Key-Frame Detection and Video Retrieval Based on DC Coefficient-Based Cosine Orthogonality and Multivariate Statistical Tests

Kalakoti, Gowrisankar; Prabakaran, G.

doi:10.18280/ts.370509

Cited by 5 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature [20] puts forward a new detection method, and its performance is greatly improved compared with the traditional one-stage and two-stage framework, especially in the real-time situation, and its accuracy is much higher than YOLOV3 at the same rate. Literatures [21,22] use NN (nearest neighbor) classifier to judge whether tracking is successful or not. Neural network classifier can measure the similarity between the collected correct image and the current new target image.…”

Section: Related Workmentioning

confidence: 99%

A Method of Key Posture Detection and Motion Recognition in Sports Based on Deep Learning

Pan

2022

Mobile Information Systems

View full text Add to dashboard Cite

Moving target recognition and analysis is an important research direction in the field of computer vision, which is widely used in our life, such as intelligent robot, video surveillance, medical education, sports competition, and national defense security. By analyzing the video of weightlifting, this paper extracts the key postures of athletes’ training, so as to assist coaches to train athletes more professionally. Based on DL (Deep Learning), a key pose extraction method of sports video (RoI_KP for short) based on classified learning of regions of interest is proposed. By fine-tuning CNN (Convolutional Neural Network), a network model suitable for video classification of weightlifting in the region of interest is obtained. Finally, according to the classification results, the selection strategy of classification results is designed to extract key poses. According to the characteristics of different modal information, different DNN (deep neural network) is adopted, and various depth networks are combined to mine the multi-modal spatio-temporal depth features of human movements in video. Experimental results show that the method proposed in this paper is very competitive.

show abstract

Section: Related Workmentioning

confidence: 99%

A Method of Key Posture Detection and Motion Recognition in Sports Based on Deep Learning

Pan

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…In CBIR and CBVR schemes, color characteristics play an important role and are explored in various color spaces, such as RGB, HSV, YCrCb, LAB and LUV [5]. For image and video indexing and retrieval, several different color functions are available, including color histogram (CH), color moments (CM), color coherence vector (CCV), fuzzy color histogram (FCH) [6]- [10]. The color spaces of HSV, YIQ, LAB, YCrCb and I1I2I3 have rich human vision and more discriminatory control than RGB, so they can be used to reflect colors instead of RGB instead of RGB [11], [12].…”

Section: Literature Reviewmentioning

confidence: 99%

Content-Based Video Retrieval Based on Multifaceted Feature Extraction Using Statistical Methods

Kalakoti¹,

Prabakaran²

2022

ECS Trans.

View full text Add to dashboard Cite

For content-dependent video recovery, this paper proposes a multifaceted feature extraction approach based on color string extraction, local texture characteristics, and amount of Absolute Difference, which extracts the features such as color components , texture components, and motion behavior. The color string function is derived using the string duration count, and the color histogram approach is used for detecting scene shifts. Based on scene shift recognition, the key-frames are retrieved. Based on the color string and local texture functions, the color and texture characteristics are derived from the key-frame. The Amount of Absolute Difference is measured, and the motion function of a video is derived using it. To compare the function vectors of the question and main frames of the video to be recovered, the Jeffrey's Divergence measure is implemented. The suggested approach has the greatest capture of both spatial and temporal aspects, and the recovery efficiency is increased by utilizing multifaceted features. The system suggested outperforms the current approaches.

show abstract

“…One depends on foundation displaying which attempts to make an appropriate foundation for each casing of the succession by utilizing a movement content extraction technique. Another is direction arrangement in which long directions are registered for features focuses utilizing a proper tracker and next a grouping approach is utilized to separate the directions having a place with similar content from those of basic models [11,12]. Another procedure is to expand foundation of feature removal techniques dependent on low position and insufficient pattern deterioration created for the instance of static cameras for the instance of a moving camera.…”

Section: Literature Surveymentioning

confidence: 99%

Feature Extraction Model with Group-Based Classifier for Content Extraction from Video Data

Kalakoti¹,

Prabakaran²

2021

RIA

Self Cite

View full text Add to dashboard Cite

In today's PC illustration, numerous object locations of videos are quite critical duties to accomplish. Swiftly and reliably recognising and distinguishing the multiple aspects of a video is a crucial attribute for collaborating with one's condition (object). The core issue is that in theory, to ensure that no significant aspect is missing; all aspects of a content in a video must be scanned for elements on various different scales. It requires some investment and effort anyway, to really arrange the substance of a given content region and both time and computational limits that an operator can spend on classification are constrained. Two presumption procedures for accelerating the standard identifier are performed by the proposed method and demonstrate their capability by performing both identification efficiency and velocity. The main enhancement of our group-based classifier focuses on accelerating the grouping of sub features by planning the problem as a selection procedure for consecutive features. The subsequent improvement gives better multiscale features to distinguish objects of all sizes without rescaling the information image from a video. Extracting contents from video is an assortment of successive images with a steady time interim. So video can give more data about contents in it when situations are changing regarding time. Along these lines, physically taking care of contents with features are very unimaginable. In the proposed work, it is suggested that a Group-based Video Content Extraction Classifier (GbCCE) extracts content from a video by extracting relevant features using a group-based classifier. The proposed method is distinct from conventional approaches and the findings indicate that better output is demonstrated by the proposed method.

show abstract

Key-Frame Detection and Video Retrieval Based on DC Coefficient-Based Cosine Orthogonality and Multivariate Statistical Tests

Cited by 5 publications

References 53 publications

A Method of Key Posture Detection and Motion Recognition in Sports Based on Deep Learning

A Method of Key Posture Detection and Motion Recognition in Sports Based on Deep Learning

Content-Based Video Retrieval Based on Multifaceted Feature Extraction Using Statistical Methods

Feature Extraction Model with Group-Based Classifier for Content Extraction from Video Data

Contact Info

Product

Resources

About