27,575 Hits in 2.8 sec


M. Li, X. Zhao, J. Li, D. Zhu
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In the paper, the YOLOv3 network is trained as a detection benchmark and BASNet is used to generate saliency maps from the thermal images.  ...  To address these problems, we propose to use the saliency map of thermal images for image enhancement as the attention mechanism of the object detector.  ...  We suppose that the fusion images maintain texture information and clear boundaries of objects, which can enhance the recognition capability of the trained models using the fusion images.  ... 
doi:10.5194/isprs-archives-xliii-b2-2020-1233-2020 fatcat:dg36lxqucnekxew6isjudwy3vi

Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network [article]

Fangting Lin, Chao Yang, Huizhou Li, Bin Jiang
2019 arXiv   pre-print
Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance.  ...  However, most of them ignore the complementarity between saliency features and boundary features, thus get worse predictions in scenes with low contrast between foreground and background.  ...  On the other hand, we also add F S i−1 to F B i to supplement missing saliency information, and use F G B i to generate more detailed boundary information.  ... 
arXiv:1912.05236v1 fatcat:sxxy733dwvb5xoxhcdivh7mrra

Salient target detection in hyperspectral image based on visual attention

Minghua Zhao, Liqin Yue, Jing Hu, Shuangli Du, Peng Li, Li Wang
2021 IET Image Processing  
FT model is used to get target with clear border, and spectral information is made full use of to improve the accuracy of target detection.  ...  Firstly, FT is used to detect saliency of hyperspectral image and the saliency map is generated.  ...  The results in column (i) have clear boundary and the description of the target object is clearer. The main reason is that we use FT saliency model and add the detection of spectral information.  ... 
doi:10.1049/ipr2.12197 fatcat:dllgxujtbvbnbd5dwrh6qxr6wi

Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping

Jingjing ZHONG, Siwei LUO, Qi ZOU
2009 IEICE transactions on information and systems  
The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images.  ...  Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects.  ...  In this paper we propose a novel multi-scale boundary detection algorithm for contour grouping using selective attention guided global spatial prior information.  ... 
doi:10.1587/transinf.e92.d.555 fatcat:rdldv3bsh5bsdhhs6lqgdly42u

Hybrid Local and Global Deep-Learning Architecture for Salient-Object Detection

Wajeeha Sultan, Nadeem Anjum, Mark Stansfield, Naeem Ramzan
2020 Applied Sciences  
These features are then integrated to extract the exact boundary of the object of interest in an image.  ...  Salient-object detection is a fundamental and the most challenging problem in computer vision. This paper focuses on the detection of salient objects, especially in low-contrast images.  ...  [11] developed a technique that makes use of prior saliency-detection techniques.  ... 
doi:10.3390/app10238754 fatcat:w4poi5kk2zffzhhyqwhzjfslii

Edge-guided Non-local Fully Convolutional Network for Salient Object Detection [article]

Zhengzheng Tu, Yan Ma, Chenglong Li, Jin Tang, Bin Luo
2019 arXiv   pre-print
To preserve good boundaries of salient objects, we propose a guidance block to embed edge prior knowledge into hierarchical feature maps.  ...  In a specific, we extract hierarchical global and local information in FCN to incorporate non-local features for effective feature representations.  ...  Through using parallel edge features to guide saliency detection, we could obtain more accurate saliency maps with clearer object boundaries. III.  ... 
arXiv:1908.02460v2 fatcat:e7sjjjwpfbh6roglc4ujrjae5e

Salient Object Detection via Adaptive Region Merging

2016 KSII Transactions on Internet and Information Systems  
We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained.  ...  In this paper, a novel salient object detection algorithm is proposed based on region merging.  ...  These use high-level information to guide the saliency computation, equating saliency to the detection of stimuli from certain object classes [11] .  ... 
doi:10.3837/tiis.2016.09.020 fatcat:65m37cgljvba7nctmxilpgd34i

Saliency detection with color contrast based on boundary information and neighbors

Min Xu, Hanling Zhang
2014 The Visual Computer  
Object-level saliency detection is significant in many computer vision tasks. In this paper, we propose a novel saliency detection model based on color contrast and image boundaries.  ...  First of all, according to the definition of saliency, we take four boundaries of image into consideration respectively to obtain a combination coarse saliency map.  ...  information will not contribute much to the detection algorithm.  ... 
doi:10.1007/s00371-014-0930-9 fatcat:3mhdraly7ndpxiasjery6phwfi

