RSF: A Novel Saliency Fusion Framework for Image Saliency Detection

Image saliency detection has recently witnessed rapid progress due to deep neural networks. However, there still exist many important problems in the existing deep learning based methods. Pixel-wise convolutional neural network (CNN) methods suffer from blurry boundaries due to the convolutional and pooling operations. While region-based deep learning methods lack spatial consistency since they deal with each region independently. In this paper, we propose a novel salient object detection framework using a superpixelwise variational autoencoder (SuperVAE) network. We first use VAE to model the image background and then separate salient objects from the background through the reconstruction residuals. To better capture semantic and spatial contexts information, we also propose a perceptual loss to take advantage from deep pre-trained CNNs to train our SuperVAE network. Without the supervision of mask-level annotated data, our method generates high quality saliency results which can better preserve object boundaries and maintain the spatial consistency. Extensive experiments on five wildly-used benchmark datasets show that the proposed method achieves superior or competitive performance compared to other algorithms including the very recent state-of-the-art supervised methods.

Download Full-text

Fast DCT-based image saliency detection

2012 IEEE Global High Tech Congress on Electronics ◽

10.1109/ghtce.2012.6490124 ◽

2012 ◽

Cited By ~ 1

Author(s):

Xiaoshan Yang ◽

Jianbing Shen ◽

Chao Liang ◽

Yun Zhu

Keyword(s):

Saliency Detection ◽

Image Saliency

Download Full-text

A new deep spatial transformer convolutional neural network for image saliency detection

Design Automation for Embedded Systems ◽

10.1007/s10617-018-9209-0 ◽

2018 ◽

Vol 22 (3) ◽

pp. 243-256 ◽

Cited By ~ 6

Author(s):

Xinsheng Zhang ◽

Teng Gao ◽

Dongdong Gao

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Saliency Detection ◽

Image Saliency

Download Full-text

An image saliency detection algorithm based on color and space information

2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) ◽

10.1109/ispacs.2017.8266557 ◽

2017 ◽

Cited By ~ 1

Author(s):

Liyuan Feng ◽

Peizhi Wen ◽

Yuanyuan Miao ◽

Ying Zhou

Keyword(s):

Saliency Detection ◽

Detection Algorithm ◽

Image Saliency

Download Full-text

Research on an Infrared Multi-Target Saliency Detection Algorithm under Sky Background Conditions

Sensors ◽

10.3390/s20020459 ◽

2020 ◽

Vol 20 (2) ◽

pp. 459

Author(s):

Shaosheng Dai ◽

Dongyang Li

Keyword(s):

Saliency Detection ◽

Infrared Image ◽

Detection Algorithm ◽

Saliency Map ◽

Phase Spectrum ◽

Background Suppression ◽

Suppression Effect ◽

Multi Scale ◽

Saliency Maps ◽

Image Saliency

Aiming at solving the problem of incomplete saliency detection and unclear boundaries in infrared multi-target images with different target sizes and low signal-to-noise ratio under sky background conditions, this paper proposes a saliency detection method for multiple targets based on multi-saliency detection. The multiple target areas of the infrared image are mainly bright and the background areas are dark. Combining with the multi-scale top hat (Top-hat) transformation, the image is firstly corroded and expanded to extract the subtraction of light and shade parts and reconstruct the image to reduce the interference of sky blurred background noise. Then the image obtained by a multi-scale Top-hat transformation is transformed from the time domain to the frequency domain, and the spectral residuals and phase spectrum are extracted directly to obtain two kinds of image saliency maps by multi-scale Gauss filtering reconstruction, respectively. On the other hand, the quaternion features are extracted directly to transform the phase spectrum, and then the phase spectrum is reconstructed to obtain one kind of image saliency map by the Gauss filtering. Finally, the above three saliency maps are fused to complete the saliency detection of infrared images. The test results show that after the experimental analysis of infrared video photographs and the comparative analysis of Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUC) index, the infrared image saliency map generated by this method has clear target details and good background suppression effect, and the AUC index performance is good, reaching over 99%. It effectively improves the multi-target saliency detection effect of the infrared image under the sky background and is beneficial to subsequent detection and tracking of image targets.

Download Full-text