Correction method for aero-optical effect of road vehicle target images based on knowledge constraints
A knowledge-constrained, aero-optical technology, applied in the field of interdisciplinary science, can solve problems affecting target area correction, affecting algorithm real-time performance, non-target area correction waste, etc., to achieve the effect of improving efficiency and accuracy, and improving efficiency
Inactive Publication Date: 2016-04-13
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of the blind deconvolution algorithms are processed for the whole image, which not only wastes a lot of time for the correction of non-target areas and affects the real-time performance of the algorithm, but also the characteristics of non-target intervals (such as smoothness, etc.) will eventually affect the correction of the target area
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
example
[0071] This example specifically includes the following steps:
[0072] (1) Establishment of vehicle-road spatial constraint relationship
[0073] The road and vehicle areas in the image are extracted by using the vehicle-road spatial constraint relationship in the image; the correction algorithm performs precise correction on road and vehicle areas, and performs rough correction on non-road areas. The needs of remote sensing, detection, navigation and guidance of advanced aircraft.
[0074] The vehicle-road spatial relationship can be expressed as a set:
[0075] V ⋐ R ⋐ I
[0076] In the above formula, the set V represents the vehicle, and the element V in the set V i Represents the i-th type of vehicle; the set R represents the road; the set I represents the image.
[0077] (2) Ground knowledge preparation
[0078] (2.1) Establishment of multi-scale highway template
[0079] Build a multi-scale highway temp...
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 a knowledge-constrained road vehicle infrared image pneumatic optical effect correcting method. The method comprises the steps that a vehicle template and a multi-scale road template are built, and the multi-scale road template is used for extracting road areas in real-time blurred images under the condition of hypersonic velocity; the HU-moment-constrained maximum likelihood estimation algorithm is used for correcting road areas in pneumatic optical effect images, and road area correcting images are obtained; the vehicle template is used for matching vehicle area positions in the road area correcting images to obtain vehicle areas needing to be extracted; the HU-moment-constrained maximum likelihood estimation algorithm is used for correcting the vehicle areas to obtain vehicle area correcting images. According to the method, the recursive processing from thickness to thinness is adopted, accurate correction of interested areas is achieved, correction algorithm efficiency and precision can be greatly improved, and the development requirement of hypersonic velocity flight vehicle optical imaging detection technology is met. The method can greatly improve the correction algorithm efficiency, and meets the requirements for hypersonic velocity flight vehicle navigation, guidance and remote sensing.
Description
technical field [0001] The invention belongs to the field of interdisciplinary science and technology combining aerospace technology and image processing, and in particular relates to a knowledge-constrained aero-optical effect image correction method for a road vehicle target image. Background technique [0002] Remote sensing, detection, navigation and guidance of hypersonic vehicles is an important field in the development of the aerospace industry in the 21st century, and it has important scientific significance and application value in the future high-tech and national economic development. Remote sensing, detection, navigation, and guidance based on hypersonic vehicles face the challenge of aero-optical effects. [0003] Aero-optics is a subject that studies the influence of high-speed flow on imaging and detection of high-speed aircraft. When a high-speed aircraft with an optical imaging detection system flies in the atmosphere, a complex flow field is formed between...
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): G06T7/00G06T7/60G06K9/64
Inventor 张天序刘立何力王正周钢戴小兵姚守悝凡速飞
Owner HUAZHONG UNIV OF SCI & TECH