Real time video summarizing using image semantic segmentation for CBVR

Jain, Rahul; Jain, Pooja; Kumar, Tapan

doi:10.1007/s11554-021-01151-6

Cited by 9 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e three parameters of spatial contrast sensitivity function, brightness adaptive factor, and contrast masking factor of the digital multimedia video image are calculated, respectively. According to the product of the three parameters, the transform domain JND model of the digital multimedia video image is established, and the model is used for the quantization and coding of multimedia video multiresolution image [10,11].…”

Section: Fault Tolerant Digital Video Transmission Systemmentioning

confidence: 99%

Simulation of Video Image Fault Tolerant Coding Transmission in Digital Multimedia

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to effectively improve the quality of video image transmission, this paper proposes a method of digital multimedia video image coding. The transmission of digital multimedia video image fault-tolerant coding requires sparse decomposition of a digital multimedia video image to obtain the linear form of the image and complete the transmission of video image fault-tolerant coding. The traditional method of fault-tolerant coding is based on human visual characteristics but ignores the linear form of the digital multimedia video image, which leads to the unsatisfactory effect of coding and transmission. In this paper, a fault-tolerant coding method based on wavelet transform and vector quantization is proposed to decompose and reconstruct digital multimedia video images. The smoothness of wavelet transform can remove visual redundancy; the decomposed image is vector quantized. The mean square deviation method and the similar scalar optimal quantization method are used to select and calculate the image vector, construct the over complete database of a digital multimedia video image, and normalize it; the digital multimedia video image is thinly decomposed by asymmetric atoms, and a linear representation of the image is obtained. According to the above-given operations, we can master the distribution range and law of pixels and realize fault-tolerant coding. The experimental results show that when the number of iterations is 15, the CR index is the same, PSNR increases by 8.7%, coding is 23.7% faster and decoding is 15% faster. Conclusion. The proposed method can not only improve the speed of fault-tolerant coding but also improve the quality of video image transmission.

show abstract

Section: Fault Tolerant Digital Video Transmission Systemmentioning

confidence: 99%

Simulation of Video Image Fault Tolerant Coding Transmission in Digital Multimedia

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The author (Jain et al, 2021 ) proposed a technique for effectively summarizing videos in real time. To identify common objects, the Mask R-CNN model trained on the COCO dataset is employed.…”

Section: Literature Surveymentioning

confidence: 99%

“…Because summary evaluation is a subjective process, manual comparisons are difficult to achieve reliable results. In the video summarizing bibliography, many datasets stand out: SumMe (Choudhary et al, 2017 ; Taylor and Qureshi, 2018 ), TVSum, ADL (Yousefi et al, 2018 ), TRECKVID'08 (Ren and Jiang, 2009 ), and COCO (Jain et al, 2021 ) rushes require a thorough video summary. The dataset used in Table 2 is shown in Figure 7 .…”

Section: Literature Surveymentioning

confidence: 99%

From video summarization to real time video summarization in smart cities and beyond: A survey

Shambharkar

Goel

2023

Front. Big Data

View full text Add to dashboard Cite

With the massive expansion of videos on the internet, searching through millions of them has become quite challenging. Smartphones, recording devices, and file sharing are all examples of ways to capture massive amounts of real time video. In smart cities, there are many surveillance cameras, which has created a massive volume of video data whose indexing, retrieval, and administration is a difficult problem. Exploring such results takes time and degrades the user experience. In this case, video summarization is extremely useful. Video summarization allows for the efficient storing, retrieval, and browsing of huge amounts of information from video without sacrificing key features. This article presents a classification and analysis of video summarization approaches, with a focus on real-time video summarization (RVS) domain techniques that can be used to summarize videos. The current study will be useful in integrating essential research findings and data for quick reference, laying the preliminaries, and investigating prospective research directions. A variety of practical uses, including aberrant detection in a video surveillance system, have made successful use of video summarization in smart cities.

show abstract

“…We expanded on previous work from (Machireddy et al, 2021), where authors showed that a sparsely manually annotated dataset, typically around 1% of the image stack, was sufficient to train models to segment the whole volume. While state-of-the-art in semantic segmentation has been dominated by attention-based models for natural images (Jain et al, 2021), convolutional architectures remain main stream with EM data, and were used in (Machireddy et al, 2021), and the companion paper within this journal volume. In this paper, we compared architectures as well as training frameworks to find the most suitable one for the task of semantic segmentation in the aforementioned specific context of FIB-SEM images.…”

Section: Introductionmentioning

confidence: 99%

Efficient semi-supervised semantic segmentation of electron microscopy cancer images with sparse annotations

Pagano,

Thibault,

Bousselham

et al. 2023

Preprint

View full text Add to dashboard Cite

Electron microscopy (EM) enables imaging at nanometer resolution and can shed light on how cancer evolves to develop resistance to therapy. Acquiring these images has become a routine task; however, analyzing them is now the bottleneck, as manual structure identification is very time-consuming and can take up to several months for a single sample. Deep learning approaches offer a suitable solution to speed up the analysis. In this work, we present a study of several state-of-the-art deep learning models for the task of segmenting nuclei and nucleoli in volumes from tumor biopsies. We compared previous results obtained with the ResUNet architecture to the more recent UNet++, FracTALResNet, SenFormer, and CEECNet models. In addition, we explored the utilization of unlabeled images through semi-supervised learning with Cross Pseudo Supervision. We have trained and evaluated all of the models on sparse manual labels from three fully annotated in-house datasets that we have made available on demand, demonstrating improvements in terms of 3D Dice score. From the analysis of these results, we drew conclusions on the relative gains of using more complex models, semi-supervised learning as well as next steps for the mitigation of the manual segmentation bottleneck.

show abstract

Real time video summarizing using image semantic segmentation for CBVR

Cited by 9 publications

References 23 publications

Simulation of Video Image Fault Tolerant Coding Transmission in Digital Multimedia

Simulation of Video Image Fault Tolerant Coding Transmission in Digital Multimedia

From video summarization to real time video summarization in smart cities and beyond: A survey

Efficient semi-supervised semantic segmentation of electron microscopy cancer images with sparse annotations

Contact Info

Product

Resources

About