Shot Boundary Detection Algorithm Based on HSV Histogram and HOG Feature

Shao, Hong; Qu, Yang; Cui, Wencheng

doi:10.2991/icaemt-15.2015.181

Cited by 17 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shot Boundary Detection is a classical task to detect shot transitions due to video editing such as scene cuts, fades/dissolves, and panning. Some recent works are [5,16,50,43,48]. These shot boundaries are well-defined and an overcomplete set is easy to detect since the changes between shots are often significant.…”

Section: Related Workmentioning

confidence: 99%

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Shou¹,

Lei²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks. Conventional work in temporal video segmentation and action detection focuses on localizing pre-defined action categories and thus does not scale to generic videos. Cognitive Science has known since last century that humans consistently segment videos into meaningful temporal chunks. This segmentation happens naturally, with no pre-defined event categories and without being explicitly asked to do so. Here, we repeat these cognitive experiments on mainstream CV datasets; with our novel annotation guideline which addresses the complexities of taxonomy-free event boundary annotation, we introduce the task of Generic Event Boundary Detection (GEBD) and the new benchmark Kinetics-GEBD. Through experiment and human study we demonstrate the value of the annotations. We view this as an important stepping stone towards understanding the video as a whole, and believe it has been previously neglected due to a lack of proper task definition and annotations. Further, inspired by the cognitive finding that humans mark boundaries at points where they are unable to predict the future accurately, we explore un-supervised approaches based on temporal predictability. We identify and extensively explore important design factors for GEBD models on the TAPOS dataset and our Kinetics-GEBD while achieving competitive performance and suggesting future work. We will release our annotations and code at CVPR'21 LOVEU Challenge: https://sites.google.com/ view/loveucvpr21

show abstract

Section: Related Workmentioning

confidence: 99%

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Shou¹,

Lei²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Authors in [1], [29] exploit the color histogram features approaches like Hue Saturation Value (HSV) and Histogram of Gradient (HOG) for detecting the abrupt transition. This HSV color histogram and HOG feature approaches are utilized as the primary and secondary approach for the shot detection, which helps to increase the proficiency of these approaches.…”

Section: Literature Surveymentioning

confidence: 99%

Hybrid Method of Video Shot Segmentation Based on YCbCr Space Color Model

Nayak

Majumdar

2021

JERR

View full text Add to dashboard Cite

In this digital world, Video analysis is the most important and useful task. Currently, tremendous tasks have been done in video analysis like compressing the videos, video retrieval process and video database indexing, etc. For all these tasks, one common step is segmenting the video shots, which are referred to as Video Shots Segmentation (VSS). Video shots segmentation is used to segment the input videos into a number of frames sequentially where the scene changes occurred, i.e. called shots. In this article, segmenting the video shots follows a hybrid procedure. Here, we have introduced the moments of colors, distance metrics and threshold techniques. All the videos follow the above mentioned steps for segmenting the video shots. But, before that, the input video is converted into a specific color model i.e. YCbCr. Then, apply the color moments to extract the feature vectors of frames, which are differentiated based on the color features of frames. In every two frames of the video, distance metrics methods are applying to compute the similarity and dissimilarity of frames. And the dissimilarity of the frames can be computed by using the threshold technique to get the shots from the video. In this paper, we are using the adaptive threshold technique to segment the videos into various shots. In this step, we will get a true number of shots. By the experimental results, this proposed methodology can be evaluated with the sequence of videos based on the performance or evaluation metrics.

show abstract

“…Later, few advancements like color histogram, SIFT features, color coherence vector, gray level co-occurrence matrix and so-on have been widely used to characterize the frame level features in-order to detect the shot boundaries. Shao et al [3] have used HSV histogram and histogram of oriented gradients (HOG) to represent the subsequent frames in the video and the transitions were detected by threshold approach. Video shot boundary detection using block based cumulative approach is developed in [4].…”

Section: Introductionmentioning

confidence: 99%

Pyramidal-Relative Entropy Based Temporal Signature for Video Transition Detection using LSTM

Sasithradevi

Roomi²,

Gupta

2022

Preprint

View full text Add to dashboard Cite

Video transition detection (VTD) is a significant topic in the field of video analytics, owing to its useful applications in video indexing, video surveillance, and video understanding. The challenge in VTD is to extract the complex temporal variations caused by the change in illumination, rapid motion of object and camera. To address these challenges, a pyramidal-relative en-tropy based long-short term memory (LSTM) framework is proposed. Initially, the uncompressed video frame is modeled using pyramidal attributes. Then, the temporal signature is generated based on forward-backward ratio of relative entropy measure. The LSTM network is trained to detect the transitions through temporal signature and categorizes them as no transition, abrupt transition and gradual transition. Benchmarks namely TRECVID 2001, TRECVID 2007, VIDEO-SEG2004, RAI and BBC data-sets have been used in evaluation assessments. The simulation results illustrate the efficacy of the proposed framework to achieve an average F 1 score of 95.5±0.06%, 98.51±0.79%, 97.5 ±2.6%, 93.54±5.03%, and 97.58±1.89% on TRECVID 2001, TRECVID 2007 VIDEOSEG 2004, RAI and BBC data-sets, respectively.

show abstract

Shot Boundary Detection Algorithm Based on HSV Histogram and HOG Feature

Cited by 17 publications

References 6 publications

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Hybrid Method of Video Shot Segmentation Based on YCbCr Space Color Model

Pyramidal-Relative Entropy Based Temporal Signature for Video Transition Detection using LSTM

Contact Info

Product

Resources

About