a recognition accuracy of around 88% and can accurately discriminate between different foot gestures.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Manisha Kowdiki, Arti Khaparde
Summary: This paper presents an improved segmentation and deep learning-based strategy for dynamic hand gesture recognition, which enhances the performance by combining different algorithms and utilizes Dynamic Time Warping to improve the dynamic hand gestures performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Multidisciplinary Sciences
Saed Alqaraleh, A. H. Abdul Hafez, Ammar Tello
Summary: This paper introduces a new visual place recognition method based on dynamic time warping and deep convolutional neural network, which is capable of addressing changes in visual conditions like appearance and viewpoint. Experimental results demonstrate that the proposed method outperforms traditional features and is compared with other existing visual place recognition algorithms.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Ramin Fathian, Steven Phan, Chester Ho, Hossein Rouhani
Summary: This study aimed to develop and validate a technology using a wrist-mounted inertial measurement unit (IMU) based on dynamic time warping (DTW) and k-nearest neighbours (KNN) for detecting and monitoring face touch in controlled and natural environment trials. The sensitivity, precision, and accuracy of the developed technology were evaluated, showing high performance in both controlled and natural environment trials. In conclusion, the wrist-mounted IMU can be used as an ambulatory system to detect and monitor face touching as a high-risk habit in daily life.
Article
Multidisciplinary Sciences
Shiqi Wang, Kankan Wang, Tingping Yang, Yiming Li, Di Fan
Summary: This paper proposes an improved 3D-ResNet sign language recognition algorithm with enhanced hand features, aiming to improve the accuracy of sign language recognition. The algorithm detects the hand regions using the improved EfficientDet network and enhances the detection ability with dual channel and spatial attention modules. Additionally, an improved residual module is used to extract sign language features. Experimental results show that the proposed algorithm achieves higher recognition accuracy compared to other algorithms.
SCIENTIFIC REPORTS
(2022)
Article
Chemistry, Analytical
Tsung-Han Tsai, Yih-Ru Tsai
Summary: With advancements in technology, gesture control systems are becoming more intuitive, but vision-based hand gesture recognition systems still face challenges. This paper proposes a VLSI design with dual-cameras for dynamic gesture recognition, achieving high accuracy.
Article
Multidisciplinary Sciences
Atefe Alitaleshi, Hamid Jazayeriy, Javad Kazemitabar
Summary: This paper focuses on fingerprinting-based indoor positioning method and proposes a solution for pedestrian trajectory reconstruction in the process of fingerprint map creation. By using a spatial-temporal matching mechanism, the positioning accuracy is significantly improved and the quality of the radio map is validated.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Chengfeng Jian, Xingze Liu, Meiyu Zhang
Summary: This paper introduces a dynamic hand gesture detection method RD-Hand for mobile terminals, achieving high accuracy in gesture trajectory recognition through regression tasks, without relying on GPU, and demonstrating good real-time performance.
APPLIED INTELLIGENCE
(2022)
Article
Chemistry, Analytical
Jesus Galvan-Ruiz, Carlos M. Travieso-Gonzalez, Alejandro Pinan-Roescher, Jesus B. Alonso-Hernandez
Summary: According to WHO, a significant percentage of the global population faces difficulty in oral communication due to hearing disorders. This article discusses the importance of developing tools to aid in daily communication for these individuals. The research focuses on transcribing Spanish Sign Language (SSL) using a Leap Motion volumetric sensor capable of recognizing hand movements in 3D. By collaborating with a hearing-impaired subject and recording 176 dynamic words, the research achieves an accuracy of 95.17% in predicting input through the use of Dynamic Time Warping (DTW).
Article
Chemistry, Analytical
Enmin Zhong, Carlos R. del-Blanco, Daniel Berjon, Fernando Jaureguizar, Narciso Garcia
Summary: Automatic hand gesture recognition in video sequences is widely applied in various fields such as home automation, sign language interpretation, and clinical operations. This study proposes a hybrid approach combining 3D-CNNs and Transformers to address the challenge of real-time recognition and efficient handling of temporal dependencies. The method achieves high accuracy and real-time performance using a standard CPU, outperforming existing state-of-the-art methods that require specialized GPUs.
