- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP) - Hangzhou (2018.10.18-2018.10.20)] 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP) - Dynamic Hand Gesture Recognition Using FMCW Radar Sensor for Driving Assistance
摘要： Dynamic hand gesture recognition is very important for human-computer interaction. In vehicles, hand gesture recognition can be used as the driver's auxiliary system to achieve remote control of the instrument. To a certain extent, this system can avoid physical buttons and touch screens causing interference to the driver. In this paper, we describe a driver-assisted dynamic gesture recognition system to classify nine hand gestures based on micro-Doppler signatures obtained by 77GHz FMCW radar using a convolutional neural network (CNN). We further explore the changes in the accuracy of same gestures in a variety of experimental scenarios to help optimize the robustness of the system.
关键词： convolutional neural network,hand gesture recognition,driver assistance system,FMCW radar sensor
更新于2025-09-23 15:22:29
-
Hand Gesture Recognition in Automotive Human–Machine Interaction Using Depth Cameras
摘要： In this review, we describe current Machine Learning approaches to hand gesture recognition with depth data from time-of-flight sensors. In particular, we summarise the achievements on a line of research at the Computational Neuroscience laboratory at the Ruhr West University of Applied Sciences. Relating our results to the work of others in this field, we confirm that Convolutional Neural Networks and Long Short-Term Memory yield most reliable results. We investigated several sensor data fusion techniques in a deep learning framework and performed user studies to evaluate our system in practice. During our course of research, we gathered and published our data in a novel benchmark dataset (REHAP), containing over a million unique three-dimensional hand posture samples.
关键词： time-of-flight sensors,hand gesture recognition,automotive,human–machine interaction,neural networks
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE Asian Solid-State Circuits Conference (A-SSCC) - Tainan, Taiwan (2018.11.5-2018.11.7)] 2018 IEEE Asian Solid-State Circuits Conference (A-SSCC) - A 137-μW Area-Efficient Real-Time Gesture Recognition System for Smart Wearable Devices
摘要： Gesture recognition has increasingly become one of the most popular human-machine interaction techniques for smart devices. Existing gesture recognition systems suffer from either excessive power consumption or large size, limiting their applications for ultra-low power IoT and wearable devices. This paper presents an accurate, area-efficient, and ultra-low power real-time gesture recognition system for smart wearable devices. The proposed work utilizes a peak-based gesture classification engine with less memory and a low-resolution and low-power on-chip image sensor for achieving high area efficiency and low power. The feature extraction architecture removes fixed-pattern noises from the low-power on-chip image sensor for accuracy improvement and employs parallelism for recognition speed enhancement. The proposed system requires only 3.2 KB on-chip memory for processing 32x32 pixel data. Measurement results of a test chip fabricated in 65nm CMOS demonstrate that the proposed system consumes 137.0 pW at 0.8 V and 30fps while occupying only 1.78mm2, which achieves the lowest power and smallest area among existing gesture recognition systems.
关键词： system on chip,low power processor,image sensor,wearable devices,gesture recognition,feature extraction
更新于2025-09-23 15:22:29
-
Integrated Optical Fiber Force Myography Sensor as Pervasive Predictor of Hand Postures
摘要： Force myography (FMG) is an appealing alternative to traditional electromyography in biomedical applications, mainly due to its simpler signal pattern and immunity to electrical interference. Most FMG sensors, however, send data to a computer for further processing, which reduces the user mobility and, thus, the chances for practical application. In this sense, this work proposes to remodel a typical optical fiber FMG sensor with smaller portable components. Moreover, all data acquisition and processing routines were migrated to a Raspberry Pi 3 Model B microprocessor, ensuring the comfort of use and portability. The sensor was successfully demonstrated for 2 input channels and 9 postures classification with an average precision and accuracy of ~99.5% and ~99.8%, respectively, using a feedforward artificial neural network of 2 hidden layers and a competitive output layer.
关键词： user interface,optical fiber sensor,Force myography,gesture recognition,integrated sensor
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Sozopol, Bulgaria (2019.9.6-2019.9.8)] 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Peculiarities of Wave Surface of a SemiconductorDielectric Metamaterial
摘要： We present GyroPen, a method to reconstruct the motion path for pen-like interaction from standard built-in sensors in modern smartphones. The key idea is to reconstruct a representation of the trajectory of the phone’s corner that is touching a writing or drawing surface from the measurements obtained from the phone’s gyroscopes and accelerometers. We propose to directly use the angular trajectory for this reconstruction, which removes the necessity for accurate absolute 3-D position estimation, a task that can be difficult using low-cost accelerometers. We connect GyroPen to a handwriting recognition system and perform two proof-of-concept experiments to demonstrate that the reconstruction accuracy of GyroPen is accurate enough to be a promising approach to text entry. In a first experiment, the average novice participant (n = 10) was able to write the first word only 37 s after the starting to use GyroPen for the first time. In a second experiment, experienced users (n = 2) were able to write at the speed of 3–4 s for one English word and with a character error rate of 18%.
