Software hardware method based on remote sensing image SIFT processing
A remote sensing image and hardware-based technology, applied in the direction of processor architecture/configuration, computer components, instruments, etc., can solve problems such as huge amount of computation, high algorithm complexity, etc., to improve computing efficiency, increase processing speed, and improve real-time performance Effect
Pending Publication Date: 2020-11-20
PEKING UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the SIFT algorithm needs to construct a feature vector of up to 128 dimensions for each feature point, and the complexity of the algorithm is relatively high. Although the speed of the SIFT algorithm improved by H Bay, YanKe, Zheng Yongbin, etc. Under the processing requirements of remote sensing images, it will still bring a huge amount of computation
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] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0039] In order to make the technical problems, technical solutions and beneficial effects to be solved by the embodiments of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0040] see figure 1 , the software part and hardware part of the system are designed separately. The design process of the software part includes: based on the SIFT algorithm program on the PC side, adapting the SIFT algorithm to the characteristics of the DSP platform and transplanting it, using the sample diagram for simulation testing, completing the SIFT algorithm writing on the DSP side, and building multi-core pro...
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 software hardware method based on remote sensing image SIFT processing. The method comprises the following steps: 1) modifying an SIFT algorithm, namely deleting an OpenCV library function called in the SIFT algorithm, and rewriting the OpenCV library function by using a C language; 2) establishing an SIFT image scale space by using the modified SIFT algorithm, detectingan extreme point of the image scale space, positioning a key point, determining a key point direction, and describing the key point, wherein an SIFT image scale space is created by adopting a Gaussianscale space and a hierarchical filtering strategy based on a differential Gaussian DoG scale space; and subtracting adjacent images in the Gaussian scale space to obtain an image reconstructed pyramid as a DoG pyramid, taking the extreme point of the image scale space as a local extreme point in the DoG scale space, and determining a key point, a key point direction and key point description according to the local extreme point in the DoG scale space.
Description
technical field [0001] The invention relates to the fields of aerospace remote sensing, computer imagery, photogrammetry and the like, and in particular to a software-hardware method based on SIFT processing of remote sensing images. Background technique [0002] In the fields of UAV remote sensing, aerial image processing, and photogrammetry, the traditional method is to apply the SIFT algorithm based on PC platform software when performing image matching and splicing on the acquired aerial images. With the development of photographic technology and storage technology, the clarity and image size of aerial images are increasing at an extremely fast speed, which also means that the image processing process will consume more time and reduce efficiency. At present, the use of traditional PC equipment cannot meet the efficiency requirements of aerial image processing, and it is difficult to meet the current application requirements in the field of UAV remote sensing in terms of ...
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): G06K9/46G06T1/20
CPCG06T1/20G06V10/462
Inventor 晏磊赵海盟蒋兴伟张鹏张飞舟林沂刘帆陈林刘思远丁静于田张子晗
Owner PEKING UNIV