Head Gesture-Based on IMU Sensors: a Performance Comparison Between the Unimodal and Multimodal Approach

Severin, Ionuţ-Cristian

doi:10.1109/isscs52333.2021.9497434

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their classification results achieved an accuracy of 97.5%. Severin et al [13][14][15] tested some classification methods based on IMU data and found that when using 16 features from the head motion time series, most classifiers can achieve a completely accurate classification. However, these studies did not cover the endpoint detection methods for head motion time series data, and endpoint detection is a necessary step for the real-time segmentation of head motion time series data.…”

Section: Methods For Head Motion Recognitionmentioning

confidence: 99%

“…The former achieved a complete and correct classification except for the kNN algorithm [14]. When analyzing the impact of the number of sensors on classification results, it was found that a system with three sensors can achieve better classification results [15]. However, in an experiment, the three sensors were installed in completely different locations compared to the single sensor, which makes it difficult to draw a significant comparison between the two.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Head Gesture Recognition Combining Activity Detection and Dynamic Time Warping

Li,

2024

J. Imaging

View full text Add to dashboard Cite

The recognition of head movements plays an important role in human–computer interface domains. The data collected with image sensors or inertial measurement unit (IMU) sensors are often used for identifying these types of actions. Compared with image processing methods, a recognition system using an IMU sensor has obvious advantages in terms of complexity, processing speed, and cost. In this paper, an IMU sensor is used to collect head movement data on the legs of glasses, and a new approach for recognizing head movements is proposed by combining activity detection and dynamic time warping (DTW). The activity detection of the time series of head movements is essentially based on the different characteristics exhibited by actions and noises. The DTW method estimates the warp path distances between the time series of the actions and the templates by warping under the time axis. Then, the types of head movements are determined by the minimum of these distances. The results show that a 100% accuracy was achieved in the task of classifying six types of head movements. This method provides a new option for head gesture recognition in current human–computer interfaces.

show abstract

Section: Methods For Head Motion Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%