Automatic salient object segmentation based on context and shape prior

Jiang, Huaizu; Wang, Jingdong; Yuan, Zejian; Li, Shipeng; Zheng, Nanning

doi:10.5244/c.25.110

Cited by 397 publications

(334 citation statements)

References 31 publications

Supporting

Mentioning

331

Contrasting

Order By: Relevance

“…The baselines include training based low-rank matrix recovery (TLR) model [31], region contrast based model (RC) [8], kernel density estimation based (KDE) model [27], context and shape prior based (CBS) model [21], contextaware (CA) model [14], frequency-tuned (FT) model [1], graph based (GB) model [18] and spectral residual (SR) model [19]. For evaluation of other recent models, one can refer to the benchmarking report [5].…”

Section: Baselinesmentioning

confidence: 99%

“…A number of computational models measure the saliency based on global, local and regional contrasts with different forms [1,8,14,21], and a variety of theories and methods, including information theory [6,37], graph theory [4,18], machine learning [26], statistical model [27], frequency domain analysis [15,19], have been exploited to build saliency models. These models may work well for objects within consistent scenes, thus, most of them are validated on relatively simple dataset like MSRA-1000 [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation Driven Low-rank Matrix Recovery for Saliency Detection

Zou¹,

Kpalma²,

Li³

et al. 2013

Procedings of the British Machine Vision Conference 2013

114

View full text Add to dashboard Cite

Low-rank matrix recovery (LRMR) model, aiming at decomposing a matrix into a low-rank matrix and a sparse one, has shown the potential to address the problem of saliency detection, where the decomposed low-rank matrix naturally corresponds to the background, and the sparse one captures salient objects. This is under the assumption that the background is consistent and objects are obviously distinctive. Unfortunately, in real images, the background may be cluttered and may have low contrast with objects. Thus directly applying the LRMR model to the saliency detection has limited robustness. This paper proposes a novel approach that exploits bottom-up segmentation as a guidance cue of the matrix recovery. This method is fully unsupervised, yet obtains higher performance than the supervised LRMR model. A new challenging dataset PASCAL-1500 is also introduced to validate the saliency detection performance. Extensive evaluations on the widely used MSRA-1000 dataset and also on the new PASCAL-1500 dataset demonstrate that the proposed saliency model outperforms the state-of-the-art models.

show abstract

Section: Baselinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Segmentation Driven Low-rank Matrix Recovery for Saliency Detection

Zou¹,

Kpalma²,

Li³

et al. 2013

Procedings of the British Machine Vision Conference 2013

114

View full text Add to dashboard Cite

show abstract

“…Recently the models have been used to boost some computer vision and pattern recognition techniques such as object detection [113], [124], [125], object recognition [126]- [131], action recognition [132], [133], segmentation [37], [114], [115], [134], [135] and background subtraction [136]. Besides, specific applications include video summarization [137] and compression [138], scene understanding [139]- [141], computer-human interaction [98], [142]- [147], robotics [132], [148]- [150], and driver assistance [151], [152].…”

Section: Discussionmentioning

confidence: 99%

“…In such cases no subjects nor gaze data are required for the evaluation. With this, salient region extraction techniques such as [114], [115] also employ this measure. Those techniques have different goals from the saliency computation as shown in Sect.…”

Section: Evaluation Measuresmentioning

confidence: 99%

Computational Models of Human Visual Attention and Their Implementations: A Survey

