Touchless Head-Control (THC): Head Gesture Recognition for Cursor and Orientation Control

Rahmaniar, Wahyu; Ma’arif, Alfian; Lin, Ting-Lan

doi:10.1109/tnsre.2022.3187472

Cited by 8 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the system reached 70.5% in one of the tested conditions. Rahmaniar et al ( 2022 ); on the other hand, proposed a head gesture recognition interface for cursor control that also achieved high target selection scores. Chin ( 2008 ) showed in a study of with HMIs that compared the use of EMG, eye tracking, and a combination of both as solutions for cursor control for users with motor disabilities that, although the hybrid solution has a slower control than eye-tracking only, it was more reliable for click operations.…”

Section: Discussionmentioning

confidence: 99%

Human-machine interface for two-dimensional steering control with the auricular muscles

et al. 2023

View full text Add to dashboard Cite

Human-machine interfaces (HMIs) can be used to decode a user's motor intention to control an external device. People that suffer from motor disabilities, such as spinal cord injury, can benefit from the uses of these interfaces. While many solutions can be found in this direction, there is still room for improvement both from a decoding, hardware, and subject-motor learning perspective. Here we show, in a series of experiments with non-disabled participants, a novel decoding and training paradigm allowing naïve participants to use their auricular muscles (AM) to control two degrees of freedom with a virtual cursor. AMs are particularly interesting because they are vestigial muscles and are often preserved after neurological diseases. Our method relies on the use of surface electromyographic records and the use of contraction levels of both AMs to modulate the velocity and direction of a cursor in a two-dimensional paradigm. We used a locking mechanism to fix the current position of each axis separately to enable the user to stop the cursor at a certain location. A five-session training procedure (20–30 min per session) with a 2D center-out task was performed by five volunteers. All participants increased their success rate (Initial: 52.78 ± 5.56%; Final: 72.22 ± 6.67%; median ± median absolute deviation) and their trajectory performances throughout the training. We implemented a dual task with visual distractors to assess the mental challenge of controlling while executing another task; our results suggest that the participants could perform the task in cognitively demanding conditions (success rate of 66.67 ± 5.56%). Finally, using the Nasa Task Load Index questionnaire, we found that participants reported lower mental demand and effort in the last two sessions. To summarize, all subjects could learn to control the movement of a cursor with two degrees of freedom using their AM, with a low impact on the cognitive load. Our study is a first step in developing AM-based decoders for HMIs for people with motor disabilities, such as spinal cord injury.

show abstract

Section: Discussionmentioning

confidence: 99%

Human-machine interface for two-dimensional steering control with the auricular muscles

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As with previous related work that make human-computer interfaces for disabled people [11][12][13][14][15], the tests were conducted with non-disabled people as a first step due to the limited access to disabled participants. The results obtained allowed to identify usability characteristics that needed to be improved prior to the testing phase with people with disabilities.…”

Section: Discussionmentioning

confidence: 99%

“…When users used EMKEY voice commands, they obtained better results than just using their head to move the car. By using this functionality, it is proven that the emulator can be more useful and user-friendly for interacting with computers in comparison with the studies in [15,48] which are systems that control the use of the computer using only head movements and simple gestures. Implementing voice commands eliminates the need for users to make awkward facial gestures to emulate actions such as clicking.…”

Section: Discussionmentioning

confidence: 99%

“…These technologies are intended to provide support and assistance to people with a variety of disabilities, including mobility [2,3], vision [4] and hearing impairments [5], and cognitive disabilities [6]. It includes a variety of hardware and software approaches that apply the latest advances in technology, such as: speech recognition [7,8], computer vision [9], brain-computer interfaces [10], eye tracking [11], head and face tracking [12][13][14][15], etc. The purpose of assistive technology is to facilitate the performance of tasks that would otherwise be difficult or impossible for individuals with disabilities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Evaluation of EMKEY: An Assistive Technology for People with Upper Limb Disabilities

Zapata

Valencia-Aragón

Ramos-Galarza

2023

Sensors

View full text Add to dashboard Cite

Assistive technology can help people with disabilities to use computers more effectively and can enable them to access the same information and resources as people without disabilities. To obtain more insight into the factors that can bring about the design of an Emulator of Mouse and Keyboard (EMKEY) to higher levels of user satisfaction, an experimental study was conducted in order to analyse its effectiveness and efficiency. The experimental study involved 27 participants (Mage = 20.81, SD = 1.14) who performed three experimental games under different conditions (using the mouse and using EMKEY with head movements and voice commands). According to the results, the use of EMKEY allowed for the successful performance of tasks such as matching stimuli (F (2, 78) = 2.39, p = 0.10, η2 = 0.06). However, the execution times of a task were found to be higher when using the emulator to drag an object on the screen (t (52, 1) = −18.45, p ≤ 0.001, d = 9.60). These results indicate the effectiveness of technological development for people with upper limb disabilities; however, there is room for improvement in terms of efficiency. The findings are discussed in relation to previous research and are based on future studies aimed at improving the operation of the EMKEY emulator.

show abstract

“…Subsequently, at runtime, the options of the nearby virtual surroundings area unit are continuously extracted and used as input variables in the neural network to create a sound reproduction of character animation. Traditional object recognition techniques accomplish object recognition by matching a set of manually selected feature rules [18][19][20]. For example, "hand" objects in digital images are recognized through the color of the skin and the shape of the hand.…”

Section: Introductionmentioning

confidence: 99%

High Speed and Accuracy of Animation 3D Pose Recognition Based on an Improved Deep Convolution Neural Network

Ding

2023

Applied Sciences

View full text Add to dashboard Cite

Pose recognition in character animations is an important avenue of research in computer graphics. However, the current use of traditional artificial intelligence algorithms to recognize animation gestures faces hurdles such as low accuracy and speed. Therefore, to overcome the above problems, this paper proposes a real-time 3D pose recognition system, which includes both facial and body poses, based on deep convolutional neural networks and further designs a single-purpose 3D pose estimation system. First, we transformed the human pose extracted from the input image to an abstract pose data structure. Subsequently, we generated the required character animation at runtime based on the transformed dataset. This challenges the conventional concept of monocular 3D pose estimation, which is extremely difficult to achieve. It can also achieve real-time running speed at a resolution of 384 fps. The proposed method was used to identify multiple-character animation using multiple datasets (Microsoft COCO 2014, CMU Panoptic, Human3.6M, and JTA). The results indicated that the improved algorithm improved the recognition accuracy and performance by approximately 3.5% and 8–10 times, respectively, which is significantly superior to other classic algorithms. Furthermore, we tested the proposed system on multiple pose-recognition datasets. The 3D attitude estimation system speed can reach 24 fps with an error of 100 mm, which is considerably less than that of the 2D attitude estimation system with a speed of 60 fps. The pose recognition based on deep learning proposed in this study yielded surprisingly superior performance, proving that the use of deep-learning technology for image recognition has great potential.

show abstract

Touchless Head-Control (THC): Head Gesture Recognition for Cursor and Orientation Control

Cited by 8 publications

References 22 publications

Human-machine interface for two-dimensional steering control with the auricular muscles

Human-machine interface for two-dimensional steering control with the auricular muscles

Experimental Evaluation of EMKEY: An Assistive Technology for People with Upper Limb Disabilities

High Speed and Accuracy of Animation 3D Pose Recognition Based on an Improved Deep Convolution Neural Network

Contact Info

Product

Resources

About