Multi-scale Saliency Detection Research Articles

Uneven Illumination Surface Defects Inspection Based on Saliency Detection and Intrinsic Image Decomposition

Surface defect detection based on computer vision remains a challenging task due to the uneven illumination, low contrast and miscellaneous patterns of defects. Current methods usually present undesirable detection accuracy and lack adaptability for the various scenes. In the paper, the novel uneven illumination surface defects inspection (UISDI) method is proposed to address these issues. First, the multi-scale saliency detection (MSSD) method is proposed to construct a coarse defect map and obtain the corresponding background regions. Second, a novel background similarity prior-based intrinsic image decomposition model (BSIID) is applied to divide the defect image into a non-defective shading layer and a defective reflectance layer. An accelerated optimization solution is proposed to solve the minimization problem of the intrinsic image decomposition model. Last, the enhanced defect image is obtained by filtering the reflectance image and is then utilized to accurately segment the defect region from the coarse defect map. The experiments conducted using four real-world defect datasets demonstrate that the proposed method outperforms state-of-the-art methods.

Multiscale saliency detection method for ship targets in synthetic aperture radar images

Ship detection is an important direction of synthetic aperture radar (SAR) image application in maritime surveillance. A multi-scale optimisation threshold saliency detection is developed in this letter, which is used to detect ships targets of SAR images. The SAR image is first decomposed into a pyramid image sequence. Then the saliency detection is performed using the spectral residual method for each layer in the sequence, and the salient sub-graph that contains ship targets is obtained. Finally, each sub-graph is fused and the optimisation threshold segmentation method that applies to the saliency map gives the final detection result. Experimental results show that the proposed approach has low complexity and high detection accuracy and greatly reduces the dependence on prior knowledge.

Unsupervised change detection method based on saliency analysis and convolutional neural network

Due to great advantages in deep features representation and classification for image data, deep learning is becoming increasingly popular for change detection (CD) in the remote-sensing community. An unsupervised CD method is proposed by combining deep features representation, saliency detection, and convolutional neural network (CNN). First, bitemporal images are fed into the pretrained CNN model for deep features extraction and difference image generation. Second, multiscale saliency detection is adopted to implement the uncertainty analysis for the difference image, where image pixels can be categorized into three classes: changed, unchanged, and uncertain. Then, a flexible CNN model is constructed and trained using the interested changed and unchanged pixels, and the change type of the uncertain pixels can be determined by the CNN model. Finally, object-based refinement and multiscale fusion strategies are utilized to generate the final change map. The effectiveness and reliability of our CD method are verified on three very high-resolution datasets, and the experimental results show that our proposed approach outperforms the other state-of-the-art CD methods in terms of five quantitative metrics.

Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals

Infrared (IR) imaging systems with low-density focal plane arrays produce images with poor spatial resolution. To address this limitation, super-resolution (SR) algorithms can be applied on IR-low resolution (LR) images. In this paper, we present a new SR technique based on the multi-scale saliency detection and the residuals learned by the deep convolutional neural network (CNN) in the wavelet domain (DWCNN). The input LR image is processed in the transformed domain by applying 2D discrete wavelet transform. It decomposes an image into its low-frequency and high-frequency subbands. The multi-scale saliency detection is used to extract small scale and large scale salient feature maps from the bicubic upscaled LR image. These maps are incorporated in the high-frequency subbands of the LR image. Furthermore, the low-frequency and high-frequency subands are refined using the residuals learned by the DWCNN in training phase. The proposed algorithm is compared with the conventional and state-of-the-art SR methods. Results indicate that our method yields good reconstruction quality with high peak signal to ratio, structural similarity and low blur indices. Besides, our method requires less computational time.

Fast and Accurate Target Detection Based on Multiscale Saliency and Active Contour Model for High-Resolution SAR Images

The active contour model (ACM) is widely used in target detection of optical and medical images, but multiplicative speckle noise largely interferes with its use in synthetic aperture radar (SAR) images. To overcome this difficulty, a region- and edge-based convex ACM with high efficiency is proposed for target detection in small-scale SAR images. Then, a novel detection algorithm, which combines the advantages of a multiscale saliency detection method and the proposed high-efficiency ACM, is presented to address a large-scale and high-resolution SAR image automatically. Target detection experiments in real and simulated SAR images show that the proposed methods outperform classical ACMs and the popular two-parameter constant false alarm rate detector in terms of efficiency and accuracy.

Surroundedness based multiscale saliency detection

In this paper, a surroundedness-based multiscale saliency method is proposed based on the Gestalt principles for figure-ground segregation, which states that (1) surrounded regions are more likely to be perceived as figures, (2) the humans understand the external stimuli as whole rather than the sum of their parts. First, an image is characterized by a set of binary images, which is generated by a simple and effective homogeneous region extraction method with well contour preservation. And the contour confidence map is obtained by a fast contour detection method. Then for each connect homogeneous region in a binary map, surroundedness is defined by the average outer contour confidence. Finally, integrating the background priors, multiscale saliency maps are generated and combined to the final saliency map. The proposed method is evaluated on two widely used public datasets with pixel accurate salient region annotations using both precision and recall analysis and ROC analysis. And the experimental results show that the proposed method outperforms 14 alternative methods.

Video saliency detection using 3D shearlet transform

Recently, visual saliency detection has received great interest. As most video saliency detection models are based on spatiotemporal mechanism, we firstly give a simple introduction of it in this paper. After discussing issues to be addressed, we present a novel framework for video saliency detection based on 3D discrete shearlet transform. Instead of measuring saliency by fusing spatial and temporal saliency maps, the proposed model regards video as three-dimensional data. By decomposing the video with 3D discrete shearlet transform and reconstructing it on multi-scales, this multi-scale saliency detection model obtains a number of feature blocks to describe the video. Based on each feature block, every a number of successive feature maps are taken as a whole, and the global contrast is calculated to obtain the saliency maps. By fusing all the saliency maps of different levels, the saliency map is generated for each video frame. This novel framework is very simple, and experimental results on ten videos show that the proposed model outperforms lots existing models.

A New Framework for Multiscale Saliency Detection Based on Image Patches

In this paper, we propose a new multiscale saliency detection algorithm based on image patches. To measure saliency of pixels in a given image, we segment the image into patches by a fixed scale an...