Abstract
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding of achievements and issues remains lacking. We aim to provide a comprehensive review of recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics for salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance, and suggest future research directions.
Highlights
Humans are able to detect visually distinctive, so called salient, scene regions effortlessly and rapidly in a pre-attentive stage
We only focus on salient object detection, a research area that has greatly developed in the past twenty years, and in particular since 2007 [20]
multilayer perceptrons (MLPs)-based works rely mostly on segment-level information and classification networks. These image patches are normally resized to a fixed size and are fed into a classification network which is used to determine the saliency of each patch
Summary
Humans are able to detect visually distinctive, so called salient, scene regions effortlessly and rapidly in a pre-attentive stage. These filtered regions are perceived and processed in finer detail for the extraction of richer high-level information, in an attentive stage. Following the seminal works by Itti et al [24] and Liu et al [25], models adopt the saliency concept to simultaneously perform the two stages together. This is witnessed by the fact that these stages have not been separately evaluated. The second stage falls into the realm of classic segmentation problems in computer vision but with the difference that here, accuracy is only determined by the most salient object
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
