CN108955699B - Vehicle-mounted navigation system - Google Patents

Vehicle-mounted navigation system Download PDF

Info

Publication number
CN108955699B
CN108955699B CN201810807236.4A CN201810807236A CN108955699B CN 108955699 B CN108955699 B CN 108955699B CN 201810807236 A CN201810807236 A CN 201810807236A CN 108955699 B CN108955699 B CN 108955699B
Authority
CN
China
Prior art keywords
noise
image
module
video image
denoising
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810807236.4A
Other languages
Chinese (zh)
Other versions
CN108955699A (en
Inventor
许晓山
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Anzewi Technology Co ltd
Original Assignee
Shenzhen Anzewi Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Anzewi Technology Co ltd filed Critical Shenzhen Anzewi Technology Co ltd
Priority to CN201810807236.4A priority Critical patent/CN108955699B/en
Publication of CN108955699A publication Critical patent/CN108955699A/en
Application granted granted Critical
Publication of CN108955699B publication Critical patent/CN108955699B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network

Abstract

The invention provides a vehicle-mounted navigation system which comprises a camera module, an image processing module, a positioning module, a path input module and a guiding module, wherein the camera module is used for acquiring a road video image of a vehicle, the image processing module is used for processing the road video image, the positioning module is used for acquiring the position information of the vehicle, the path input module is used for inputting a navigation path, and the guiding module is used for guiding the vehicle according to the processed road video image, the position information of the vehicle and the navigation path. The invention has the beneficial effects that: the vehicle-mounted navigation system is provided, and accurate guiding of the vehicle is achieved through accurate acquisition of the road video image and the position.