Saliency Cuts: Salient Region Extraction based on Local Adaptive Thresholding for Image Information Recognition of the Visually Impaired

Mukhriddin Mukhiddinov, Rag-Gyo Jeong, Jinsoo Cho
2020 ˜The œinternational Arab journal of information technology  
Lastly, based on the binary mask and extracted salient object, outer boundaries and internal edges are detected by Canny edge detection method.  ...  The saliency cuts approach is an effective tool for salient object detection.  ...  As shown in Figure 7 , the boundaries of salient objects are well detected using binary images and the Canny edge operator, providing valuable information to the visually impaired.  ... 
doi:10.34028/iajit/17/5/4 fatcat:p2qzp6ak5bbs3b2ool4h6e5lkm

Pyramid Feature Attention Network for Saliency detection [article]

Ting Zhao, Xiangqian Wu
2019 arXiv   pre-print
However, not all features are useful for saliency detection and some even cause interferences.  ...  Finally, we propose an edge preservation loss to guide network to learn more detailed information in boundary localization.  ...  Because the second derivative can be used to detect edges, we use the Laplace operator to get salient object boundaries.  ... 
arXiv:1903.00179v2 fatcat:5ypifrq5rnbl5n2wa3u2uodswq

Pyramid Feature Attention Network for Saliency Detection

Ting Zhao, Xiangqian Wu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Recently, CNNs are the most widely used and powerful techniques for saliency detection, in which feature maps from different layers are always integrated without distinction.  ...  Saliency detection is one of the basic challenges in computer vision.  ...  Because the second derivative can be used to detect edges, we use the Laplace operator to get salient object boundaries.  ... 
doi:10.1109/cvpr.2019.00320 dblp:conf/cvpr/ZhaoW19 fatcat:ukv2a3r6hfc4bc2ow7ooajfa64

Weakly-supervised Salient Instance Detection [article]

Xin Tian, Ke Xu, Xin Yang, Baocai Yin, Rynson W.H. Lau
2020 arXiv   pre-print
class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.  ...  We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting  ...  It has three synergic branches: (1) a Boundary Detection Branch for detecting object boundaries using class discrepancy information; (2) a Saliency Detection Branch for detecting objects using class consistency  ... 
arXiv:2009.13898v1 fatcat:baighmhl5fafdbgm2b2aiasgqm

Moving object detection in aerial video based on spatiotemporal saliency

Hao Shen, Shuxiao Li, Chengfei Zhu, Hongxing Chang, Jinglan Zhang
2013 Chinese Journal of Aeronautics  
Finally, by combining temporal and spatial saliency information, we can get refined detection results.  ...  While motion cues have been extensively exploited in the literature, how to use spatial information is still an open problem.  ...  They would also like to thank the anonymous reviewers for their insightful comments and useful suggestions that help to improve the quality of this work.  ... 
doi:10.1016/j.cja.2013.07.038 fatcat:7jgtiabh4jcq7baoi3hlad7jie

Contour Grouping and Object-Based Attention with Saliency Maps

Jingjing ZHONG, Siwei LUO, Jiao WANG
2009 IEICE transactions on information and systems  
First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model.  ...  the complete boundaries of objects in images.  ...  We make use of image information in two ways: the definition of the similarity of tangent pairs and the saliency of regions which are enclosed by boundaries, while most other models only consider edges  ... 
doi:10.1587/transinf.e92.d.2531 fatcat:c7ysrfenjrhhppib36l2nqfqhm

Saliency driven clustering for salient object detection

Lei Zhou, Yi Jun Li, Yi Peng Song, Yu Qiao, Jie Yang
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The final saliency map are obtained by combining the refined contrast prior saliency and boundary prior saliency.  ...  In this work, a novel salient object detection method is proposed based on the saliency driven clustering.  ...  The structural information of images reflected by clusters is useful for generating saliency maps of high quality.  ... 
doi:10.1109/icassp.2014.6854629 dblp:conf/icassp/ZhouLSQY14 fatcat:zud3k5qmczguzlhqctmclsrweu
« Previous Showing results 1 — 15 out of 27,575 results