Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures
Abstract Radar‐based hand gesture recognition (HGR) has attracted growing interest in human–computer interaction. A rich diversity in how people perform gestures causes a large intra‐class variance, and the sample quality varies from person to person. It makes HGR more challenging to identify dynami...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | IET Radar, Sonar & Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rsn2.12280 |
| _version_ | 1828184395137155072 |
|---|---|
| author | Liying Wang Zongyong Cui Yiming Pi Changjie Cao Zongjie Cao |
| author_facet | Liying Wang Zongyong Cui Yiming Pi Changjie Cao Zongjie Cao |
| author_sort | Liying Wang |
| collection | DOAJ |
| description | Abstract Radar‐based hand gesture recognition (HGR) has attracted growing interest in human–computer interaction. A rich diversity in how people perform gestures causes a large intra‐class variance, and the sample quality varies from person to person. It makes HGR more challenging to identify dynamic, complicated, and deforming hand gestures. It is urgent for the real world to explore a robust method that better identifies the gestures from non‐specified users. To address the above issues, an adaptive framework is proposed for gesture recognition, and it has two main contributions. First of all, a trajectory range Doppler map (t‐RDM) is obtained by non‐coherent accumulating for inter‐frame dependencies, and then t‐RDM is enhanced to highlight the trajectory information. Taking into account different movement patterns of the gestures, a two‐pathway convolutional neural network targeted for raw and enhanced t‐RDMs is proposed, which independently mines discriminative information from the two t‐RDMs with different salient features. Second, an adaptive individual cost (AIC) loss is proposed, aiming to establish a powerful feature representation by adaptively extracting the commonalities in variant gestures according to the sample quality. Based on a public dataset using soli radar, the proposed method is evaluated on two tasks: cross‐person recognition and cross‐scenario recognition. These two recognition modes require that the training set and the test set are mutually exclusive not only at the sample level but also at the source level. Extensive experiments demonstrate that the proposed method is superior to the existing approaches for alleviating the low recognition performance caused by gesture diversity. |
| first_indexed | 2024-04-12T06:48:21Z |
| format | Article |
| id | doaj.art-9a55df1472714be9ade4d9ca5cc51a2e |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-12T06:48:21Z |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-9a55df1472714be9ade4d9ca5cc51a2e2022-12-22T03:43:28ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922022-09-011691538155310.1049/rsn2.12280Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signaturesLiying Wang0Zongyong Cui1Yiming Pi2Changjie Cao3Zongjie Cao4School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu ChinaSchool of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu ChinaSchool of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu ChinaSchool of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu ChinaSchool of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu ChinaAbstract Radar‐based hand gesture recognition (HGR) has attracted growing interest in human–computer interaction. A rich diversity in how people perform gestures causes a large intra‐class variance, and the sample quality varies from person to person. It makes HGR more challenging to identify dynamic, complicated, and deforming hand gestures. It is urgent for the real world to explore a robust method that better identifies the gestures from non‐specified users. To address the above issues, an adaptive framework is proposed for gesture recognition, and it has two main contributions. First of all, a trajectory range Doppler map (t‐RDM) is obtained by non‐coherent accumulating for inter‐frame dependencies, and then t‐RDM is enhanced to highlight the trajectory information. Taking into account different movement patterns of the gestures, a two‐pathway convolutional neural network targeted for raw and enhanced t‐RDMs is proposed, which independently mines discriminative information from the two t‐RDMs with different salient features. Second, an adaptive individual cost (AIC) loss is proposed, aiming to establish a powerful feature representation by adaptively extracting the commonalities in variant gestures according to the sample quality. Based on a public dataset using soli radar, the proposed method is evaluated on two tasks: cross‐person recognition and cross‐scenario recognition. These two recognition modes require that the training set and the test set are mutually exclusive not only at the sample level but also at the source level. Extensive experiments demonstrate that the proposed method is superior to the existing approaches for alleviating the low recognition performance caused by gesture diversity.https://doi.org/10.1049/rsn2.12280gesture recognitionhuman–computer interactionneural networkradar‐based |
| spellingShingle | Liying Wang Zongyong Cui Yiming Pi Changjie Cao Zongjie Cao Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures IET Radar, Sonar & Navigation gesture recognition human–computer interaction neural network radar‐based |
| title | Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures |
| title_full | Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures |
| title_fullStr | Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures |
| title_full_unstemmed | Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures |
| title_short | Adaptive framework towards radar‐based diversity gesture recognition with range‐Doppler signatures |
| title_sort | adaptive framework towards radar based diversity gesture recognition with range doppler signatures |
| topic | gesture recognition human–computer interaction neural network radar‐based |
| url | https://doi.org/10.1049/rsn2.12280 |
| work_keys_str_mv | AT liyingwang adaptiveframeworktowardsradarbaseddiversitygesturerecognitionwithrangedopplersignatures AT zongyongcui adaptiveframeworktowardsradarbaseddiversitygesturerecognitionwithrangedopplersignatures AT yimingpi adaptiveframeworktowardsradarbaseddiversitygesturerecognitionwithrangedopplersignatures AT changjiecao adaptiveframeworktowardsradarbaseddiversitygesturerecognitionwithrangedopplersignatures AT zongjiecao adaptiveframeworktowardsradarbaseddiversitygesturerecognitionwithrangedopplersignatures |