Saliency detection using adaptive background template

Salient object detection is a process of extracting an object which is visually attractive from a single image or a video. As a powerful technique for automatic image or video segmentation, saliency detection has been focused and studied recently. In this paper, we propose a novel method for salient object detection without training or learning-based techniques. The proposed framework consists of two major steps, the generation of saliency map candidates and the selection of an optimal saliency map. To generate saliency map candidates, prior maps based on combinations of RGB color components are proposed. To select the optimal saliency map among the candidates, we propose a compactness measure, which evaluates the degree to which the generated saliency maps show objects. As a result, among recent works on saliency detection, our saliency detection method achieves the highest performance in terms of saliency detection.

Nowadays, ship detection in sea-sky background is not only useful in maritime visual surveillance, but also helpful in maritime search and rescue. Since ships are salient objects in infrared images with sea-sky background, we present a novel and effective algorithm based on saliency for ship detection in this situation. Our algorithm adopts global saliency, local saliency and background prior to generate saliency maps. Ships are finally segmented in saliency maps. Our algorithm is compared with four classic salient object detection algorithms. And experimental results show our algorithm outperforms the other four algorithms in qualitative and quantitative terms. Keyword list: ship detection ; salient object detection ; infrared image ; sea - sky background . 1. INTRODUCTION Since ships are important vehicles for sea transportation, ship detection in sea-sky background is extensively used in maritime visual surveillance and reconnaissance, avoidance of ship collision accidents, maritime search and rescue, etc. Infrared imaging systems can almost work in any environment and all-weather conditions with its visual capacity in darkness and frog, which makes it a very suitable tool in this application. In recent years, ship detection in infrared images with sea-sky background attracts increasing attention. Many methods are proposed in this field, including image segmentation methods [1-2] and morphological methods [3]. However, due to complex sea-sky environment and large variation of ship sizes, these methods cannot solve the issue completely. And since ships are often salient objects in infrared images with sea-sky background, some researchers have recently tried salient object detection ideas used in color images [4-6]. And the paper is focused on using salient object detection methods to solve the issue. Salient objects are objects which stand out in the image and attract most people ¶VLPPHGLDWHDWWHQWLRQ7KHVWDQGDUGway to detect salient ob MHFWVLVILUVWO\XVLQJVDOLHQF\GHWHFWLRQPHWKRGVWRJHQHUDWHVDOLHQF\PDSVLQZKLFKDSL[HO¶VJUH\value is proportional to its degree of saliency and then segmenting salient objects in saliency maps. Many salient detection methods can be divided into three categories: local contrast methods, global rarity methods and other methods. In local contrast methods, regions which have high contrast with local neighbouring regions are regarded as salient regions. Itti et al. [7] decompose an image into several feature maps . The saliency in each feature map is measured by local center-surround difference in several scales and saliency of different feature maps are integrated to a final saliency

Video saliency detection aims to pop out the most salient regions in every frame of a video. Up to now, many efforts have been made from various aspects for video saliency detection. Unfortunately, the existing video saliency models are very likely to fail in challenging videos with complicated motions and complex scenes. Therefore, in this paper, we propose a novel framework to improve the saliency detection results generated by existing video saliency models. The proposed framework consists of three key steps including localized estimation, spatiotemporal refinement, and saliency update. Specifically, the initial saliency map of each frame in a video is first generated by using an existing saliency model. Then, by considering the temporal consistency and strong correlation among adjacent frames, the localized estimation models, which are generated by training the random forest regressor within a local temporal window, are employed to generate the temporary saliency map. Finally, by taking the appearance and motion information of salient objects into consideration, the spatiotemporal refinement step is deployed to further improve the temporary saliency map and generate the final saliency map. Furthermore, such an improved saliency map is then utilized to update the initial saliency map and provide reliable cues for saliency detection in the next frame. The experimental results on four challenging datasets demonstrate that the proposed framework is able to consistently and significantly improve the saliency detection performance of various video saliency models, thereby achieving the state-of-the-art performance.

