Salient object detection from low contrast images based on local contrast enhancing and non-local feature learning
- PDF / 2,203,278 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 11 Downloads / 187 Views
ORIGINAL ARTICLE
Salient object detection from low contrast images based on local contrast enhancing and non-local feature learning Tengda Guo1 · Xin Xu1,2
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Salient object detection can facilitate numerous applications. Traditional salient object detection models mainly utilize lowlevel hand-crafted features or high-level deep features. However, they may face great challenges in the nighttime scene, due to the difficulties in extracting well-defined features to represent saliency information from low contrast images. In this paper, we present a salient object detection model based on local contrast enhancing and non-local feature learning. This model extracts non-local feature combines with local features under a unified deep learning framework. Besides, a deeply enhanced network is employed as a preprocessing of the low contrast images to assist our saliency detection model. The key idea of this paper is firstly hierarchically introducing a non-local module with local contrast-processing blocks, to provide a detailed and robust representation of saliency information. Then, an encoder-decoder image-enhanced network with full convolution layers is introduced to process the low contrast images for higher contrast and completer structure. As a minor contribution, this paper contributes a new dataset, including 676 low contrast images for testing our model. Extensive experiments have been conducted in the proposed low contrast image dataset to evaluate the performance of our method. Experimental results indicate that the proposed method yields competitive performance compared to existing state-of-the-art models. Keywords Salient object detection · Low contrast · Non-local feature · Image-enhanced network
1 Introduction Saliency detection refers to extract significant areas and targets (i.e., region of interest) in images. Aiming to imitate the characteristic of human visual attention system, saliency detection model is able to separate predominant objects from images in different scenes. As an effective pre-proceeding step, saliency detection has a wide range of applications in numerous computer vision missions, including pedestrian detection [1], identification [2], semantic segmentation [3, 4], object retargeting [5, 6], image retrieval [7, 8], visual tracking [9, 10], photo-synthesis [11, 12], etc. Traditional saliency detection models generally design hand-crafted low-level features to estimate image saliency
B
Xin Xu [email protected]
1
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China
2
Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China
by calculating the contrast between pixels (or regions) and their surroundings. As recent years have gone on the advance of deep learning, high-level features have demonstrated their superior performance compared to conventional met
Data Loading...
