Image identification method for crater
A technology of image recognition and ring pit, applied in the field of image recognition, can solve problems such as low recognition efficiency and high computational complexity
Active Publication Date: 2014-09-10
NAT ASTRONOMICAL OBSERVATORIES CHINESE ACAD OF SCI
View PDF2 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The number of craters on the moon increases exponentially with the decrease of its diameter, and the traditional method of using image data to identify craters has a very high computational cost due to the use of complex mathematical operations for exhaustive traversal. Complexity, especially in the case of high-resolution image data, the recognition efficiency is relatively low
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
[0038] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0039] figure 1 A flow chart of an image recognition method for a ring pit in the present invention is shown. Such as figure 1 As shown, the method includes:
[0040] Step 1, preprocessing the input image data;
[0041] Step 2, identifying the bright area and shadow area of the annular crater from the preprocessed image data, and extracting the edge of the annular crater;
[0042] Step 3, using the morphological relationship of the bright area, shadow area and edge of the annular crater to match, and selecting the eligible annular crater as the suspected annular crater;
[0043] Step 4, using the strong classifier of the annular pit to identify the suspected annular pit, and obtain the identified annular pit, wherei...
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 identification method for a crater. The image identification method for the crater comprises the following steps: 1) pre-processing an image to be identified; 2) identifying a bright area and a shadow area of a crater in the pre-processed image to be identified, and extracting the edge of the crater; 3) matching by a morphological relationship among the bright area, the shadow area and the edge of the crater, and selecting a crater which matches a condition as a suspected crater; and 4) identifying the suspected crater by a strong classifier of the crater to obtain an identified crater, wherein the strong classifier of the crater is obtained in a way that a training sample is subjected to a strong classifier training based on a texture feature by an Adaboost algorithm. According to the image identification method for the crater, which is disclosed by the invention, the crater can be precisely classified and identified only by one-time judgment calculation, and the computation complexity of the crater identification is lowered.
Description
technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an image recognition method for an annular crater, which is a method for quickly identifying a small annular crater in Chang'e-2 CCD image data by using a shadow-bright pattern. Background technique [0002] As a major topographic feature on the moon, craters have always been a research hotspot in the field of lunar science. Through the research and analysis of the shape, size and distribution characteristics of the craters, it is helpful to explain scientific issues such as lunar impact dynamics, lunar geological age and terrain evolution. The identification of annular craters provides a technical means for such research. [0003] From the perspective of recognition methods, the recognition algorithms of ring pits can be roughly divided into three categories: 1) Unsupervised detection algorithms, which use the geometric characteristics of ring pits and oth...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46
Inventor 张舟斌李春来左维
Owner NAT ASTRONOMICAL OBSERVATORIES CHINESE ACAD OF SCI