Abstract
Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.
Highlights
Salient object detection (SOD) is an important computer vision task aimed at precise detection and segmentation of visually distinctive image regions from the perspective of the human visual system (HVS)
With the availability of adequate training datasets, classifier/regressor can be trained to automatically integrate a large but fixed number of regional features for the most discriminative ones. The performance of such learning based models is superior to their heuristic counterparts, the advances in conventional saliency detection still fall short in accurately handling saliency detection in challenging scenarios
The salient object detection (SOD) subnet combines the FIN map with backbone deeper side features in a top-down scheme to generate initial saliency prediction. These saliency maps are refined by an iterative conditional random fields (CRFs) for the self-training of the SOD branch
Summary
Salient object detection (SOD) is an important computer vision task aimed at precise detection and segmentation of visually distinctive image regions from the perspective of the human visual system (HVS). SOD is different from fixation prediction as models for the former should detect and segment the entire extent of salient regions/objects in the scene. A general approach adopted by conventional SOD models to accomplish this goal is to assign high probability values to salient elements in a scene while producing a saliency map. Once detected, techniques such as thresholding can be used to segment out the whole salient object. Various complementary heuristic saliency priors have been deployed to effectively capture the most conspicuous object regions in images These conventional models have been proven to be efficient and effective in relatively simple scenes with a single object and/or clean background.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have