Description

Vehicle-mounted navigation system
Technical Field
The invention relates to the technical field of navigation, in particular to a vehicle-mounted navigation system.
Background
With the popularization of vehicles, vehicle navigation systems are increasingly popularized. The existing navigation system is not accurate enough to acquire the road image, so that the navigation precision is poor.
Disclosure of Invention
In view of the above problems, the present invention is directed to a vehicle navigation system.
The purpose of the invention is realized by adopting the following technical scheme:
the vehicle-mounted navigation system comprises a camera module, an image processing module, a positioning module, a path input module and a guiding module, wherein the camera module is used for acquiring a road video image of a vehicle, the image processing module is used for processing the road video image, the positioning module is used for acquiring the position information of the vehicle, the path input module is used for inputting a navigation path, and the guiding module is used for guiding the vehicle according to the processed road video image, the position information of the vehicle and the navigation path; the image processing module comprises a model establishing module, a noise removing module and a denoising evaluation module, wherein the model establishing module is used for establishing a video image noise model, the noise removing module is used for removing the noise of the video image according to the noise model, and the denoising evaluation module is used for evaluating the denoising effect of the noise removing module.
The invention has the beneficial effects that: the vehicle-mounted navigation system is provided, and accurate guiding of the vehicle is achieved through accurate acquisition of the road video image and the position.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic structural view of the present invention;
reference numerals:
the device comprises a camera module 1, an image processing module 2, a positioning module 3, a path input module 4 and a guide module 5.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the vehicle-mounted navigation system of the present embodiment includes a camera module 1, an image processing module 2, a positioning module 3, a route input module 4, and a guidance module 5, where the camera module 1 is configured to acquire a road video image of a vehicle, the image processing module 2 is configured to process the road video image, the positioning module 3 is configured to acquire position information of the vehicle, the route input module 4 is configured to input a navigation route, and the guidance module 5 is configured to guide the vehicle according to the processed road video image, the position information of the vehicle, and the navigation route; the image processing module 2 comprises a model establishing module, a noise removing module and a denoising evaluating module, wherein the model establishing module is used for establishing a video image noise model, the noise removing module is used for removing the video image noise according to the noise model, and the denoising evaluating module is used for evaluating the denoising effect of the noise removing module.
The embodiment provides a vehicle-mounted navigation system, which realizes accurate guidance of a vehicle through accurate acquisition of road video images and positions.
Preferably, the model establishing module is configured to establish a video image noise model, specifically:
taking each frame image in the video sequence as an image block, and expressing a video image noise model as follows:
Figure 100002_DEST_PATH_IMAGE002
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE003
representing a matrix of clean images free of noise,
Figure 100002_DEST_PATH_IMAGE004
,
Figure DEST_PATH_IMAGE005
is shown as
Figure 100002_DEST_PATH_IMAGE006
The number of clean image blocks is one,
Figure DEST_PATH_IMAGE007
indicates the number of image frames,
Figure 100002_DEST_PATH_IMAGE008
，
Figure DEST_PATH_IMAGE009
which represents the impulse noise matrix, is,
Figure 100002_DEST_PATH_IMAGE010
，
Figure DEST_PATH_IMAGE011
to represent
Figure 447842DEST_PATH_IMAGE005
The corresponding impulse noise is generated by the corresponding impulse noise,
Figure 20774DEST_PATH_IMAGE008
，
Figure 100002_DEST_PATH_IMAGE012
a matrix of gaussian noise is represented which is,
Figure DEST_PATH_IMAGE013
，
Figure 100002_DEST_PATH_IMAGE014
to represent
Figure 3774DEST_PATH_IMAGE005
The corresponding gaussian noise is generated by the corresponding gaussian noise,
Figure 352978DEST_PATH_IMAGE008
，
Figure DEST_PATH_IMAGE015
is a matrix of images that contains noise,
Figure 100002_DEST_PATH_IMAGE016
，
Figure DEST_PATH_IMAGE017
represent
Figure 291984DEST_PATH_IMAGE005
The corresponding image containing noise is then displayed on the display,
Figure 848867DEST_PATH_IMAGE008
。
the existing algorithms for removing impulse noise are all performed on a single image, a video is an ordered sequence of a plurality of images, and the time redundancy of a video signal is ignored, so that the efficiency of removing the impulse noise in the video by the existing algorithms is low.
