Salient Object Detection in the Distributed Cloud-Edge Intelligent Network

Gao, Zhifan; Zhang, Heye; Dong, Shizhou; Sun, Shanhui; Wang, Xin; Yang, Guang; Wu, Wanqing; Li, Shuo; Albuquerque, Victor Hugo C. de

doi:10.1109/mnet.001.1900260

Cited by 71 publications

(21 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Zhao et al [54] have proposed a method for the similarity learning with joint transfer constraints. Generally, video-based re-identification faces many severe challenges, particularly viewpoint changing [7] and cluttered background [10]. Moreover, even under the same viewpoint, images belonging to a person may differ considerably due to the dramatic variations caused by variable illumination, pose and occlusion [18].…”

Section: Related Workmentioning

confidence: 99%

Person Re-Identification from different views based on dynamic linear combination of distances

Elaoud

Barhoumi

Drira

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Person re-identification from videos taken by multiple cameras from different views is a very challenging problem that has attracted growing interest in last years. In fact, the same person from significant cross-view has different appearances from clothes change, illumination, and cluttered background. To deal with this issue, we use the skeleton information since it is not affected by appearance and pose variations. The skeleton as an input is projected on the Grassmann manifold in order to model the human motion as a trajectory. Then, we calculate the distance on the Grassmann manifold, in order to guarantee invariance against rotation, as well as local distances allowing to discriminate anthropometric for each person. The two distances are thereafter combined while defining dynamically the optimal combination weight for each person. Indeed, a machine learning process learns to predict the best weight for each person according to the rank metric of its re-identification results. Experimental results, using challenging 3D (IAS

show abstract

Section: Related Workmentioning

confidence: 99%

Person Re-Identification from different views based on dynamic linear combination of distances

Elaoud

Barhoumi

Drira

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Genovese et al [20] proposed computational intelligence techniques based on neural networks to select only the actual sweat pores from the set of extracted candidate points. Recently, deep learning has achieved great success in the field of image analysis [39,40]. Labati et al [21] proposed a CNN for pore detection (CNN D ) and another CNN for refinement (CNN R ).…”

Section: Sweat Pore Extraction From Surface Fingerprint Imagementioning

confidence: 99%

Subcutaneous sweat pore estimation from optical coherence tomography

Ding

Wang

Chen

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Sweat pore, one of the level 3 features of fingerprint, has attracted much attention in fingerprint recognition. Traditional sweat pores on surface fingerprint are unclear or blurred when fingers are stained or damaged. Subcutaneous sweat pores, as cross section of the sweat glands, are resistant to external interferences. With 3D fingertip information measured by optical coherence tomography (OCT), the subcutaneous sweat pore estimation from OCT volume data is investigated. First, an adaptive subcutaneous pore image reconstruction method is proposed. It utilizes the skin surface and viable epidermis junction as reference and realizes depth-adaptive pore image reconstruction. Second, a dilated U-Net combining the U-Net with dilated convolution is proposed for subcutaneous sweat pore extraction, which can prevent information loss of sweat pores caused by downsampling. To the best knowledge, it is the first time that subcutaneous sweat pore extraction is investigated and proposed. Experiments on subcutaneous pore image reconstruction and sweat pore extraction are both conducted. The qualitative and quantitative results show that the proposed adaptive method performs better in subcutaneous pore image reconstruction compared with the fix-depth method, and the dilated U-Net outperforms other methods on subcutaneous sweat pore extraction.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…In weakly supervised semantic segmentation, one of the main challenges is to effectively build a bridge between image-level keyword annotations and corresponding semantic objects. Many works use a saliency detector [32][33][34] to capture pixel-level information and generate proxy ground-truth from the original images. Although the development of weakly supervised semantic segmentation is rapid, theirs performance still cannot match the models trained on finely annotated datasets.…”

Section: Related Workmentioning

confidence: 99%

Parallel global convolutional network for semantic image segmentation

Bai

Zhou

2020

IET Image Processing

View full text Add to dashboard Cite

In this paper, a novel convolutional neural network for fast semantic segmentation is presented. Deep convolutional neural networks have achieved great progress in the task of vision scene understanding. While the increase of the accuracy mainly depends on the increase of depth and width. This slows down large networks and consumes power. A fast and efficient convolutional neural network, PGCNet, aiming at segmenting high-resolution images with a high speed is introduced. Compared with the competitive methods, the generated model has high performance with fewer parameters and floating point operations. First, a lightweight general architecture pre-trained on ImageNet is relied on as the main encoder. Then, a novel lateral connection module to better transmit features from encoder to decoder. Third, a powerful method termed as PGCN block to extract features of each block in the encoder is proposed and an edge decoder is applied as a supervision for pixels on the edge of stuff and things during training. Experiments show that this method has great advantages. Based on the proposed PGCNet, 75.8% mean IoU is achieved on the cityscapes test set and 35.4 Hz on a standard Cityscapes image on GTX1080Ti.

show abstract

Salient Object Detection in the Distributed Cloud-Edge Intelligent Network

Cited by 71 publications

References 15 publications

Person Re-Identification from different views based on dynamic linear combination of distances

Person Re-Identification from different views based on dynamic linear combination of distances

Subcutaneous sweat pore estimation from optical coherence tomography

Parallel global convolutional network for semantic image segmentation

Contact Info

Product

Resources

About