REDN: A Recursive Encoder-Decoder Network for Edge Detection

Le, Tu; Duan, Ye

doi:10.1109/access.2020.2994160

Cited by 17 publications

(9 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods differ in the way the derivatives are calculated, and an evaluation of various classical edge detectors is provided in Reference 7. In recent years, several studies have also explored the use of machine learning for edge detection 8‐10 . Dollár and Zitnick 8 used structured forests to speed up the process of edge detection.…”

Section: Related Workmentioning

confidence: 99%

“…Xie and Tu 9 proposed the algorithm of holistically nested edge detection to address the problem of holistic images and multi‐scale features. Le and Duan 10 introduced a recursive encoder‐decoder network, which enabled iterative refinement of the edges using a single network model. Unlike the aforementioned studies, which search for edges in 2D images, we search for boundaries in 3D space.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Detecting color boundaries on 3D surfaces by applying edge‐detection image filters on a quad‐remeshing

Huang

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Edge detection is a common image-processing technique that has numerous applications. In this article, we propose an algorithm for detecting edges based on the color of a mesh surface. We name the edges the color boundaries. Our approach is based on the data structure of a quad mesh, which makes the data structure of 3D meshes resemble the data structure of images. As a result, image-processing methods can be applied on the 3D meshes. In this article, six classical edge detection filters are implemented on the 3D meshes. The experimental results demonstrate that our method can identify areas of high color gradient on 3D meshes. A comparison with two other methods for detecting color boundaries on 3D meshes reveals that our method is more effective at detecting boundaries. Lastly, we propose two novel applications that utilize the information of color boundaries on a 3D mesh surface.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Detecting color boundaries on 3D surfaces by applying edge‐detection image filters on a quad‐remeshing

Huang

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…In the experiment, five standard images with 256×256 pixels are tested. We make a comparison with other three state-of-the-art methods including FL [17], CGAN [18], REDN [19]. The evaluation indicators include peak signal-to-noise ratio (PSNR), running time, and an evaluation method based on the score of connected components (4-connected components B, 8-connected components C and the ratio of C/B) [20].…”

Section: Experiments and Analysismentioning

confidence: 99%

GPNRBNN: A Robot Image Edge Detection Method Based on Gaussian Positive-Negative Radial Basis Neural Network

Zheng

2021

Sens Imaging

View full text Add to dashboard Cite

In the traditional edge detection models, due to the influence of artifact, occlusion and other factors, the detection efficiency is poor and the error is large, which affects the subsequent image processing. Therefore, this paper proposes a new edge detection method based on Gaussian positive-negative radial basis neural network (GPN-RBNN). Firstly, a novel GPNRBNN is constructed in this paper. Each pixel preprocessed by Gaussian filter in the image is taken as the central point of the GPNRBNN and input into the neural network. Then, the weight sharing and sparse connection in the convolutional neural network are used for processing the pixels. The results are output after the calculation in the extended layer and the hidden layer. Thirdly, the edge is extracted by contour tracking according to the output results. Finally, experiments are conducted on the composite image, part of the uneven gray image and medical images etc. Compared with other models, the efficiency of the proposed model is improved, and the edge connectivity is better.

show abstract

“…Boundary detection. Some methods explore deep networks to detecting boundary (Xie and Tu, 2015;Le and Duan, 2020) and semantic boundary (Yu et al, 2018b). The results obtained by these methods surpass those based on hand-crafted features.…”

Section: Related Workmentioning

confidence: 99%

Attention-based fusion of semantic boundary and non-boundary information to improve semantic segmentation

Fontinele,

Lefundes,

Oliveira

2021

Preprint

View full text Add to dashboard Cite

This paper introduces a method for image semantic segmentation grounded on a novel fusion scheme, which takes place inside a deep convolutional neural network. The main goal of our proposal is to explore object boundary information to improve the overall segmentation performance. Unlike previous works that combine boundary and segmentation features, or those that use boundary information to regularize semantic segmentation, we instead propose a novel approach that embodies boundary information onto segmentation. For that, our semantic segmentation method uses two streams, which are combined through an attention gate, forming an end-to-end Y-model. To the best of our knowledge, ours is the first work to show that boundary detection can improve semantic segmentation when fused through a semantic fusion gate (attention model). We performed an extensive evaluation of our method over public data sets. We found competitive results on all data sets after comparing our proposed model with other twelve stateof-the-art segmenters, considering the same training conditions. Our proposed model achieved the best mIoU on the CityScapes, CamVid, and Pascal Context data sets, and the second best on Mapillary Vistas.

show abstract

REDN: A Recursive Encoder-Decoder Network for Edge Detection

Cited by 17 publications

References 80 publications

Detecting color boundaries on 3D surfaces by applying edge‐detection image filters on a quad‐remeshing

Detecting color boundaries on 3D surfaces by applying edge‐detection image filters on a quad‐remeshing

GPNRBNN: A Robot Image Edge Detection Method Based on Gaussian Positive-Negative Radial Basis Neural Network

Attention-based fusion of semantic boundary and non-boundary information to improve semantic segmentation

Contact Info

Product

Resources

About