Article
Computer Science, Artificial Intelligence
Dongjie Li, Zilei Zhang, Hongyue Zhao
Summary: In this paper, a new method based on machine vision and deep learning is proposed to address the challenges of occlusion, complex background, and fast gesture movement in dynamic gesture trajectory recognition. By extracting video keyframes and introducing real-time tracking features, the problem of object occlusion is effectively solved. The DenseNet-BC-169 network is used to balance recognition rate and training time. Experimental results show significant improvements in accuracy and real-time processing speed compared to the champion of the dynamic gesture recognition challenge.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jubayer Al Mahmud, Bandhan Chandra Das, Jungpil Shin, Khan Md Hasib, Rifat Sadik, M. F. Mridha
Summary: The research proposes a 3D gesture recognition and adaption system based on Kinect for human-robot interaction, comprising four modules: pointing gesture recognition, 3D dynamic gesture recognition, gesture adaptation, and robot navigation. The system achieves high accuracy in dynamic gesture recognition and is capable of recognizing pointing gestures in real-time.
Article
Chemistry, Analytical
Kim S. Sczuka, Marc Schneider, Alan K. Bourke, Sabato Mellone, Ngaire Kerse, Jorunn L. Helbostad, Clemens Becker, Jochen Klenk
Summary: A two-layer locomotion recognition method using inertial sensor data was proposed to identify walking, ascending and descending stairs. The results showed high sensitivity in recognizing walking but lower sensitivity in recognizing stair climbing.
Article
Computer Science, Information Systems
A. Romero-Garces, R. Salles De Freitas, R. Marfil, C. Vicente-Chicote, J. Martinez, J. F. Ingles-Romero, A. Bandera
Summary: This paper proposes an approach to self-adaptation in robots by modeling behavior variability at design-time and allowing the robot to configure its behavior at runtime based on contextual information. This approach is supported by a model-based framework that allows robotic engineers to specify behavior variation points, contextual information, and non-functional properties for measuring Quality-of-Service (QoS) of the robot. The framework automatically generates the runtime infrastructure for the robot to adapt its behavior and achieve the best QoS according to its current context.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Daniel Gonzalez-Toledo, Maria Cuevas-Rodriguez, Luis Molina-Tanco, Arcadio Reyes-Lecuona
Summary: Virtual trackball techniques are widely used for 3D interaction through interfaces with limited degrees of freedom. This study conducted an experiment using a mouse and touch device to investigate the effects of selecting different fixed axes based on the user's mental model. The findings suggest that consistency between the fixed axis and the object's intrinsic axis positively impacts usability. The study highlights the importance of considering implementations that allow for selecting different fixed axes for specific objects in future reduced-DoF interaction interfaces.
Article
Computer Science, Artificial Intelligence
Ana Iglesias, Javier Garcia, Angel Garcia-Olaya, Raquel Fuentetaja, Fernando Fernandez, Adrian Romero-Garces, Rebeca Marfil, Antonio Bandera, Karine Lan Hing Ting, Dimitri Voilmy, Alvaro Duenas, Cristina Suarez-Mejias
Summary: The introduction of robots in the real world requires evaluation of factors like usability, user experience, social acceptance, and societal impact. This article proposes an extension of a popular HRI evaluation framework to include accessibility as a new evaluation factor. The proposed AUSUS approach considers Accessibility, Usability, Social acceptance, User experience, and Societal impact, and was tested in a use case with a socially assistive robotic platform for comprehensive geriatric assessment.
