- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
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
-
Cowpea-structured PVDF/ZnO Nanofibers Based Flexible Self-powered Piezoelectric Bending Motion Sensor Towards Remote Control of Gestures
摘要： Interactive human-machine interface (iHMI) is a bridge connecting human beings and robots, which has an important requirement for perceiving the change of pressure and bending angle. Here, we designed a flexible self-powered piezoelectric sensor (PES) based on the cowpea-structured PVDF/ZnO nanofibers (CPZNs) for remote control of gestures in human-machine interactive system. Due to the synergistic piezoelectric effect of hybrid PVDF/ZnO and the flexibility of polymer, this PES exhibited excellent bending sensitivity of 4.4 mV deg-1 ranging widely from 44 ° to 122 °, fast response time of 76 ms, and good mechanical stability. Besides, the PES could operate under both bending and pressing mode, show ultrahigh pressing sensitivity of 0.33 V kPa-1, with response time of 16 ms. When integrated in iHMI, the PES could be conformably covered on different curve surfaces, demonstrated accurate bending angle recording and fast recognition for realizing intelligent human-machine interaction. On this basis, the application of remote control of robotic hand was successfully realized in form of acting the same gesture as human hand synchronously. This CPZNs-based self-powered PES is distinct and unique in its structure and fundamental mechanism, and exhibits a prospective potential application in iHMI.
关键词： human-machine interaction,cowpea-structured nanofiber,bending monitoring,self-powered,PVDF/ZnO
更新于2025-09-23 15:21:01
-
[IEEE 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Xi'an, China (2018.11.7-2018.11.10)] 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Human-Computer Interaction using Finger Signing Recognition with Hand Palm Centroid PSO Search and Skin-Color Classification and Segmentation
摘要： This paper presents a novel image processing technique for recognizing finger signs language alphabet. A human-computer interaction system is built based on the recognition of sign language which constitutes an interface between the computer and hearing-impaired persons, or as an assistive technology in industrial robotics. The sign language recognition is articulated on the extraction of the contours of the sign language alphabets, therefore, converting into one dimensional signal processing, which improves the recognition efficiency and significantly reduces the processing time. The pre-processing of images is performed by a novel skin-color region segmentation defined inside the standard RGB (sRGB) color space, then a morphological filtering is used for non-skin residuals removal. Afterwards, a circular correlation achieves the identification of the sign language after extracting the sign closed contour vector and performing matching between extracted vector and target alphabets vectors. The closed contour vector is generated around the hand palm centroid with position optimized by a particle swarm optimization algorithm search. Finally, a multi-objective function is used for computing the recognition score. The results presented in this paper for skin color segmentation, centroid search and pattern recognition show high effectiveness of the novel artificial vision engine.
关键词： Skin-color,Pattern recognition,Sign language,Segmentation,Particle Swarm Optimization,Human-Machine Interaction
更新于2025-09-19 17:15:36
-
Neuroergonomics || Why is Eye Tracking an Essential Part of Neuroergonomics?
摘要： Neuroergonomics generally promotes the use of brain imaging techniques or electroencephalography to measure the neural mechanisms underpinning human performance in complex real-life situations, so eye tracking is not the first type of neuroergonomics method that comes to mind. Why bring eye movements and pupillary changes into neuroergonomics? Human vision is tightly coupled to a majority of our activities, and vision provides the brain with a wealth of information. It is difficult, though not impossible, to imagine, for example, an aircraft pilot with visual impairment. The eyes are an important mediator between the environment and the brain, facilitating interaction with our everyday world. Our eyes constantly move to direct our foveas (the small region of the central retina that has highest visual acuity) to objects of interest. Light passes through the pupil to the retina, which then nervates to the brain. Importantly, the retina is a part of the embryonic diencephalon that progressively evolves into a complex connection using several neural pathways to support visual perception and attentional orientation. Hence eye tracking, though an indirect measure of brain activity, is in a way the technique that measures with the closest proximity to the brain–the retina is in fact the only part of the brain visible (e.g., to an optometrist) by the naked eye.
关键词： Pupillometry,Eye Movements,Neuroergonomics,Eye Tracking,Human-Machine Interaction
更新于2025-09-10 09:29:36