Saliency and co-saliency detection aim to distinguish conspicuous foreground objects from single and multiple images, thus are essential in many multimedia and vision applications. To achieve balanced efficiency and accuracy, most recent successful saliency detectors are based on superpixels. However, saliency detection with single-scale superpixel segmentation may fail in capturing intrinsic salient objects of complex natural scenes with small-scale high-contrast backgrounds. To tackle this problem, we present a simple strategy using multiscale superpixels to jointly detect salient object via low-rank optimisation. Specifically, we first build a multiscale superpixel pyramid and derive the corresponding saliency map by multimodal saliency features and priors at each single scale. Then, we use joint low-rank analysis of multiscale saliency maps to obtain a more reliable and adaptively-fused saliency map, which properly takes all scales saliency into account. We further propose a GMM generative co-saliency prior to enable the above approach to detect co-salient objects from multiple images. Extensive experiments on benchmark datasets validate the effectiveness and superiority of the proposed saliency and co-saliency detector over state-of-the-arts.

Many existing salient object detection methods are dedicated to fusing features from different levels of a pre-trained convolutional neural network (CNN). However, these methods can easily lead to internal discontinuities within the salient objects because of unreasonable feature fusion strategies and short-range dependencies resulting from common convolution and pooling operations. In this paper, we propose a novel non-local duplicate pooling (NLDP) network to overcome these internal discontinuities. NLDP begins by removing the first few convolutional layers of a classic CNN, which have small receptive fields and require large amounts of calculation. A novel duplicate pooling module (DPM) is then used to generate richer and more detailed saliency maps. This is achieved by constructing a double-pathway that can integrating partial feature maps. Within the DPM, a non-local module (NLM) is used to obtain long-range dependencies. This enhances the internal continuities between the saliency maps. Comprehensive experiments conducted on six benchmark datasets have confirmed the increased effectiveness and detection speed of our method in relation to other salient object detection methods.

Salient object detection aims to detect the most attractive objects in images, which has been widely used as a fundamental of various multimedia applications. In this paper, we propose a novel salient object detection method for RGB-D images based on evolution strategy. Firstly, we independently generate two saliency maps on color channel and depth channel of a given RGB-D image based on its super-pixels representation. Then, we fuse the two saliency maps with refinement to provide an initial saliency map with high precision. Finally, we utilize cellular automata to iteratively propagate saliency on the initial saliency map and generate the final detection result with complete salient objects. The proposed method is evaluated on two public RGB-D datasets, and the experimental results show that our method outperforms the state-of-the-art methods.

News items

Due to the rapid development of deep learning, salient object detection has achieved promising results in recent years. However, how to construct a powerful saliency detection network to generate saliency maps with completely highlighted salient objects and effectively suppressed background noise still remains an open and challenging problem. In this paper, we propose a novel trifurcated cascaded refinement network (TCRNet) to explore multi-level feature fusion and global information representation. Specifically, all the side-output features from the backbone network are divided into three branches (i.e., global information, deep information and shallow information) according to feature similarities, and then the global contexts, semantic knowledge and fined details respectively generated by the three branches are integrated in a cascaded refinement way. This refinement strategy aims to guide the feature learning of important regions and suppress background noises. Moreover, we propose a cross-level feature fusion (CFF) module to fuse multi-level similar features within a same branch by exploring their interrelationship, thus capturing the important semantic information and structure details. To this end, the complementarity of similar features is utilized to refine feature at each level by sharing an encoded spatial weight map. Besides, we design a context-aware feature learning (CFL) module to capture global contexts in a single layer by taking account of both single-feature representation and multi-feature interaction, thus providing important location information of salient objects. Extensive experiments on five benchmarks are conducted to demonstrate that the proposed network TCRNet performs favorably against 20 state-of-the-art salient object detection methods on five benchmark datasets, indicating the effectiveness and superiority of our method.

Saliency detection is a technique to analyze image surroundings to extract relevant regions from the background. In this paper, we propose a simple and effective saliency detection method based on image sparse representation and color features combination. First, the input image is segmented into non-overlapping super-pixels, so as to perform the saliency detection at the region level to reduce computational complexity. Then, a background optimization selection scheme is used to construct an appropriate background template. Based on this, a primary saliency map is obtained by using image sparse representation. Next, through the linear combination of color coefficients we generate an improved saliency map with more prominent salient regions. Finally, the two saliency maps are integrated within Bayesian framework to obtain the final saliency map. Experimental results show that the proposed method has desirable detection performance in terms of detection accuracy and running time.

