Segmenting Salient Objects from Images and Videos

Abstract

In this paper we introduce a new salient object segmentation method, which is based on combining a saliency measure with a conditional random field (CRF) model. The proposed saliency measure is formulated using a statistical framework and local feature contrast in illumination, color, and motion information. The resulting saliency map is then used in a CRF model to define an energy minimization based segmentation approach, which aims to recover well-defined salient objects. The method is efficiently implemented by using the integral histogram approach and graph cut solvers. Compared to previous approaches the introduced method is among the few which are applicable to both still images and videos including motion cues. The experiments show that our approach outperforms the current state-of-the-art methods in both qualitative and quantitative terms.

Detecting and Removing Visual Distractors for Video Aesthetic Enhancement

“…Zhai and Shah [34] use spatiotemporal cues to calculate the saliency map on each frame. Rahtu et al [35] and Liu et al [36] employed optimization frameworks such as CRFs to detect saliency using energy minimization, since they can be applied to data that are multi-dimensionally correlated.…”

Fusing generic objectness and visual saliency for salient object detection

“…Hou and Zhang [8] and Achanta et al [2] both use an image-dependent saliency threshold to segment the objects. Liu et al [14] and Rahtu et al [19] instead take saliency as one of the features in the unary term of a conditional random field model. Once the parameters have been learned, single salient object detection can be achieved through inference.…”

“…Despite the close connection between saliency and objectness, existing approaches [3,5,12,14,15,19,20] still lack a good computational model to thoroughly explore the two concepts and their mutual effects. Only one single direction of the interactions is considered: The techniques in [5,12,15] exploit object detection to help saliency estimations, while those in [3,14,19,20] use saliency information Figure 2.…”

“…Only one single direction of the interactions is considered: The techniques in [5,12,15] exploit object detection to help saliency estimations, while those in [3,14,19,20] use saliency information Figure 2. Inefficiency of saliency detection and object detection.…”

Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation

“…For instance, Rahtu et al [11] estimate (2), by approximating both P (f |1) and P (f |0) using histogram approximation over pixels' color values. Moreover, they assume P (0) and P (1) are constant.…”