Action recognition using spatio-temporal differential motion

Yadav, Gaurav; Sethi, Amit

doi:10.1109/icip.2017.8296916

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The content difference between frames is identified with the help of its color features in a hue histogram. This is followed by the shot view classification (Yadav and Sethi, 2017) which provides the clues for the pattern in which the possibility of an event can occur. Segmentation is done to identify the region, that is, the playing field, with the dominant color property as well as the average size of the player.…”

Section: Proposed Systemmentioning

confidence: 99%

RETRACTED: Sports highlight recognition and event detection using rule inference system

Soundararajan

Mala

2022

Concurrent Engineering

View full text Add to dashboard Cite

Computer vision in sport is a very interesting application. People spend a lot of time watching sports videos because this is one of the best field of entertainment. Sports video broadcasts generally take a lot of time, ranging from two to four hours. However, the interesting part happens for just a few minutes. Detecting the highlighted event in a sport will be useful for people who like to watch only the prominent events section instead of watching the whole video broadcast. Event detection will give precise details about the action that occurred for a particular time, but the detection of highlighted events is more complex. This is due to the fact that a sports video contains collections of events. Among them, segregation of the required event is a time-consuming process but it requires more knowledge about the sport as well as processing time. Hence, a novel work is proposed focused on identifying the location of the functional object using agglomerative clustering and annotating the event highlights automatically by means of the rule inference mechanism. The SHRED (Sports Highlight Recognition and Event Detection) system achieves an overall accuracy of about 97.38% relative to other state-of-art methods in event class annotation.

show abstract

Section: Proposed Systemmentioning

confidence: 99%

RETRACTED: Sports highlight recognition and event detection using rule inference system

Soundararajan

Mala

2022

Concurrent Engineering

View full text Add to dashboard Cite

show abstract

“…Motion map + MBH [40] 75.13 Two-stream LSTM [41] 94.60 Differential motion [42] 90.24 CNN+TR-LSTM [43] 93.80 CNN+LSTM [43] 92.30 Proposed 92.90…”

Section: Methodsmentioning

confidence: 99%

Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation

Huang¹

2021

Preprint

View full text Add to dashboard Cite

Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action understanding task. It is vital to encode the spatialtemporal information of event data properly and use standard computer vision tool to learn from the data. In this work, we propose a timestamp image encoding 2D network, which takes the encoded spatial-temporal images with polarity information of the event data as input and output the action label. In addition, we propose a future timestamp image generator to generate future action information to aid the model to anticipate the human action when the action is not completed. Experiment results show that our method can achieve the same level of performance as those RGB-based benchmarks on real world action recognition, and also achieve the state of the art (SOTA) result on gesture recognition. Our future timestamp image generating model can effectively improve the prediction accuracy when the action is not completed. We also provide insight discussion on the importance of motion and appearance information in action recognition and anticipation.

show abstract

“…Through 3D video analysis, Rezazadegan et al [24] collected the kinematic images and data of the basic movements of women's floor exercise, and quantified the dynamics and kinematics features of athletes in landing, using a simulation model of the actual movement process. Yadav and Sethi [25] explored the movement features, laws, and characteristics of the triple jumps of single figure skaters, and discussed the correlation of movement standardization with the coordination between upper and lower limbs, movement time, center of gravity, as well as the angles and speeds of upper and lower limbs.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Wrong Sports Movements Based on Deep Neural Network

Wang¹

2020

RIA

View full text Add to dashboard Cite

During physical education (PE), the teaching quality is severely affected by problems like nonstandard technical movements or wrong demonstrative movements. High-speed photography can capture instantaneous movements that cannot be recognized with naked eyes. Therefore, this technology has been widely used to judge the sprint movements in track and field competitions, and assess the quality of artistic gymnastics. Inspired by three-dimensional (3D) image analysis, this paper proposes a method to recognize the standard and wrong demonstrative sports movements, based on 3D convolutional neural network (CNN) and graph theory. Firstly, a 3D posture perception strategy for demonstrative sports movements was constructed based on video sequence. Next, the authors provided the framework of the recognition system for standard and wrong demonstrative sports movements. After that, a 3D CNN was stablished to distinguish between standard and wrong demonstrative sports movements. The proposed method was proved effective and superior through experiments. The research results provide a good reference for the application of 3D image analysis in the recognition of other body behaviors and movements.

show abstract

Action recognition using spatio-temporal differential motion

Cited by 5 publications

References 14 publications

RETRACTED: Sports highlight recognition and event detection using rule inference system

RETRACTED: Sports highlight recognition and event detection using rule inference system

Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation

Recognition of Wrong Sports Movements Based on Deep Neural Network

Contact Info

Product

Resources

About