Deep spatiotemporal LSTM network with temporal pattern feature for 3D human action recognition

Wu, Yirui; Wei, Lianglei; Duan, Yucong

doi:10.1111/coin.12207

Cited by 10 publications

(6 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the objects z 1 and z 2 in the surrounding environment are measured; then, the distance between the dynamic human motion and the marker is calculated to achieve targeting localization, and finally, the human localization of motion, object localization, and the 3D spatial information e 2 are accurately calculated. At the moment k, from the estimated camera gesture z k , the results are shown in (4).…”

Section: Tracking Object Of Determinedmentioning

confidence: 99%

“…Relevant researchers worldwide have made some achievements in the research of this field, which have been applied to various other fields [3]. For instance, in robot vision, the camera can be used to recognize objects; thus, finally, the target object can be grasped [4]. In addition, in some disaster rescue, accurate positioning of the trapped can be realized through target tracking, thus shortening the time for search and rescue [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gesture Tracking and Recognition Algorithm for Dynamic Human Motion Using Multimodal Deep Learning

Xia

Xing

2022

Security and Communication Networks

View full text Add to dashboard Cite

To address the problems of the traditional human motion gesture tracking and recognition methods, such as poor tracking effect, low recognition accuracy, high frame loss rate, and long-time cost, a dynamic human motion gesture tracking and recognition algorithm using multimode deep learning was proposed. Firstly, the collected human motion images are repaired in the three-dimensional (3D) environment, and the multimodal 3D human motion model is reconstructed using the processed images. Secondly, according to the results of model reconstruction, the camera gesture and other parameters of the keyframe are used to construct the target tracking optimization function so as to achieve the purpose of accurate tracking of human motion. Finally, for multimodal human motion gesture learning, a convolutional neural network (CNN) is developed. The trained CNN is utilized to complete dynamic human motion recognition after convolutional and pooling calculations. The results demonstrate that the proposed algorithm is effective in tracking human motion gestures. The average recognition accuracy is 96%, the average frame loss rate is 8.8%, the time cost is low, and the proposed algorithm has a high F-measure and much lower power consumption than other algorithms, indicating that the proposed algorithm is effective.

show abstract

Section: Tracking Object Of Determinedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gesture Tracking and Recognition Algorithm for Dynamic Human Motion Using Multimodal Deep Learning

Xia

Xing

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…It can be seen that whether an athlete can complete a highquality whipping action in a game directly affects the outcome of the game [4]. According to the technical statistics of the 216 men's games in the 2010 National Sanda Championships, the use of whip legs accounted for 78.25% of all leg techniques and 39.51% of the entire Sanda technique [5]. The use rate of leg techniques was significantly higher than that of any other movements.…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Image Analysis and Training Method of Action Characteristics of Sanda Whip Leg Technique Based on Wavelet Transform

Song

2022

Advances in Multimedia

View full text Add to dashboard Cite

The whip leg technique is an indispensable offensive action for high-level Sanda athletes in the competition. In order to improve the effective guidance of the action of Wushu Sanda whip leg, based on wavelet transform, the three-dimensional image analysis of Sanda whip leg technical action characteristics, to explore the movement speed of each link of the attacking leg, the contraction form, and force sequence of major muscles or muscle groups and put forward correct and reasonable movement techniques, is expected to provide theoretical basis and reference for coaches and athletes in the training of Sanda whip leg movement. Based on this, this paper attempts to use the three-dimensional image analysis system and surface electromyography acquisition system from the perspective of wavelet transform to collect the speed of the attacking leg movement and the parameters related to muscle discharge and to quantitatively analyze and evaluate its movements. The sequence of activities of the whip leg strike is hip joint-knee joint-hip joint-knee joint-ankle joint. It is suggested to strictly follow the principle of link movement in practice, and the completion of the whole movement should be relaxed and natural.

show abstract

“…The fusion approach in [60] proposes to learn spatial features of individual 3D skeletons using CNN and then train an LSTM network on top of such features. In [61], multi-modal features are first extracted from the input actions and then fused by an autoencoder network. In [62], the authors propose to fuse the RGB and 3D skeleton modalities.…”

Section: ) Fusion Methodsmentioning

confidence: 99%

Content-Based Management of Human Motion Data: Survey and Challenges

et al. 2021

View full text Add to dashboard Cite

Digitization of human motion using skeleton representations offers exciting possibilities for a large number of applications but, at the same time, requires innovative techniques for their effective and efficient processing. Content-based processing of skeleton data has developed rapidly in recent years, focusing mainly on specialized prototypes with limited consideration of generic data management possibilities. In this survey article, we synthesize and categorize the existing approaches and outline future research challenges brought by the increasing availability of human motion data. In particular, we first discuss the problems of suitable representation and segmentation of continuous skeleton data obtained from various sources. Then, we concentrate on comparison models for assessing the similarity of time-restricted pieces of motions, as required by any content-based management operation. Next, we review the techniques for evaluating similarity queries over collections of motion sequences and filtering query-relevant parts from continuous motion streams. Finally, we summarize the usability of existing techniques in perspective application domains and discuss the new challenges related to current technological and infrastructural developments. We especially assess the existing techniques from the perspective of scalability and propose future research directions for dealing with large and diverse volumes of skeleton data.

show abstract

Deep spatiotemporal LSTM network with temporal pattern feature for 3D human action recognition

Cited by 10 publications

References 68 publications

Gesture Tracking and Recognition Algorithm for Dynamic Human Motion Using Multimodal Deep Learning

Gesture Tracking and Recognition Algorithm for Dynamic Human Motion Using Multimodal Deep Learning

Three-Dimensional Image Analysis and Training Method of Action Characteristics of Sanda Whip Leg Technique Based on Wavelet Transform

Content-Based Management of Human Motion Data: Survey and Challenges

Contact Info

Product

Resources

About