There are two main areas in saliency detection: fixation prediction and salient object detection. Researchers always use bottom-up low-level features and straightforward rules for salient object detection. However these rules are unreliable in common scenes. As a result, most salient object detection technologies can gain a fine performance in limited situation. While in a more complex scene (such as PASCAL-S dataset), they may miss the really wanted salient objects. Fixation prediction is a technology of predicting the regions which can attract human's attention. Most fixation prediction technologies are based on the discoveries of neuroscience and cognitive psychology. Their rules for fixation prediction more accord with human's sensory mechanism. Thus, fixation map can provide a more reliable salient priori. Based on above reasons, we propose a novel salient object detection method with fixation priori. We refine fixation map to gain a reliable priori, and conduct salient object detection based on the priori. We perform experiment on two datasets, and find that our method outperforms the comparative state-of-art salient object detection technologies.

Deep (machine) learning in recent years has significantly increased the predictive modeling strengths for applications in the areas of computer vision, speech recognition, and natural language processing. Being heavily data-driven, conventional general-purpose deep learning methods mainly rely on training data to learn task-specific data representations. In this thesis, we focus on leveraging novel learning algorithms in deep learning to tackle visual recognition challenges at the three key levels -- namely pixel, object, and image levels. Throughout the thesis, we demonstrate how each and every of our proposed methods can address a specific visual recognition problem. Firstly, we apply deep learning to improve the saliency detection performance of deep networks. A coarse saliency map of the input image's salient object is initially predicted by a convolutional-deconvolutional network (or equivalently a fully convolutional network). Following that, the coarse saliency map is sequentially refined by a separate network called Recurrent Attentional Convolutional-Deconvolutional Network (RACDNN) that shares its network weights across its sequential steps. At every sequential (temporal) step, the same RACDNN is applied to a newly selected/attended image sub-region and it performs saliency map refinement for that particular sub-region. Despite having many learnable network parameters and no access to additional training data, RADCNN can be trained well and it outperforms the "single-step" (coarse saliency detection) baseline and state-of-the-art saliency detection methods by large margins, on several saliency detection benchmark datasets. Secondly, we introduce auto-encoder weight transfer networks (AE-WTN+), a deep model for scaling up object detection. Conventional WTN transfers object class knowledge from the classification weights of a pretrained large-scale image classification network, to the classification weights of an object detection network. However, they suffer from under-fitting and are not able to preserve the rich object class information of novel classes. In this work, we propose a new WTN method -- AE-WTN+ which makes use of normalization techniques to ease network optimization. Inputs and intermediate features are normalized to improve trainability for reduced under-fitting. More importantly, a novel auto-encoding (reconstruction) loss is proposed to encourage information preservation of all classes in the weight predictions of AE-WTN+. This enables the predicted weights of AE-WTN+ to maintain the class discriminability and neighbourhood relationships contained in the pre-trained large-scale classification weights. Experiments on large-scale detection datasets validate the effectiveness of AE-WTN+ on both seen and novel classes. Thirdly, we improve the efficiency of cross-layer network connections for very deep convolutional network in the context of image classification. This gives rise to a new convolutional network architecture called Deluge Networks (DelugeNets) which pass the output (feature activations) of any preceding composite network layer as direct inputs to all succeeding composite layers. For the incoming feature activations of preceding composite layers, the succeeding composite layers first apply rather lightweight cross-layer depthwise convolutional weights on them for feature aggregation. The heavy lifting is carried out by the last convolutional weight layer in each preceding composite layer that performs cross-channel convolutions. The proposed technique enables unimpeded information flow among many layers in very deep DelugeNets with great efficiency. Experiments on small-scale and large-scale datasets show that DelugeNets perform competitively to state-of-the-art deep convolutional networks at lower computational and parameter costs. Fourthly, we propose Stochastic Downsampling (SDPoint), a method to overcome a major limitation suffered by conventional deep convolutional networks -- their computational costs during inference are fixed and cannot be changed. SDPoint downsamples the feature maps at a randomly selected point (layer index) in the network hierarchy during training. The many downsampling configurations known as SDPoint instances each entail a unique downsampling point and downsampling ratio. The same convolutional network weights are shared across the different SDPoint instances that downsample feature maps differently. During inference, the computational cost of a network trained with SDPoint can be instantaneously adjusted to fit a given computational budget, by manually selecting an appropriate SDPoint instance. Additionally, sharing weights between different feature map scales provides significant regularization benefits, making the networks trained with SDPoint less sensitive to scales and more competent. In image classification experiments, SDPoint demonstrates significant cost-accuracy and computational advantages, over independently-trained (non-weight-shared) baselines with various inference costs.