Kimura

Yonetani

Hirayama

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe humans are easily able to instantaneously detect the regions in a visual scene that are most likely to contain something of interest. Exploiting this pre-selection mechanism called visual attention for image and video processing systems would make them more sophisticated and therefore more useful. This paper briefly describes various computational models of human visual attention and their development, as well as related psychophysical findings. In particular, our objective is to carefully distinguish several types of studies related to human visual attention and saliency as a measure of attentiveness, and to provide a taxonomy from several viewpoints such as the main objective, the use of additional cues and mathematical principles. This survey finally discusses possible future directions for research into human visual attention and saliency computation. key words : human visual attention, computational model, saliency, bottom-up, top-down MotivationDeveloping sophisticated algorithms for detecting and recognizing something like objects from a given image and video has been a long distance challenge in pattern recognition and computer vision research fields. In fact, a huge number of studies, techniques and theories related to object detection and recognition have already been developed. In particular, several methods for detecting certain specific categories of objects such as human bodies and human faces have already been put to practical use in for example surveillance, authentication and the human-centric enhancement of image quality, with the best possible use of the prior knowledge of target objects (human bodies and faces) [1], [2]. However, generic object detection and recognition without any constraints as regards the target objects has remained major challenge, because (1) various kinds of objects might constitute the targets and (2) target objects in the same category might have different appearances due to variations of instances in a specific category, illumination changes and so on. † † The author is with the Graduate School of Informatics, Kyoto University, Kyoto-shi, 606-8501 Japan.† † † The author is with the Graduate School of Information Science, Nagoya University, Nagoya-shi, 464-8603 Japan.a) E-mail: akisato@ieee.org b) E-mail: yonetani@vision.kuee.kyoto-u.ac.jp c) E-mail: hirayama@is.nagoya-u.ac.jp DOI: 10.1587/transinf.E96.D.562 On the other hand, human beings seem to be able to detect various kinds of objects without any thought or effort. For example, from Fig. 1 left, we can easily and instantly detect a red car, a blue traffic sign and a broad white line. Visual attention [3] is considered to play an important role in achieving this function. Visual attention is one of the built-in mechanisms of the human visual system that quickly selects regions in a visual scene, which are most likely to contain items of interest. Such a pre-selection mechanism focusing only on relevant data would be essential in enabling computers to undertake subsequent processing such as generic o...

show abstract

“…However, it remains unclear how this strategy can act on the performance in other classification framework. In contrast with [39], where only one saliency detection method (context-aware) is evaluated, we investigate fifteen kinds of typical methods, which are AC [53], attention by information maximization (AIM) [54], context-aware (CA) [52], context-based (CB) [55], discriminative regional feature integration (DRFI) [56], frequency-tuned (FT) [57], graph-based visual saliency (GBVS) [58], IM [59], low rank matrix recovery (LRR) [60], maximum symmetric surround (MSS) [61], rarity-based saliency (RARE) [62], salient segmentation (SEG) [63], self-resemblance (SeR) [64], spectral residual (SR) [65] and saliency using natural statistics (SUN) [66], and present detailed comparative experiments for them. We do not review these methods due to the limited space, and details of each method can be found in its corresponding paper.…”

Section: Feature Coding Based On the Saliency Mapmentioning

confidence: 99%

Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery

Xia

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Scene classification of high-resolution remote sensing (HRRS) imagery is an important task in the intelligent processing of remote sensing images and has attracted much attention in recent years. Although the existing scene classification methods, e.g., the bag-of-words (BOW) model and its variants, can achieve acceptable performance, these approaches strongly rely on the extraction of local features and the complicated coding strategy, which are usually time consuming and demand much expert effort. In this paper, we propose a fast binary coding (FBC) method, to effectively generate efficient discriminative scene representations of HRRS images. The main idea is inspired by the unsupervised feature learning technique and the binary feature descriptions. More precisely, equipped with the unsupervised feature learning technique, we first learn a set of optimal "filters" from large quantities of randomly-sampled image patches and then obtain feature maps by convolving the image scene with the learned filters. After binarizing the feature maps, we perform a simple hashing step to convert the binary-valued feature map to the integer-valued feature map. Finally, statistical histograms computed on the integer-valued feature map are used as global feature representations of the scenes of HRRS images, similar to the conventional BOW model. The analysis of the algorithm complexity and experiments on HRRS image datasets demonstrate that, in contrast with existing scene classification approaches, the proposed FBC has much faster computational speed and achieves comparable classification performance. In addition, we also propose two extensions to FBC, i.e., the spatial co-occurrence matrix and different visual saliency maps, for further improving its final classification accuracy.

show abstract

Automatic salient object segmentation based on context and shape prior

Cited by 397 publications

References 31 publications

Segmentation Driven Low-rank Matrix Recovery for Saliency Detection

Segmentation Driven Low-rank Matrix Recovery for Saliency Detection

Computational Models of Human Visual Attention and Their Implementations: A Survey

Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery

Contact Info

Product

Resources

About