Abstract
Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, up-sample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.
Highlights
Called pixel-level classification, is the task of clustering parts of image together which belong to the same object class (Thoma 2016)
In the computer vision and image processing area, feature is a piece of information which is relevant for solving the computational tasks
Variety of features are used for semantic segmentation, such as Pixel color, Histogram of oriented gradients (HOG) (Dalal and Triggs 2005; Bourdev et al 2010), Scale-invariant feature transform (SIFT) (Lowe 2004), Local Binary Pattern (LBP) (He and Wang 1990), SURF (Bay et al 2008), Harris Corners (Derpanis 2004), Shi-Tomasi (Shi et al 1994), Sub-pixel Corner (Medioni and Yasumoto 1987), SUSAN (Smith and Brady 1997), Features from Accelerated Segment Test (FAST) (Rosten and Drummond 2005), FAST- ER (Rosten et al 2010), AGAST (Mair et al 2010) and Multiscale AGAST (Leutenegger et al 2011) Detector, Bag-of-visual-words (BOV) (Csurka et al 2004), Pselets (Brox et al 2011), and Textons (Zhu et al 2005), just to name a few
Summary
Called pixel-level classification, is the task of clustering parts of image together which belong to the same object class (Thoma 2016). Two other main image tasks are image level classification and detection. Classification means treating each image as an identical category. Image segmentation can be treated as pixel-level prediction because it classifies each pixel into its category. There is a task named instance segmentation which joints detection and segmentation together. More details can refer to literature (Lin et al 2014; Li et al 2017a)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