Preferably, the noise removing module comprises a first denoising submodule and a second denoising submodule, the first denoising submodule is used for removing gaussian noise of the video image, and the second denoising submodule is used for processing the video image after the gaussian noise is removed and removing impulse noise of the video image;
the first denoising submodule is used for removing gaussian noise of a video image, and specifically comprises: removing Gaussian noise from each frame of image to obtain a video image with the Gaussian noise removed:
Figure DEST_PATH_IMAGE019
in the formula (I), the compound is shown in the specification,
Figure 100002_DEST_PATH_IMAGE020
for an image matrix containing only impulse noise,
Figure DEST_PATH_IMAGE021
，
Figure 100002_DEST_PATH_IMAGE022
to represent
Figure 942332DEST_PATH_IMAGE005
The corresponding image contains only impulse noise,
Figure 797024DEST_PATH_IMAGE008
；
the second denoising submodule is used for processing the video image without the Gaussian noise and removing the impulse noise of the video image, and specifically comprises:
for containing
Figure 997061DEST_PATH_IMAGE007
Video sequence of frames, divided into
Figure 396950DEST_PATH_IMAGE007
Groups, each of which is arranged in front of and behind each frame of image with the image as the center
Figure DEST_PATH_IMAGE023
Frame image is used as similar image block of said image, said similar image block is arranged in order to form matrix, the rank of said matrix is minimized, and a processing result of said image is obtained, because every frame image can be formedProcessing for 2n +1 times, and performing simple weighted average on the results of the 2n +1 times to obtain the result of the image after pulse noise is removed;
obtaining the result of all frame images after removing the impulse noise to obtain the video image after removing the impulse noise
Figure 100002_DEST_PATH_IMAGE024
，
Figure DEST_PATH_IMAGE025
,
Figure 100002_DEST_PATH_IMAGE026
Is shown as
Figure 308536DEST_PATH_IMAGE006
The image after the impulse noise is removed is displayed,
Figure 701340DEST_PATH_IMAGE007
indicates the number of image frames,
Figure 755884DEST_PATH_IMAGE008
。
due to the time pi redundancy of the video, the structures of adjacent images are similar, and if a matrix is formed by the noiseless video images, the matrix has low rank. And the matrix formed by the video images with noise is a degraded matrix with polluted partial elements of the low-rank matrix, and the removal of the video noise is to recover the low-rank matrix from the degraded matrix. In the preferred embodiment, for each frame of image, the video image with the impulse noise removed is obtained by performing simple weighted average on the rank of the minimized matrix and the processing result, and the video image with the impulse noise removed is obtained by processing all the frame images.
Preferably, the denoising evaluation module is configured to evaluate a denoising effect of the noise removal module, and specifically includes:
the evaluation factor was defined using the following formula:
Figure 100002_DEST_PATH_IMAGE028
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE029
which represents the evaluation factor(s) of the evaluation,
Figure 100002_DEST_PATH_IMAGE030
respectively representing images from which salt and pepper noise is removed
Figure 221281DEST_PATH_IMAGE026
And a clean image free of noise
Figure 994065DEST_PATH_IMAGE005
The average value of the luminance of (a),
Figure DEST_PATH_IMAGE031
respectively representing images with salt and pepper noise removed
Figure 659402DEST_PATH_IMAGE026
And a clean image free of noise
Figure 506135DEST_PATH_IMAGE005
The luminance variance of (2) represents an image from which salt and pepper noise is removed
Figure 575722DEST_PATH_IMAGE026
The standard deviation of the luminance of (a),
Figure 100002_DEST_PATH_IMAGE032
representing clean images free of noise
Figure 993059DEST_PATH_IMAGE005
The standard deviation of the luminance of (a),
Figure DEST_PATH_IMAGE033
representing images with salt and pepper noise removed
Figure 806295DEST_PATH_IMAGE026
And do notClean image containing noise
Figure 960064DEST_PATH_IMAGE005
Peak signal-to-noise ratio of (d); the larger the evaluation factor is, the better the denoising effect of the image denoising module is.
The subjective evaluation mode is to use human eyes to perceive the visual effect of the algorithm processing result, and subjectively measure whether the algorithm achieves the expectation, whether the noise is removed and whether the fuzzy is caused, and the like. The subjective evaluation is closely related to evaluators, and evaluation conclusions obtained by different observers are possibly different. The preferred embodiment evaluates the denoising effect by defining evaluation factors, fully considers the peak signal-to-noise ratio of the denoising image and the structural similarity of the denoising image and the original image, realizes accurate evaluation of the denoising effect, and overcomes the evaluation difference caused by different evaluators in subjective evaluation.
From the above description of embodiments, it is clear for a person skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, a processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (3)

