Key frame extraction based on global motion statistics for team-sport videos

Yuan, Yuan; Lu, Zheng; Yang, Zhou; Jian, Meng; Wu, Lifang; Li, Zeyu; Liu, Xu

doi:10.1007/s00530-021-00777-7

Cited by 16 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It facilitates effective analysis, visualization and communication of underlying information [9]. Numerous techniques have been developed in the literature [10], including shot recognition, video frame clustering [11], and motion-based algorithms [12]. Modern algorithms have been utilized for video indexing, browsing, and retrieval since they have demonstrated their performance [9].…”

Section: Related Workmentioning

confidence: 99%

Deep AngioKey: A Novel Approach for Objective Keyframe Extraction in Coronary Angiography Analysis

Moalla,

Ghrab,

Bahloul

et al. 2023

Preprint

View full text Add to dashboard Cite

Coronary angiography represents the GOLD standard for diagnosing and treating obstructive coronary artery disease. Its analysis relies on cardiologist?s visual assessment which is subjective and leads to inter-observer variability and different treatment strategies. Objective methods have been proposed and implemented in catheterization laboratories. However, their input is manually chosen by the cardi-ologist. In this paper, we present a new coronary angiogram keyframe extraction, Deep AngioKey. It is based on feature extraction. The frame with the highest vessel structure was identified as keyframe. Feature extraction was done using a U-Net model trained for binary vessel segmentation. Our solution surpassed existing methods and reached an overall accuracy of 98.1% in keyframe identification with an average main frame distance of 1.63.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep AngioKey: A Novel Approach for Objective Keyframe Extraction in Coronary Angiography Analysis

Moalla,

Ghrab,

Bahloul

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…If a lens mutation occurs between frames 3 N = and G and G+1, then the constant sequence ( ) sw K b is (1,3,6,6,3,1). Set the a frame lens boundary similarity factor to:…”

Section: Edge Detection Of Motion Videomentioning

confidence: 99%

“…Therefore, it is essential to realize the effective processing and query of video and to classify it automatically. In medical care, network supervision, intelligent video surveillance, and other fields, automatic video classification are also of great significance: for example, classifying videos to screen out harmful videos to meet network supervision needs and ensure online video quality [1]. An image classification algorithm is used for wireless endoscopy images in medical treatment.…”

Section: Introductionmentioning

confidence: 99%

Video Shot Boundary Detection and Sports Video Classification Algorithm Based on Particle Filter

Chen,

2023

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

INTRODUCTION: Sports video is a very important information resource. The classification of sports video with high accuracy can effectively improve the browsing and query effect of users. This project intends to study a motion video classification algorithm based on deep learning particle filter to solve the problems of strong subjectivity and low accuracy of existing motion video classification algorithms. A key box extraction method based on similarity is proposed. The moving video classification algorithm based on deep learning coding model is studied. Examples of various types of sports videos are analyzed. The overall performance of the motion video classification algorithm proposed in this paper is much better than other existing motion video classification algorithms. This algorithm can greatly improve the classification performance of motion video.

show abstract

“…Jian et al [24] extracted the KFs of sports videos, considering the neighboring probability difference of frames, and these probabilities were estimated from a CNN on extracted region of interest areas. Yuan et al [25] introduced a global motion model to extract candidate KFs; spatial-temporal consistency and hierarchical clustering were used to extract KFs.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

Unsupervised Few Shot Key Frame Extraction for Cow Teat Videos

Zhang

Wieland

Basran

2022

Data

View full text Add to dashboard Cite

A novel method of monitoring the health of dairy cows in large-scale dairy farms is proposed via image-based analysis of cows on rotary-based milking platforms, where deep learning is used to classify the extent of teat-end hyperkeratosis. The videos can be analyzed to segment the teats for feature analysis, which can then be used to assess the risk of infections and other diseases. This analysis can be performed more efficiently by using the key frames of each cow as they pass through the image frame. Extracting key frames from these videos would greatly simplify this analysis, but there are several challenges. First, data collection in the farm setting is harsh, resulting in unpredictable temporal key frame positions; empty, obfuscated, or shifted images of the cow’s teats; frequently empty stalls due to challenges with herding cows into the parlor; and regular interruptions and reversals in the direction of the parlor. Second, supervised learning requires expensive and time-consuming human annotation of key frames, which is impractical in large commercial dairy farms housing thousands of cows. Unsupervised learning methods rely on large frame differences and often suffer low performance. In this paper, we propose a novel unsupervised few-shot learning model which extracts key frames from large (∼21,000 frames) video streams. Using a simple L1 distance metric that combines both image and deep features between each unlabeled frame and a few (32) labeled key frames, a key frame selection mechanism, and a quality check process, key frames can be extracted with sufficient accuracy (F score 63.6%) and timeliness (<10 min per 21,000 frames) for commercial dairy farm setting demands.

show abstract

Key frame extraction based on global motion statistics for team-sport videos

Cited by 16 publications

References 41 publications

Deep AngioKey: A Novel Approach for Objective Keyframe Extraction in Coronary Angiography Analysis

Deep AngioKey: A Novel Approach for Objective Keyframe Extraction in Coronary Angiography Analysis

Video Shot Boundary Detection and Sports Video Classification Algorithm Based on Particle Filter

Unsupervised Few Shot Key Frame Extraction for Cow Teat Videos

Contact Info

Product

Resources

About