A Real-time Posture Recognition System using YOLACT++ and ResNet18

Lin, Jiacheng; Hsieh, Chen-Chiung

doi:10.1109/icce-tw52618.2021.9602910

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, MediaPipe exhibited the fastest processing speed (12 FPS) with a significant number of incorrect keypoint predictions (16) and missing keypoints (43). OpenPose, while achieving a processing speed of 1 FPS, suffered from even more incorrect keypoint predictions (24) and missing keypoints (9).…”

Section: Mmpose Methodsmentioning

confidence: 99%

“…Integrating YOLACT can significantly improve the precision of action recognition tasks and enhance scene analysis. Lin et al [ 24 ] proposed a system that leverages YOLACT++ for precise human body part segmentation and identification. This information is then combined with the feature extraction capabilities of ResNet18, allowing the system to learn distinctive features and achieve accurate posture classification.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Human Action Recognition and Note Recognition: A Deep Learning Approach Using STA-GCN

Enkhbat,

Shih,

Cheewaprakobkit

2024

Sensors

View full text Add to dashboard Cite

Human action recognition (HAR) is growing in machine learning with a wide range of applications. One challenging aspect of HAR is recognizing human actions while playing music, further complicated by the need to recognize the musical notes being played. This paper proposes a deep learning-based method for simultaneous HAR and musical note recognition in music performances. We conducted experiments on Morin khuur performances, a traditional Mongolian instrument. The proposed method consists of two stages. First, we created a new dataset of Morin khuur performances. We used motion capture systems and depth sensors to collect data that includes hand keypoints, instrument segmentation information, and detailed movement information. We then analyzed RGB images, depth images, and motion data to determine which type of data provides the most valuable features for recognizing actions and notes in music performances. The second stage utilizes a Spatial Temporal Attention Graph Convolutional Network (STA-GCN) to recognize musical notes as continuous gestures. The STA-GCN model is designed to learn the relationships between hand keypoints and instrument segmentation information, which are crucial for accurate recognition. Evaluation on our dataset demonstrates that our model outperforms the traditional ST-GCN model, achieving an accuracy of 81.4%.

show abstract

Section: Mmpose Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%