scispace - formally typeset
Search or ask a question
Author

Wei Jiang

Bio: Wei Jiang is an academic researcher. The author has contributed to research in topics: Image segmentation & Region growing. The author has an hindex of 1, co-authored 1 publications receiving 5 citations.

Papers
More filters
Patent
27 Apr 2017
TL;DR: In this article, a multi-view segmentation algorithm is used where a four-dimensional (4D) graph-cut is constructed by adding links across neighboring views over space and for consecutive frames over time.
Abstract: Embodiments are provided for achieving multi-view video foreground-background segmentation with spatial-temporal graph cuts A multi-view segmentation algorithm is used where a four-dimensional (4D) graph-cut is constructed by adding links across neighboring views over space and for consecutive frames over time The segmentation uses both the color values of each input image and the image difference between the input image and the background image to obtain an initial graph-cut, before adding the temporal and spatial links By using the background subtraction results as the initial segmentation seed, no user annotation is needed to perform multi-view segmentation

5 citations


Cited by
More filters
Patent
10 Oct 2017
TL;DR: In this paper, a multi-view model is used to detect the tableware in an image, and then tableware recognition is performed using multi-perspective characteristics to integrate the learned new characteristics.
Abstract: The present invention discloses a tableware detection and recognition method based on a multi-view model. Through the use of the learning framework of the multi-view model, the tableware detection and tableware recognition are combined into a unified frame. First, the multi-view model is used to detect the tableware in an image, and then the tableware recognition is performed using multi-perspective characteristics to integrate the learned new characteristics. The multi-view model is used to detect the tableware in an image, and the characteristics of the super pixel points in multiple views are used to construct a graph model, and then, the confidence of each super pixel at the position of the tableware is learned so as to detect the tableware more accurately. According to the invention, a multi-view fusion algorithm is utilized for characteristics integration so as to construct stronger distinguishing characteristics and to increase the recognition rate. In the construction of the multi-view model, the exponential type weight parameter is used to avoid occurrence that the weight coefficient of the multi-view is zero, so that the characteristics of each view can complement each other.

5 citations

Patent
19 Jan 2018
TL;DR: In this article, a binocular stereoscopic visual system-based foreground segmentation method was proposed, which comprises the following steps of: obtaining a left view and a right view of a same object by utilizing binocular stereo-vision visual system; separating the foreground and background of the left view; defining an energy equation; and endowing foreground pixel points in the foregrounds and background pixels in the background with different labels by utilizing the energy equation so as to separate the foreground's and the backgrounds.
Abstract: The invention discloses a binocular stereoscopic visual system-based foreground segmentation method. The method comprises the following steps of: obtaining a left view and a right view of a same object by utilizing a binocular stereoscopic visual system; separating the foreground and background of the left view and separating the foreground and background of the right view; defining an energy equation; and endowing foreground pixel points in the foregrounds and background pixel points in the backgrounds with different labels by utilizing the energy equation so as to separate the foregrounds and the backgrounds. The method has the beneficial effects that foreground pixel points and the background pixel points in a picture are endowed with different labels through defining the energy equation, so that the foreground pixel points and the background pixel points can be correctly separated and then the foreground segmentation correctness is improved; and according to the method, the foreground segmentation of binocular color images can be realized, so that the method is wide in application range.

2 citations

Patent
07 Sep 2017
TL;DR: In this article, an image processing apparatus comprises generating unit configured to generate a second image by changing a size of a first image such that a region of interest in the second image satisfies a predetermined criterion about a dimension.
Abstract: An image processing apparatus comprises generating unit configured to generate a second image by changing a size of a first image such that a region of interest in the second image satisfies a predetermined criterion about a dimension; and extracting unit configured to extract the region of interest from the second image generated by the generating unit, by applying a Graph-Cut method using a Graph-Cut coefficient corresponding to the criterion to the second image.

1 citations

Patent
11 Jan 2019
TL;DR: In this paper, a remote sensing image change detection method based on feature learning of a shrinking self-encoder was proposed, which includes the steps of utilizing multi-temporal images to generate difference images under different scales to record difference information in a temporal phase map; using a superpixel segmentation algorithm base on SLIC to segment that difference image to obtain a neighborhood feature block with homogeneous geomorphological information; selecting a part of the segmented blocks, and adjusting the scale as atraining sample input to the stack shrink self-Encoder for feature learning; generating new
Abstract: The invention belongs to the technical field of image analysis, and discloses a remote sensing image change detection method based on feature learning of a shrinking self-encoder. The method includesthe steps of utilizing multi-temporal images to generate difference images under different scales to record difference information in a temporal phase map; using a superpixel segmentation algorithm base on SLIC to segment that difference image to obtain a neighborhood feature block with homogeneous geomorphological information; selecting a part of the segmented blocks, and adjusting the scale as atraining sample input to the stack shrink self-encoder for feature learning; generating new difference images on the basis of high-order feature reconstruction extracted by the self-encoder; using ak-mean clustering algorithm to realize binary classification, and obtaining the detection results. The method can be composed of generation of multi-scale difference images, SLIC segmentation of multi-scale difference information, feature learning based on stack shrinking self-encoder and re-difference analysis of feature reconstruction.
Patent
29 Oct 2019
TL;DR: In this paper, an image processing apparatus comprises generating unit configured to generate a second image by changing a size of a first image such that a region of interest in the second image satisfies a predetermined criterion about a dimension.
Abstract: An image processing apparatus comprises generating unit configured to generate a second image by changing a size of a first image such that a region of interest in the second image satisfies a predetermined criterion about a dimension; and extracting unit configured to extract the region of interest from the second image generated by the generating unit, by applying a Graph-Cut method using a Graph-Cut coefficient corresponding to the criterion to the second image.