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Camilo A. Ruiz-Beltran, Adrian Romero-Garces, Martin Gonzalez, Antonio Sanchez Pedraza, Juan A. Rodriguez-Fernandez, Antonio Bandera
Summary: This paper presents a hardware-based embedded solution for real-time eye detection. By redesigning the popular Viola-Jones method, highly parallel single-pass image processing is achieved. Experimental validation shows that the proposed solution achieves 100% accuracy in eye detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Adrian Romero-Garces, Alejandro Hidalgo-Paniagua, Martin Gonzalez-Garcia, Antonio Bandera
Summary: Service robotics involves designing robots that work in dynamic and open environments, and the MAPE-K loops are a popular real-time self-adaptation scheme that coordinates multiple loops to solve complex problems. This paper describes the use of a graph-based representation, the Deep State Representation (DSR), as the knowledge component in the MAPE-K scheme applied in robotics, which has been successfully applied in a retail intralogistics scenario.
APPLIED SCIENCES-BASEL
(2022)
Editorial Material
Chemistry, Multidisciplinary
Antonio Bandera, Luis Manso Fernandez-Arguellez, Zoe Falomir
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
David Sosa-Trejo, Antonio Bandera, Martin Gonzalez, Santiago Hernandez-Leon
Summary: Since the 19th century, scientists have tried to quantify species distributions using techniques such as direct counting and microscopes. Automatic image processing and classification methods are now being utilized to avoid manual procedures for classifying marine plankton. This article summarizes the techniques proposed for classifying marine plankton from the beginning of this field to the present day, focusing on automatic methods that utilize image processing.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Silvia Guillen-Ruiz, Juan Pedro Bandera, Alejandro Hidalgo-Paniagua, Antonio Bandera
Summary: In recent years, there has been growing commercial and research interest in service robots operating in everyday environments. These devices are expected to autonomously navigate in crowded environments while taking into account movement efficiency, safety, and social acceptability. Incorporating socially aware criteria into traditional path planning modules to react to human behavior without causing discomfort presents a complex challenge. This review explores approaches to socially aware navigation and categorizes them based on the strategies adopted by robots to manage interaction or cooperation with humans.
Article
Chemistry, Analytical
Camilo A. Ruiz-Beltran, Adrian Romero-Garces, Martin Gonzalez-Garcia, Rebeca Marfil, Antonio Bandera
Summary: This article describes the implementation of an eye image detection system that can evaluate the level of defocus blur in captured images and discard unfocused eye images. Experimental evaluation shows that this system can successfully discard up to 97% of out-of-focus eye images.
Proceedings Paper
Robotics
Adrian Romero-Garces, Alejandro Hidalgo-Paniagua, Pablo Bustos, Rebeca Marfil, Antonio Bandera
Summary: The experience of inner speech is common and plays a relevant role in generating spontaneous responses to the context, as well as regulating thoughts and behaviors. Intimately tied to our sense of self, inner speech provides a continuous monologue of thoughts through internalization, which is essential for structuring and regulating activities. This paper emphasizes the specific aspect of inner speech and demonstrates examples in the CORTEX software architecture, where semantic tokens are used for internalizing the world and regulating decision making activities.
ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2
(2023)
Proceedings Paper
Robotics
Alejandro Cruces, Alberto Tudela, Adrian Romero-Garces, Juan Pedro Bandera
Summary: Sensor fusion techniques improve robustness and accuracy by combining data from multiple sensors. This paper proposes a novel perception integrator module that uses low complexity algorithms to implement fusion, tracking, and forgetting mechanisms.
ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2
(2023)
Article
Computer Science, Information Systems
Camilo A. Ruiz-Beltran, Adrian Romero-Garces, Martin Gonzalez-Garcia, Rebeca Marfil, Antonio Bandera
Summary: This paper describes the embedding of an eye detection system on a Zynq XCZU4EV UltraScale+ MPSoC. The system is used in a remote iris recognition application, requiring high resolution images and the ability to detect only focused eye images. By utilizing the neural network's multi-channel input advantage, the system uses grayscale images and high-pass filtered versions as inputs to the CNN. Experimental validation demonstrates the effectiveness of the system.