1. The vehicle-mounted navigation system is characterized by comprising a camera module, an image processing module, a positioning module, a path input module and a guiding module, wherein the camera module is used for acquiring a road video image of a vehicle, the image processing module is used for processing the road video image, the positioning module is used for acquiring the position information of the vehicle, the path input module is used for inputting a navigation path, and the guiding module is used for guiding the vehicle according to the processed road video image, the position information of the vehicle and the navigation path; the image processing module comprises a model establishing module, a noise removing module and a denoising evaluation module, wherein the model establishing module is used for establishing a video image noise model, the noise removing module is used for removing the noise of a video image according to the noise model, and the denoising evaluation module is used for evaluating the denoising effect of the noise removing module;
the model establishing module is used for establishing a video image noise model, and specifically comprises the following steps:
taking each frame image in the video sequence as an image block, and expressing a video image noise model as follows:
Figure DEST_PATH_IMAGE002
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE004
representing a matrix of clean images free of noise,
Figure DEST_PATH_IMAGE006
,
Figure DEST_PATH_IMAGE008
is shown as
Figure DEST_PATH_IMAGE010
The number of clean image blocks is one,
Figure DEST_PATH_IMAGE012
indicates the number of image frames,
Figure DEST_PATH_IMAGE014
，
Figure DEST_PATH_IMAGE016
a matrix of impulse noise is represented which is,
Figure DEST_PATH_IMAGE018
，
Figure DEST_PATH_IMAGE020
to represent
Figure 496563DEST_PATH_IMAGE008
The corresponding impulse noise is generated by the corresponding impulse noise,
Figure 210441DEST_PATH_IMAGE014
，
Figure DEST_PATH_IMAGE022
a matrix of gaussian noise is represented which is,
Figure DEST_PATH_IMAGE024
，
Figure DEST_PATH_IMAGE026
to represent
Figure 206823DEST_PATH_IMAGE008
The corresponding gaussian noise is generated by the corresponding gaussian noise,
Figure 523403DEST_PATH_IMAGE014
，
Figure DEST_PATH_IMAGE028
is a matrix of images that contains noise,
Figure DEST_PATH_IMAGE030
，
Figure DEST_PATH_IMAGE032
to represent
Figure 167137DEST_PATH_IMAGE008
The corresponding image containing noise is then displayed on the display,
Figure 910971DEST_PATH_IMAGE014
；
the noise removing module comprises a first denoising submodule and a second denoising submodule, the first denoising submodule is used for removing Gaussian noise of the video image, and the second denoising submodule is used for processing the video image after the Gaussian noise is removed and removing impulse noise of the video image;
the first denoising submodule is used for removing Gaussian noise of a video image, and specifically comprises: removing Gaussian noise from each frame of image to obtain a video image with the Gaussian noise removed:
Figure DEST_PATH_IMAGE034
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE036
for an image matrix containing only impulse noise,
Figure DEST_PATH_IMAGE038
，
Figure DEST_PATH_IMAGE040
to represent
Figure 208964DEST_PATH_IMAGE008
The corresponding image contains only impulse noise,
Figure 79968DEST_PATH_IMAGE014
。
2. the vehicle-mounted navigation system of claim 1, wherein the second denoising submodule is configured to process the video image with gaussian noise removed, and remove impulse noise of the video image, and specifically includes:
for containing
Figure 545584DEST_PATH_IMAGE012
Video sequence of frames, divided into
Figure 696205DEST_PATH_IMAGE012
Groups, each of which is arranged in front of and behind each frame of image with the image as the center
Figure DEST_PATH_IMAGE042
The frame image is used as a similar image block of the image, the similar image blocks are sequentially arranged to form a matrix, the rank of the matrix is minimized, a processing result of the image is obtained, and because each frame of image can be processed for 2n +1 times, the results of 2n +1 times are simply weighted and averaged to be used as the result of the image after pulse noise is removed;
obtaining the result of all frame images after removing the impulse noise to obtain the video image after removing the impulse noise
Figure DEST_PATH_IMAGE044
，
Figure DEST_PATH_IMAGE046
,
Figure DEST_PATH_IMAGE048
Is shown as
Figure 463917DEST_PATH_IMAGE010
An image from which impulse noise is removed,
Figure 873032DEST_PATH_IMAGE012
indicates the number of image frames,
Figure 927576DEST_PATH_IMAGE014
。
3. the vehicle-mounted navigation system of claim 2, wherein the denoising evaluation module is configured to evaluate a denoising effect of the noise removal module, and specifically:
the evaluation factor was defined using the following formula:
Figure DEST_PATH_IMAGE050
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE052
which represents the evaluation factor(s) of the evaluation,
Figure DEST_PATH_IMAGE054
respectively representing images with salt and pepper noise removed
Figure 763945DEST_PATH_IMAGE048
And a clean image free of noise
Figure 536729DEST_PATH_IMAGE008
The average value of the luminance of (a),
Figure DEST_PATH_IMAGE056
respectively representing images from which salt and pepper noise is removed
Figure 175302DEST_PATH_IMAGE048
And a clean image free of noise
Figure 225297DEST_PATH_IMAGE008
The variance of the luminance of (a) is,
Figure DEST_PATH_IMAGE058
representing images after salt and pepper noise removal
Figure 278573DEST_PATH_IMAGE048
The standard deviation of the luminance of (a),
Figure DEST_PATH_IMAGE060
representing clean images free of noise
Figure 102434DEST_PATH_IMAGE008
The standard deviation of the luminance of (a),
Figure DEST_PATH_IMAGE062
representing images with salt and pepper noise removed
Figure 305883DEST_PATH_IMAGE048
And a clean image free of noise
Figure 600598DEST_PATH_IMAGE008
Peak signal-to-noise ratio of (d); the larger the evaluation factor is, the better the denoising effect of the image denoising module is.
CN201810807236.4A 2018-07-21 2018-07-21 Vehicle-mounted navigation system Active CN108955699B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810807236.4A CN108955699B (en) 2018-07-21 2018-07-21 Vehicle-mounted navigation system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810807236.4A CN108955699B (en) 2018-07-21 2018-07-21 Vehicle-mounted navigation system

