A novel saliency measure using combined spatial redundancy and local appearance
نویسندگان
چکیده
In this paper, we present a novel approach to saliency detection. The method we propose here aims at synthesizing common knowledge of saliency in an image. We define a visually salient region with following two parameters; the spatial redundancy and its local appearance. The former is its probability of occurrence within the image, which is a quantification of the " rarity " of the concerned region, whereas the latter defines how much information is contained within the region, and it can be quantified using the entropy. By combining the global spatial redundancy measure and local entropy, we can achieve a simple, yet robust measure. We evaluated and compared it to Itti's and the spectral residual methods, and it has shown a significant improvement of performance.
منابع مشابه
Compressed-Sampling-Based Image Saliency Detection in the Wavelet Domain
When watching natural scenes, an overwhelming amount of information is delivered to the Human Visual System (HVS). The optic nerve is estimated to receive around 108 bits of information a second. This large amount of information can’t be processed right away through our neural system. Visual attention mechanism enables HVS to spend neural resources efficiently, only on the selected parts of the...
متن کاملA Novel Approach to Background Subtraction Using Visual Saliency Map
Generally human vision system searches for salient regions and movements in video scenes to lessen the search space and effort. Using visual saliency map for modelling gives important information for understanding in many applications. In this paper we present a simple method with low computation load using visual saliency map for background subtraction in video stream. The proposed technique i...
متن کاملNon-local spatial redundancy reduction for bottom-up saliency estimation
In this paper we present a redundancy reduction based approach for computational bottomup visual saliency estimation. In contrast to conventional methods, our approach determines the saliency by filtering out redundant contents instead of measuring their significance. To analyze the redundancy of self-repeating spatial structures, we propose a non-local self-similarity based procedure. The resu...
متن کاملA Saliency Detection Model via Fusing Extracted Low-level and High-level Features from an Image
Saliency regions attract more human’s attention than other regions in an image. Low- level and high-level features are utilized in saliency region detection. Low-level features contain primitive information such as color or texture while high-level features usually consider visual systems. Recently, some salient region detection methods have been proposed based on only low-level features or hig...
متن کاملA parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos
Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these m...
متن کامل