In this paper, a novel saliency detection algorithm is proposed to fuse both the background and foreground information while detecting salient objects in complex scenes. Firstly, we extract background seeds as well as their spatial information from image borders to construct a background-based saliency map. Then, an optimal contour closure is selected as the foreground region according to the first-stage saliency map. The optimal contour closure can provide a preferable description for salient object. We compute a foreground-based saliency map using the selected foreground region and integrate it with the background-based one. Finally, the unified saliency map is further refined to obtain a more accurate result. Experimental results show that the proposed algorithm can achieve favorable performance compared to the state-of-the-art ones.

Though there are many computational models proposed for saliency detection, few of them take object boundary information into account. This paper presents a hierarchical saliency detection model incorporating probabilistic object boundaries, which is based on the observation that salient objects are generally surrounded by explicit boundaries and show contrast with their surroundings. We perform adaptive thresholding operation on ultrametric contour map, which leads to hierarchical image segmentations, and compute the saliency map for each layer based on the proposed robust center bias, border bias, color dissimilarity and spatial coherence measures. After a linear weighted combination of multi-layer saliency maps, and Bayesian enhancement procedure, the final saliency map is obtained. Extensive experimental results on three challenging benchmark datasets demonstrate that the proposed model outperforms eight state-of-the-art saliency detection models.

Most existing light field saliency detection methods have achieved great success by exploiting unique light field data-focus information in focal slices. However, they process light field data in a slicewise way, leading to suboptimal results because the relative contribution of different regions in focal slices is ignored. How we can comprehensively explore and integrate focused saliency regions that would positively contribute to accurate saliency detection. Answering this question inspires us to develop a new insight. In this article, we propose a patch-aware network to explore light field data in a regionwise way. First, we excavate focused salient regions with a proposed multisource learning module (MSLM), which generates a filtering strategy for integration followed by three guidances based on saliency, boundary, and position. Second, we design a sharpness recognition module (SRM) to refine and update this strategy and perform feature integration. With our proposed MSLM and SRM, we can obtain more accurate and complete saliency maps. Comprehensive experiments on three benchmark datasets prove that our proposed method achieves competitive performance over 2-D, 3-D, and 4-D salient object detection methods. The code and results of our method are available at https://github.com/OIPLab-DUT/IEEE-TCYB-PANet.

We present a novel, robust estimation method to distinguish salient objects from complicated, dynamic backgrounds in videos. In this method, we propose a novel approach to model motion energy based on motion magnitude, motion orientation, gradient flow field, and spatial gradient of the video frame. Furthermore, an effective spatiotemporal objectness map is also proposed to estimate a compact object-like region in the current video frame leveraging both the objectness proposals and the saliency map of the previous frame. Then the current video frame is oversegmented into the granularity of superpixels using the simple linear iterative clustering algorithm. Each superpixel is designated as a node of a graph. The similarity between adjacent superpixels will be assigned as the weight of an edge that connects these two nodes. The feature values of motion energy and spatiotemporal objectness within each superpixel will be averaged respectively, and used to graphically cluster similar superpixels to form the detected salient object. Extensive experiments comparing this proposed new method against twelve existing salient object detection (SOD) methods have been performed using the benchmark datasets unconstrained video saliency detection and densely annotated video segmentation. Superior performance of this proposed SOD method has been observed through three well-known performance metrics: precision-recall curves, F-measure curves, and the mean absolute error.