Human Segmentation Based on Compressed Deep Convolutional Neural Network

Miao, Jun; Sun, Kang; Liao, Xiangyun; Leng, Lu; Chu, Jun

doi:10.1109/access.2020.3023746

Cited by 12 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liang et al [14] introduced a segmentation method called the TriSeNet. Unlike the U-Net, the whole network in this method is composed of three different network paths to extract the high-dimensional spatial features, high-level semantic features and detailed boundary features.…”

Section: Segmentationmentioning

confidence: 99%

Background Replacement in Video Conferencing

Shahi¹,

Li²

2023

IJNDI

View full text Add to dashboard Cite

Article Background Replacement in Video Conferencing Kiran Shahi *, and Yongmin Li 1 Department of Computer Science, Brunel University London, Uxbridge, UB8 3PH, United Kingdom * Correspondence: 2144420@alumni.brunel.ac.uk Received: 17 March 2023 Accepted: 24 April 2023 Abstract: Background replacement is one of the most used features in video conferencing applications by many people, perhaps mainly for privacy protection, but also for other purposes such as branding, marketing and promoting professionalism. However, the existing applications in video conference tools have serious limitations. Most applications tend to generate strong artefacts (while there is a slight change in the perspective of the background), or require green screens to avoid such artefacts, which results in an unnatural background or even exposes the original background to other users in the video conference. In this work, we aim to study the relationship between the foreground and background in real-time videos. Three different methods are presented and evaluated, including the baseline U-Net, the lightweight U-Net MobileNet, and the U-Net MobileNet&ConvLSTM models. The above models are trained on public datasets for image segmentation. Experimental results show that both the lightweight U-Net MobileNet and the U-Net MobileNet& ConvLSTM models achieve superior performance as compared to the baseline U-Net model.

show abstract

Section: Segmentationmentioning

confidence: 99%

Background Replacement in Video Conferencing

Shahi¹,

Li²

2023

IJNDI

View full text Add to dashboard Cite

show abstract

“…To optimize the convolution layer and filter, J Miao's team proposed a human body segmentation algorithm based on the compressed depth Convolutional neural network, and adopted a two-stage global filter level pruning strategy. The results showed that the segmentation speed of this method is increased by 2.4 times [6]. Chu J et al proposed an instance segmentation method that integrates non maximum suppression algorithms for semantic segmentation of bounding boxes returned by detectors.…”

Section: Related Workmentioning

confidence: 99%

Interactive Image Segmentation Technique Based on Improved Residual Network

Yang,

Geng

2023

IEEE Access

View full text Add to dashboard Cite

Interactive image segmentation offers useful guidance to users and can be applied in practical settings for production and daily life purposes. Nonetheless, the technology's intrinsic limitations, including complicated interaction methods and high error rates, have impeded its further advancement with the development of computer vision. To address the issue, this study introduces a method to determine the extreme point of center point prediction. The target center serves as the "symmetric center" of the extreme point, which facilitates the search for other extreme points. Furthermore, the Canny algorithm is combined to achieve edge image detection. Moreover, the residual network is enhanced through embedding a pre-activation step, introducing a BatchNorm layer, and adding a pyramid scene parsing network. Finally, the performance of this method is verified by analyzing its Intersection over Union, segmentation accuracy, efficiency, F1 value, and other indicators. The results show that on the Pascalvoc2012 dataset, the segmentation accuracy obtained through the extreme point method can reach over 90%. The addition of the pyramid scene analysis network stabilizes its accuracy on urban landscape datasets between 92% and 96%. When the proposed image segmentation method is applied to the Grabcut dataset, its union intersection can reach 88.7%. On the self-generated complex daily scenery dataset, this method achieves segmentation accuracy of 95% with superior stability and precision. This provides a fresh methodological reference for optimizing interactive image segmentation technology further.

show abstract

“…ReLU activates neurons then the gradient provides all times the high value. ReLU, f(n) is defined as MAX(0,n) (Miao J. et al, 2020, Feng S. et al, 2021, Zhou Y. et al, 2019& Rossinelli D. et al, 2020. Algorithm2 describes the non-ROI compression of the medical image using CNN.…”

Section: Convolution Neural Network Based Compressionmentioning

confidence: 99%

Untitled

2022

JER is an international, peer-reviewed journal that publishes f

View full text Add to dashboard Cite

Human Segmentation Based on Compressed Deep Convolutional Neural Network

Cited by 12 publications

References 34 publications

Background Replacement in Video Conferencing

Background Replacement in Video Conferencing

Interactive Image Segmentation Technique Based on Improved Residual Network

Untitled

Contact Info

Product

Resources

About