Image Segmentation Method Based on Grayscale Transfer and Renyi Entropy
A technology of image segmentation and grayscale histogram, which is applied in the field of image processing, can solve the problems that cannot meet the actual needs, can not get better segmentation effect, and the image has too many noise points
Inactive Publication Date: 2016-07-06
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the actual simulation process, it can be found that the optimal thresholds solved by the iterative method and Otsu method in complex scenes are too small, and the segmented images have more noise points, which cannot meet the actual needs
However, other threshold segmentation methods cannot obtain better segmentation results for images in areas such as Gobi or deserts with complex terrain environments.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] Such as figure 1 Shown, the present invention is based on the image segmentation method of grayscale shift and Renyi entropy and comprises the following steps:
[0050] Step 1: Extract the image f(x, y) from the video stream collected by the aircraft, and f(x, y) is the original image. Generally, the camera of the aircraft will start real-time acquisition at a distance of 3000 meters. From the collected video stream The extracted image f(x, y) is stored in the static memory in YCbCr format, where the Y component is the brightness component of the image f(x, y), and the Cb and Cr components are the The concentration offset components of blue and red, in practice, perform grayscale histogram statistics based on the brightness component in the image f(x,y), that is, draw a grayscale histogram (the grayscale histogram here is the traditional grayscale histogram);
[0051]Step 2: Perform grayscale shifting on the statistical grayscale histogram;
[0052] Step 3: Carry out...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an image segmentation method based on grey scale flitting and a Renyi entropy. The method comprises the following steps: extracting an image f(x, y) from a video streaming acquired by an aircraft, performing grey scale histogram statistics on a basis of a brightness component in the image f(x, y); performing grey scale flitting upon the grey scale histogram; performing binary image segmentation based on the Renyi entropy upon the flitting grey scale histogram obtained after grey scale flitting so as to obtain a binary image of which an obstacle area and a background can be distinguished correctly. According to the method, the grey scale histogram obtained by statistics upon an original image is subjected to grey scale flitting improvement, and then the flitting grey scale histogram obtained after grey scale flitting is subjected to binary image segmentation based on Renyi entropy so as to obtain the binary image of which the obstacle area and the background can be distinguished correctly, so that the obstacle area can be effectively eliminated, and a reliable basis is provided for searching for a flat area where the aircraft can land safely.
Description
technical field [0001] The invention relates to an image segmentation method based on grayscale transfer and Renyi entropy, which belongs to the field of image processing. Background technique [0002] When the aircraft (UAV) pre-lands, it will collect video images from an altitude of 3,000 meters through the surveillance camera installed on it, and find a flat area in the image for the aircraft to land safely. As far as the collected images are concerned, the images may include water areas, buildings, highways and other scenery. Therefore, in order to land safely, the above-mentioned scenery must be detected in real time and accurately, and the image segmentation can be performed in real time to provide a safe landing for the aircraft. flat area. [0003] At present, image segmentation can be divided into two segmentation methods, transform domain and time domain. [0004] The segmentation methods of transform domain, such as wavelet transform, Fourier transform, etc., ar...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
Inventor 邢素霞李杨
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY