A Survey on Various Saliency Detection Methods

Sebastian, E. W. Opitz; Daniel, Neenu

doi:10.5120/ijca2017913187

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work is compared to the experimental evaluations over the benchmark datasets for all the published methods. The interested reader may refer to some more survey publications on the research of saliency detection [27] [28].…”

Section: Visual Attention Based Saliency Detectionmentioning

confidence: 99%

A Survey on Approaches for Saliency Detection with Visual Attention

Zhang

2018

MATEC Web Conf.

View full text Add to dashboard Cite

Most existing approaches for detecting salient areas in natural scenes are based on the saliency contrast within the local context of image. Nowadays, a few approaches not only consider the difference between the foreground objects and the surrounding background areas, but also consider the saliency objects as the candidates for the center of attention from the human’s perspective. This article provides a survey of saliency detection with visual attention, which exploit visual cues of foreground salient areas, visual attention based on saliency map, and deep learning based saliency detection. The published works are explained and descripted in detail, and some related key benchmark datasets are briefly presented. In this article, all documents are published from 2013 to 2018, giving an overview of the progress of the field of saliency detection.

show abstract

Section: Visual Attention Based Saliency Detectionmentioning

confidence: 99%

A Survey on Approaches for Saliency Detection with Visual Attention

Zhang

2018

MATEC Web Conf.

View full text Add to dashboard Cite

show abstract

“…However, its patch detection ratio is less than that of the other models. According to the center-surround hypothesis suggested in [36], we set the patch size to n×n, where n is an odd number. To test the semantic filter precision influenced in terms of the size n and the variation, we set n = 17, 33, 65, 129 in an incremental way.…”

mentioning

confidence: 99%

A Deep Learning-Based Semantic Filter for RANSAC-Based Fundamental Matrix Calculation and the ORB-SLAM System

Shao¹,

Zhang²,

Fang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The estimation of a fundamental matrix (F-matrix) from two-view images is a crucial problem in epipolar geometry, and a key point in visual simultaneous localization and mapping (VSLAM). Conventional robust methods proposed by the data calculation space, such as Random Sample Consensus (RANSAC), encounter computational inefficiency and low accuracy when the outliers exceed 50%. In this paper, a semantic filter-based on faster region-based convolutional neural network (faster R-CNN) is proposed to solve the outlier problem in RANSAC based F-matrix calculations. The semantic filter is trained using semantic patches tailored by inliers, providing different semantic labels in various image regions. First, the patches classified into the top three bad labels are filtered out during the pre-processing phase. Second, precise and robust correspondences are determined by the remaining high-level semantic contexts. Finally, the inliers are assessed using RANSAC to produce an accurate F-matrix. The proposed algorithm can improve the accuracy of F-matrix calculations, as low-quality feature correspondences are effectively decreased. Experiments on KITTI and ETH sequences illustrate that the 3D position error can be reduced by applying the semantic filter to the ORB-SLAM system. Further, indoor and real environment experiments demonstrate that an effective lower trajectory error is yielded with the proposed approach.

show abstract