Hardware acceleration-based low-power consumption real-time binocular camera and use method
A binocular camera, hardware acceleration technology, applied in image analysis, image data processing, instruments, etc., can solve the problem of unsatisfactory depth map, and achieve the effect of low power consumption, speed improvement, and low delay
Active Publication Date: 2018-11-06
长春博立电子科技有限公司
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, when the focal length of the camera and the distance between the two lenses do not match and other factors lead to unsatisfactory quality of the left and right input images, the depth map obtained by the prior art is also unsatisfactory.
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
[0029] A low-power real-time binocular camera based on hardware acceleration, such as figure 1 and figure 2 Shown: including the first camera module 1, the second camera module 2, the first image acquisition module 3, the second image acquisition module 4, the first Bayer-to-grayscale module 5, the second Bayer-to-grayscale module 6, The first correction module 7, the second correction module 8, the BM algorithm module 9, the image output module 10, the camera control chip 11 and the terminal device 12;
[0030] The first camera module 1, the first image acquisition module 3, the first Bayer-to-grayscale module 5 and the first correction module 7 are electrically connected in sequence;
[0031] The second camera module 2, the second image acquisition module 4, the second Bayer-to-grayscale module 6 and the second correction module 8 are electrically connected in sequence;
[0032] The first correction module 7 and the second correction module 8 are connected to the BM algor...
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 belongs to the technical field of image acquisition and processing, and particularly relates to a hardware acceleration-based real-time binocular camera and use method. The hardware acceleration-based real-time binocular camera comprises a first camera module, a second camera module, a first image acquisition module, a second image acquisition module, a first Bayer-to-grayscale module, a second Bayer-to-grayscale module, a first correction module, a second correction module, a BM algorithm module, an image output module, a camera control chip and a terminal device. The hardware acceleration-based real-time binocular camera provided by the invention can process image data in real time and has the characteristics of small delay, low power consumption and the like; a depth map can be directly output to be provided to a PC or other equipment, the cost of subsequent development is reduced and the speed of subsequent development is improved; and when mismatching of the focal distance of the camera and distance between two lenses and other factors cause a result that the quality of left and right input pictures is not ideal, a relatively good depth map can also be obtained.
Description
technical field [0001] The invention belongs to the technical field of image acquisition and processing, and in particular relates to a real-time binocular camera based on hardware acceleration and a method for using it. Background technique [0002] An image depth map refers to the number of bits used to store each pixel and is also used to measure the color resolution of an image. With the development of science and technology, the previous monocular camera can no longer meet the requirements of new fields, such as the field of machine vision, the binocular camera came into being, using the principle of bionics, the synchronized images are obtained through the calibrated binocular camera, and then calculated to obtain The third-dimensional depth information of the two-dimensional image pixels. Specifically, there is an open source algorithm based on bm. First, the input left and right images are subjected to sobel calculation, and the data enters the front-end module thro...
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): G06T7/55
CPCG06T7/55
Inventor 焦健薛长宇王刚张立华
Owner 长春博立电子科技有限公司