关键词： text recognition,Computer and information processing,gesture recognition,pattern recognition,handwriting recognition
更新于2025-09-16 10:30:52
-
[IEEE 2019 International Workshop on Electromagnetics: Applications and Student Innovation Competition (iWEM) - Qingdao, China (2019.9.18-2019.9.20)] 2019 International Workshop on Electromagnetics: Applications and Student Innovation Competition (iWEM) - Dual-Polarized Bandpass Three-Dimensional FSS Based on Square Waveguide Structure
摘要： We present GyroPen, a method to reconstruct the motion path for pen-like interaction from standard built-in sensors in modern smartphones. The key idea is to reconstruct a representation of the trajectory of the phone’s corner that is touching a writing or drawing surface from the measurements obtained from the phone’s gyroscopes and accelerometers. We propose to directly use the angular trajectory for this reconstruction, which removes the necessity for accurate absolute 3-D position estimation, a task that can be difficult using low-cost accelerometers. We connect GyroPen to a handwriting recognition system and perform two proof-of-concept experiments to demonstrate that the reconstruction accuracy of GyroPen is accurate enough to be a promising approach to text entry. In a first experiment, the average novice participant (n = 10) was able to write the first word only 37 s after the starting to use GyroPen for the first time. In a second experiment, experienced users (n = 2) were able to write at the speed of 3–4 s for one English word and with a character error rate of 18%.
关键词： text recognition,Computer and information processing,gesture recognition,pattern recognition,handwriting recognition
更新于2025-09-16 10:30:52
-
Two User Adaptation-Derived Features for Biometrical Classifications of User Identity in 3D-Sensor-Based Body Gesture Recognition Applications
摘要： For human gesture recognition applications, 3D-sensor-based approaches have received considerable attention and are crucial for future applications of an advanced body sensor network (BSN). A practical gesture recognition system is to apply active gesture patterns of a gesture-making user for body action classifications. 3D-sensor-based gesture recognition, categorized as biometric recognition in BSN applications, is greatly lack of the extensible cognition ability due to substandard recognition accuracy on the gesture-making user identity. To overcome this problem, this study proposes an active gesture-based user identity recognition approach using a robust feature design, called user adaptation (UA) features, derived from a UA process. Two different UA features, namely Eigen Centroid-UA and Eigen Transform-UA features, were developed in this study to accurately represent the adaptive learning tendency of gesture recognition for a specific gesture-making user. Compared with traditional 3D sensor gesture-based identity recognition approaches that employ only the feature of fixed body skeleton information without any UA designs, the presented UA-feature can exhibit fine adaptation learning continuously to the specific action user and therefore, superior identity recognition accuracy will be constantly ensured. To demonstrate the efficiency and effectiveness of the developed robust UA features in this paper, experiments on gesture-making user identification by Gaussian mixture model (GMM) applying the proposed Eigen Centroid-UA feature and verification by support vector machine (SVM) applying the proposed Eigen Transform-UA feature were conducted.
关键词： identity recognition,body skeleton,eigenspace,gesture recognition,user adaptation,3D sensor,feature
更新于2025-09-09 09:28:46
-
[Lecture Notes in Computer Science] Smart Multimedia Volume 11010 (First International Conference, ICSM 2018, Toulon, France, August 24–26, 2018, Revised Selected Papers) || A Survey on Vision-Based Hand Gesture Recognition
摘要： Hand gesture recognition is regarded as an important part of artificial intelligence. A great effort was put into human-computer interaction so that hand gesture recognition is gradually becoming a developed technology. In light of the utilization of mouse and keyboard, the increasing needs of human-computer interaction cannot be met; hindrance turns out to be increasingly genuine. In this paper, we reviewed previous investigations of vision-based gesture recognition and summarized their findings. This paper compares the most common human-computer interaction products in recent years, which can be used to capture gesture data. Then we started with the classification of gestures and summarized the research of visual gesture recognition based on static and dynamic gestures. The gesture representations we summarized includes appearance-based and 3D model-based methods. We also introduced the applications of the two kinds of hand gestures recognition in the papers of recent years. A possible classification methods was put forward to improve the performance of gesture recognition. The goal of this paper is to summarize the current technology and research results and compare the differences and the advantage of different hand gesture recognition methods, which will contribute to the following research.
关键词： Interaction products,Gesture representation,Hand gesture recognition,Application,Classification
更新于2025-09-04 15:30:14
-
RGB-D static gesture recognition based on convolutional neural network
摘要： In the area of human–computer interaction (HCI) and computer vision, gesture recognition has always been a research hotspot. With the appearance of depth camera, gesture recognition using RGB-D camera has gradually become mainstream in this field. However, how to effectively use depth information to construct a robust gesture recognition system is still a problem. In this paper, an RGB-D static gesture recognition method based on fine-tuning Inception V3 is proposed, which can eliminate the steps of gesture segmentation and feature extraction in traditional algorithms. Compared with general CNN algorithms, the authors adopt a two-stage training strategy to fine-tune the model. This method sets a feature concatenate layer of RGB and depth images in the CNN structure, using depth information to promote the performance of gesture recognition. Finally, on the American Sign Language (ASL) Recognition dataset, the authors compared their method with other traditional machine learning methods, CNN algorithms, and the RGB input only method. Among three groups of comparative experiments, the authors’ method reached the highest accuracy of 91.35%, reaching the state-of-the-art currently on ASL dataset.
关键词： RGB-D,Inception V3,gesture recognition,human–computer interaction,CNN
更新于2025-09-04 15:30:14