Publications (2)

Publication Number Publication Date
CN108955699A CN108955699A (en) 2018-12-07
CN108955699B true CN108955699B (en) 2022-05-27

Family

ID=64497630

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810807236.4A Active CN108955699B (en) 2018-07-21 2018-07-21 Vehicle-mounted navigation system

Country Status (1)

Country Link
CN (1) CN108955699B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105526946A (en) * 2015-12-07 2016-04-27 清华大学苏州汽车研究院（吴江） Vehicle navigation system for road scene and driving guide fusion display
CN107123094A (en) * 2017-03-23 2017-09-01 四川精目科技有限公司 A kind of mixing Poisson, the video denoising method of gaussian sum impulsive noise
CN107895503A (en) * 2017-11-07 2018-04-10 钟永松 A kind of unattended parking farm monitoring system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107861510A (en) * 2017-11-01 2018-03-30 龚土婷 A kind of intelligent vehicle control loop
CN108253972A (en) * 2018-01-11 2018-07-06 深圳市晟达机械设计有限公司 A kind of high onboard navigation system of navigation accuracy

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105526946A (en) * 2015-12-07 2016-04-27 清华大学苏州汽车研究院（吴江） Vehicle navigation system for road scene and driving guide fusion display
CN107123094A (en) * 2017-03-23 2017-09-01 四川精目科技有限公司 A kind of mixing Poisson, the video denoising method of gaussian sum impulsive noise
CN107895503A (en) * 2017-11-07 2018-04-10 钟永松 A kind of unattended parking farm monitoring system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于低秩分解和形态成分分析的WMSN视频去噪算法研究;朱艳丽;《中国优秀硕士论文全文数据库信息科技辑》;20170215;第I138-4074页 *
应用残差总变分及低秩表示的视频去噪算法;张智勇等;《信号处理》;20160531;第558-565页 *

Also Published As

Publication number Publication date
CN108955699A (en) 2018-12-07

Similar Documents

Publication Publication Date Title
CN109064428B (en) Image denoising processing method, terminal device and computer readable storage medium
CN111275626B (en) Video deblurring method, device and equipment based on ambiguity
EP2568438B1 (en) Image defogging method and system
CN109741388B (en) Method and apparatus for generating a binocular depth estimation model
CN108805840A (en) Method, apparatus, terminal and the computer readable storage medium of image denoising
CN103369209A (en) Video noise reduction device and video noise reduction method
CN108986197B (en) 3D skeleton line construction method and device
CN110136054B (en) Image processing method and device
CN110827210B (en) Underwater image sharpening method and system based on color curve decomposition
CN108257112B (en) Method and device for filtering light spots
CN112785572B (en) Image quality evaluation method, apparatus and computer readable storage medium
CN107341787A (en) Method, apparatus, server and the automobile that monocular panorama is parked
CN114119383B (en) Underwater image restoration method based on multi-feature fusion
CN108955699B (en) Vehicle-mounted navigation system
CN104036472A (en) Method and device for enhancing quality of 3D image
JP2024041895A (en) Modular image interpolation method
CN110378860A (en) Method, apparatus, computer equipment and the storage medium of restored video
CN112489103B (en) High-resolution depth map acquisition method and system
CN111222446B (en) Face recognition method, face recognition device and mobile terminal
JP2010506482A (en) Method and filter for parallax recovery of video stream
CN117173232A (en) Depth image acquisition method, device and equipment
CN110349108B (en) Method, apparatus, electronic device, and storage medium for processing image
CN111743524A (en) Information processing method, terminal and computer readable storage medium
CN106897975B (en) Image denoising method for hypercube particle calculation
CN113436107B (en) Image enhancement method, intelligent device and computer storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20220507

Address after: 518000 room 702-704, 7 / F, Chuangfeng center, No. 25, east ring 1st Road, Yousong community, Longhua street, Longhua District, Shenzhen, Guangdong

Applicant after: Shenzhen anzewi Technology Co.,Ltd.

Address before: 510000 No.8 Xingfu Li, fangcunshan village, Liwan District, Guangzhou City, Guangdong Province

Applicant before: Xu Xiaoshan

GR01 Patent grant
GR01 Patent grant