SuperRare: an Object-oriented Saliency Algorithm Based on Superpixels Rarity
نویسندگان
چکیده
SuperRare is a new object-oriented attention algorithm based on the notion of rarity: rare regions are worthy of attention. The main novelty of the model is to use superpixels of several sizes instead of simple pixels. This approach allows SuperRare to react efficiently to salient objects of any size. The model is validated on Jian Li’s database, a database considering both large, medium and small salient objects. It is compared with other 9 recent state-of-the-art object-oriented saliency models. Even if the proposed algorithm is solely based on color rarity, we reach and even surpass the state-of-the-art models for the detection of salient objects. We discuss the influence of the color space on our model and how we have tried to limit this influence.
منابع مشابه
Automatic salient object segmentation based on context and shape prior
We propose a novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, i.e., a salient object has a well-defined closed boundary. Our approach is formalized as iterative energy minimization framework, leading to binary segmentation of the salient object. Such energy minimization is initialized with saliency map which is c...
متن کاملSaliency Detection in Aerial Imagery Using Multi-Scale SLIC Segmentation
Object detection in a huge volume of aerial imagery requires first detecting the salient regions. When an image is over-segmented by the superpixels, the latters will adhere to object boundaries, resulting in their shape deformation and size variation, which can be used as the saliency measure. The normalized Hausdorff distances from the inner pixels to boundary of the superpixels are then tran...
متن کاملSaliency Segmentation based on Learning and Graph Cut Refinement
Saliency detection is a well researched problem in computer vision. In previous work, most of the effort is spent on manually devising a saliency measure. Instead we propose a simple algorithm that uses a dataset with manually marked salient objects to learn to detect saliency. Building on the recent success of segmentation-based approaches to object detection, our saliency detection is based o...
متن کاملMulti-scale region-based saliency detection using W2 distance on N-dimensional normal distributions
We present a new segment-based method for saliency detection based on multi-size superpixels that combines local and global saliency cues. We extract superpixels at several scales and represent each superpixel with a normal distribution in CIE-Lab space estimated from its associated pixels. Global saliency is computed by grouping similar superpixels to estimate the spatial distribution of color...
متن کاملExploiting Randomized Prim’s Algorithm and Background Contrast for Saliency Detection
The geodesic saliency method in the literature was based on the boundary and connectivity priority, which assumed that most of the background regions can touch the image boundaries. It cannot deal with the images with complex backgrounds or variant textures. To address such problem, we propose an improved saliency detection method by involving the important foreground priority. First, the stati...
متن کامل