Inverse perspective transformation method of motion change based on monocular camera
An inverse perspective transformation, monocular camera technology, applied in the field of inverse perspective transformation of motion changes, can solve problems such as distortion and bird's-eye view distortion, and achieve the effects of fast speed, fast convergence speed, and simple network structure
Pending Publication Date: 2020-10-02
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The invention provides an inverse perspective transformation method based on the movement change of a monocular camera, which can solve the problems of distortion and distortion in the bird's-eye view obtained by using a fixed inverse perspective transformation method on complex road surfaces.
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] The present invention is described in detail below in conjunction with accompanying drawing and specific embodiment:
[0050] like figure 1 As shown, an inverse perspective transformation method based on the motion change of the monocular camera includes the following steps:
[0051] (1) Initial detection: The monocular camera starts to work, first initially detects the first frame of image, and uses the method of combining deep neural network and image texture features to detect the initial vanishing point, initial dividing line and four initial corresponding points. stage, there are two main operations: the first is to detect the initial vanishing point v 0 The coordinates of and the initial dividing line l between the sky and the road surface 0 The slope of k 0 ;
[0052] The initial vanishing point v 0 The detection is detected by the combination of deep learning and image texture features, such as Figure 4 As shown, the image is 1080×1440 (1080 is the number...
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 inverse perspective transformation method for motion change based on a monocular camera, belongs to the field of computer vision, image processing and environmental perception of intelligent vehicles, and solves the problems of distortion and the like of an obtained aerial view caused by adopting a fixed inverse perspective transformation method for complex road surfaces. The method mainly comprises the steps of initial detection, inverse perspective transformation, parallel characteristic inspection and dynamic detection, wherein a processing target is a video stream or picture set shot by a monocular camera; matrix parameters used for inverse perspective transformation have dynamic changes, the method can adapt to uphill, downhill and bumpy pavements, the quality of the obtained aerial view is higher than that of inverse perspective transformation of fixed parameters, the method can adapt to the situation that the road surface is complex, and subsequent road information extraction is facilitated.
Description
technical field [0001] The invention belongs to the fields of computer vision, image processing and environment perception of intelligent vehicles, and in particular relates to an inverse perspective transformation method based on the motion change of a monocular camera. Background technique [0002] With the introduction of electrification, networking, intelligence and sharing, the development of automobiles is becoming more and more intelligent. The development of autonomous driving has received attention. The key technologies of autonomous driving are divided into positioning and navigation technology, environmental perception technology, planning and decision-making technology and automatic control technology. Environmental perception technology is to perceive the environment around the car, including road surfaces, static and dynamic objects. To perceive static objects, it is necessary to classify objects; to perceive dynamic objects, it is necessary to perform object ...
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): G06K9/00G06K9/46G06T3/00G06T7/13G06T7/246G06T5/00
CPCG06T7/13G06T7/246G06T2207/10004G06T2207/10016G06T2207/20084G06T2207/20081G06T2207/30168G06V20/40G06V20/56G06V10/44G06T3/04G06T5/70
Inventor 周冠李祥闫鹏飞王琪
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS