CN111505577A - Mobile vehicle positioning method based on visible light communication - Google Patents
Mobile vehicle positioning method based on visible light communication Download PDFInfo
- Publication number
- CN111505577A CN111505577A CN202010344463.5A CN202010344463A CN111505577A CN 111505577 A CN111505577 A CN 111505577A CN 202010344463 A CN202010344463 A CN 202010344463A CN 111505577 A CN111505577 A CN 111505577A
- Authority
- CN
- China
- Prior art keywords
- effective
- array
- image
- mobile vehicle
- array lamp
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004891 communication Methods 0.000 title claims abstract description 19
- 238000003384 imaging method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 6
- 235000015110 jellies Nutrition 0.000 claims description 5
- 239000008274 jelly Substances 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 7
- 238000011176 pooling Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000010339 dilation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/16—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
- H04B10/114—Indoor or close-range type systems
- H04B10/116—Visible light communication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Abstract
The invention discloses a method for positioning a mobile vehicle based on visible light communication.A sending end is a roadside square L ED array lamp, an information code for displaying a position is sent by a L ED array lamp, the information code is transmitted through a free space, a receiving end is a camera arranged on the mobile vehicle, and the camera is adopted for receiving.
Description
(I) technical field
The invention belongs to a mobile vehicle positioning method based on Visible light Communication in a Visible-L light-Communication (abbreviated as V L C) system.
(II) background of the invention
In recent years, light emitting diodes (L ED) have been increasingly used for screen display panels, traffic lights and road lighting, which have the characteristics of lower power consumption, higher temperature resistance and less heat generation than incandescent lamps, outdoor L ED array lamps are used not only for lighting and signs, but also for visible light communication.
The positioning technology based on visible light communication is taken as an emerging technology to attract attention of researchers, the positioning technology based on visible light communication adopts an L ED array lamp as a sending end and uses a camera for receiving, the positioning technology has the advantages of communication and illumination, low cost and high positioning precision, the visible light communication can be carried out based on a L ED array lamp on the roadside, the camera is placed on a mobile vehicle for receiving and positioning, however, when the mobile vehicle runs at a high speed, image information of L ED array lamp received by the camera can be interfered by other signal sources, and the fuzzy positioning precision of the mobile vehicle is influenced by the fuzzy positioning effect.
For the moving vehicle, the camera arranged on the moving vehicle is adopted to receive the position information codes sent by the roadside L ED array lamps, the effective L ED array lamps are obtained by adopting an image processing algorithm, and the position information codes of the effective L ED array lamps are identified by using a convolutional neural network aiming at the influence of a jelly effect.
Disclosure of the invention
The method for positioning the mobile vehicle based on visible light communication is simple in principle and low in cost, and can realize high-precision positioning of the mobile vehicle.
In order to achieve the above object, the method for positioning a moving vehicle based on visible light communication according to the present invention comprises the steps of:
step 2: through free space transmission, the receiving end is a camera arranged on a moving vehicle, and the camera is adopted for receiving;
step 3, at a receiving end, a received image comprises a plurality of L ED array lamps from far to near, and meanwhile, environmental noise also exists on the image, and an image preprocessing method is adopted to eliminate background noise in the image;
step 4, identifying the position information codes of the effective L ED array lamps by adopting a convolutional neural network for the effective L ED array lamps, and solving the problem of image blurring caused by the influence of a jelly effect generated in the high-speed running of a mobile vehicle;
and 5, calculating the distance between the mobile vehicle and the effective L ED array lamp based on a geometric distance measurement algorithm of pinhole imaging, and combining the identified coordinate information of the position information code sent by the effective L ED array lamp to realize high-precision positioning of the mobile vehicle.
(IV) description of the drawings
FIG. 1 is a schematic diagram of a visible light communication based mobile vehicle location method of the present invention;
FIG. 2 is a schematic diagram of the image pre-processing method of the present invention;
FIG. 3 is a flow chart of an efficient selection algorithm of the present invention;
FIG. 4 is a schematic diagram of the present invention using a convolutional neural network to identify a position information code;
FIG. 5 is a scene diagram of a geometric range finding algorithm based on pinhole imaging according to the present invention;
FIG. 6 is a flow chart of the geometric ranging algorithm based on pinhole imaging of the present invention;
FIG. 7 is a flow chart of the present invention for achieving high precision positioning of a moving vehicle;
the letters in fig. 4 represent the following meanings, respectively:
FIG. 4:
input image
Conv2D convolutional layer
Max Pooling maximum pooling layer
Flatten dimension reduction
FC full connection layer
Linear rectification function of Re L u
(V) detailed description of the preferred embodiments
The present invention will be described in detail below with reference to specific experimental examples and the accompanying drawings.
The method comprises the steps that a transmitting end is a square L ED array lamp on the roadside, an L ED array lamp transmits an information code for displaying the position of a L ED array lamp, a receiving end is a camera arranged above a moving vehicle and receives the image through free space transmission, an effective L ED array lamp is obtained through an image processing algorithm including an image preprocessing method and an effective selection algorithm for the image received by the camera, then the position information code of the effective L ED array lamp is identified, the distance between the moving vehicle and the effective L ED array lamp is calculated based on a geometric distance measurement algorithm of pinhole imaging, and finally the position information code of the identified effective L ED array lamp is combined to achieve high-precision positioning of the moving vehicle.
FIG. 2 is a schematic diagram of the image preprocessing method according to the present invention, in which a large amount of environmental noise exists in the image received by the camera, so that the received image is grayed by the image preprocessing method, then binarized to remove most of the environmental noise, then the binarized image is subjected to morphological opening and dilation to remove all of the environmental noise, and finally, the output is an image with only L ED array lamps left through contour extraction and polygon fitting.
Fig. 3 shows a flow chart of an effective selection algorithm of the present invention, since there are many matching L ED array lamps in the image after the image preprocessing method, an effective selection algorithm is proposed to obtain effective L ED array lamps, in order to obtain effective L ED array lamps, i.e. L ED array lamps which are closest to the moving vehicle and present a complete L ED array lamp outline on the received image, the effective selection algorithm is adopted, the outlines of the first 4L ED array lamps with the largest area are sorted by size and respectively denoted as a1, a2, a3, a4, and then it is determined whether the ratio of the length and width of a1 and a2 is between 0.8 and 1.2, if yes, a1 and a2 are effective L ED array lamps, and if not, a 58L 6 and a4 are selected as effective 632 ED array lamps.
Fig. 4 is a schematic diagram illustrating the principle of identifying position information codes using convolutional neural networks according to the present invention, in which the image tensor of the input L ED array lamp is (224, 224, 3), the tensor after passing through a convolutional layer is (74, 74, 16), then the tensor after passing through a Re L u function and pooling layer is (24, 24, 16), then the tensor after passing through a convolutional layer is (7, 7, 64), and after passing through a Re L u function and pooling layer, the tensor becomes (3, 3, 64), and finally the matrix with the output tensor size of (1, x) is flattened after passing through two fully connected layers, each of which passes through a Re L u function, wherein the numerical size of x depends on the number of position information codes.
The obtained image of the effective L ED array lamp is input into the convolutional neural network, image blurring caused by the influence of the jelly effect is eliminated, and the position information code of the effective L ED array lamp is identified.
Fig. 5 is a scene diagram of the geometric distance measurement algorithm based on pinhole imaging according to the present invention.
FIG. 6 is a flow chart of the geometric distance measurement algorithm based on pinhole imaging of the present invention, first, the world coordinate of the effective L ED array lamp center on the left side of the road is (X)l,Yl,Zl) The coordinate on the image is (x)l,yl) The world coordinate of the center of the road right effective L ED array lamp is (X)r,Yr,Zr) The coordinate on the image is (x)r,yr) (ii) a For subsequent calculation, the coordinate of the central pixel point of the collected image is (x)mid,ymid) Then, the distance between the camera and the effective L ED array lamp on the vehicle is D, then, since the heights of the L ED array lamps on the left and right sides are the same and only have a fixed distance difference in the Y-axis direction, the equation is L, and meanwhile, the focal length f of the monocular camera can be defined by the following formula:
Zl=Zr(1)
Xl=Xr(2)
L=|Yl-Yr| (3)
where | represents the symbol of taking the absolute value.
The calculation formula of the distance D can be obtained by combining the pinhole imaging principle with the triangle similarity principle:
wherein l is the physical distance of the central points of the left and right effective L ED array lamps on the collected image, and the calculation formula is as follows:
thus, the distance D can be calculated by combining the calculation formula (4) of the distance D between the vehicle and the effective L ED array lamp with the calculation formula (6) of the distance l.
Fig. 7 is a flow chart of the present invention for achieving high-precision positioning of a moving vehicle. As for the position information of the vehicle,first, the distance D calculated by a geometric distance measurement algorithm based on pinhole imaging and the position information code of the roadside effective L ED array lamp are input, when the world coordinate of the left side of the road effective L ED array lamp center is (X)l,Yl,Zl) The world coordinate of the center of the road right effective L ED array lamp is (X)r,Yr,Zr) For the X coordinate of the vehicle, it can be seen from the scene diagram in fig. 5 that:
X=Xl-D=Xr-D (7)
for the Y coordinate of the vehicle, this is obtained from equation (5):
and finally integrating the X and Y coordinates and outputting the world coordinates (X and Y) of the vehicle.
The implementation steps are as follows:
step 2: through free space transmission, the receiving end is a camera arranged on a moving vehicle, and the camera is adopted for receiving;
and 3, at a receiving end, a received image comprises a plurality of L ED array lamps from far to near, and environmental noise also exists on the image, an image preprocessing method is adopted, as shown in FIG. 2, the received image is subjected to graying, then binarization is carried out to eliminate most of the environmental noise, then the binary image is subjected to morphological opening and expansion operation to eliminate all the environmental noise, and finally, the obtained output is the image of only L ED array lamps.
And 4, obtaining effective L ED array lamps by using an effective selection algorithm after an image preprocessing method, sorting the contours of the first 4L ED array lamps with the largest area according to the size of the images of only L ED array lamps output by the graph in FIG. 2 as the input of the graph in FIG. 3 due to the existence of a plurality of matched L ED array lamps, and respectively marking the contours as a1, a2, a3 and a4, judging whether the length-width ratio range of the a1 to the a2 is between 0.8 and 1.2, if so, marking a1 and a2 as the effective L ED array lamps, and if not, selecting a3 and a4 as the effective L ED array lamps.
And 5, inputting the obtained image of the effective L ED array lamp into a convolutional neural network shown in the figure 4, wherein the tensor of the input L ED array lamp is (224, 224, 3), the tensor after passing through a convolutional layer is (74, 74, 16), then the tensor after passing through a Re L u function and a pooling layer is (24, 24, 16), then the tensor after passing through a convolutional layer is (7, 7, 64), the tensor after passing through a Re L u function and a pooling layer is changed into (3, 3, 64), and finally, flattening the matrix which passes through two full connection layers, passes through a Re L u function after each full connection layer, and outputs the tensor with the size of (1, x), wherein the numerical value of x depends on the number of position information codes.
Step 6, based on the geometric distance measurement algorithm flow chart of the small hole imaging shown in the figure 6, according to the world coordinate of the effective L ED array lamp center on the left side of the road as (X)l,Yl,Zl) The coordinate on the image is (x)l,yl) The world coordinate of the center of the road right effective L ED array lamp is (X)r,Yr,Zr) The coordinate on the image is (x)r,yr) (ii) a The coordinate of the central pixel point of the collected image is (x)mid,ymid) The distance D between the vehicle and the effective L ED array lamp is calculated by combining a pinhole imaging principle with a triangular similarity principle and a corresponding formula thereof, wherein the heights of the left and right L ED array lamps are the same, the difference between the left and right L ED array lamps is a fixed distance in the Y-axis direction and is recorded as L, the focal length of a monocular camera is f, the physical distance between the center points of the left and right effective L ED array lamps on an acquired image is l, and the distance D between the vehicle and the effective L ED array lamp is.
Step 7, as shown in FIG. 7, inputting the distance D calculated by geometric distance measurement algorithm based on pinhole imaging and the position information code of roadside effective L ED array lamp, the world coordinate of the center of the roadside effective L ED array lamp is (X)l,Yl,Zl) The world coordinate of the center of the road right effective L ED array lamp is (X)r,Yr,Zr) And the relation between the distance D and the position information code of the roadside effective L ED array lamp, and outputting the world coordinates (X, Y) of the vehicle to realize the high-precision positioning of the moving vehicle.
(VI) major technical advantages
The transmitting end of the invention is a roadside L ED array lamp, an information code for displaying the position is transmitted by a L ED array lamp, the position information of a moving vehicle is positioned by adopting a camera arranged on the moving vehicle and receiving by adopting the camera, for the moving vehicle, the position information code transmitted by the roadside L ED array lamp is received by adopting the camera arranged on the moving vehicle, an effective L ED array lamp is obtained by adopting an image preprocessing method and an effective selection algorithm, the position information code of the effective L ED array lamp is identified by using a convolutional neural network aiming at the influence of a jelly effect, the distance between the moving vehicle and the effective L ED array lamp is calculated by adopting a geometric distance measurement algorithm based on pinhole imaging, and the high-precision positioning of the moving vehicle is realized by combining the coordinate information of the identified effective L ED array lamp position information code.
The method for positioning the mobile vehicle based on the visible light communication has the advantages of simple principle, low cost, capability of realizing high-precision positioning of the mobile vehicle and practical value.
Claims (5)
1. The method for positioning the moving vehicle based on the visible light communication is characterized by comprising the following steps:
the transmitting end is a square L ED array lamp on the roadside, and the L ED array lamp transmits an information code for displaying the position;
through free space transmission, the receiving end is a camera arranged on a moving vehicle, and the camera is adopted for receiving;
obtaining an effective L ED array lamp by adopting an image processing algorithm comprising an image preprocessing method and an effective selection algorithm;
identifying the position information code of the effective L ED array lamp by adopting a convolutional neural network;
and the high-precision positioning of the moving vehicle is realized by adopting a geometric distance measurement algorithm based on pinhole imaging and combining the identified position information code of the effective L ED array lamp.
2. The visible light communication-based mobile vehicle positioning method as claimed in claim 1, wherein the image preprocessing method comprises image gray scale value, binarization, image morphology processing, polygon fitting algorithm and target contour searching, and background noise in the image is eliminated by adopting the image preprocessing method.
3. The visible light communication-based mobile vehicle positioning method as claimed in claim 1, wherein the effective selection algorithm is to select L ED array lamp with the largest area match as the effective L ED array lamp in case of L ED array lamp being complete in the image after the image preprocessing method.
4. The visible-light-communication-based mobile vehicle positioning method of claim 1, wherein the convolutional neural network is adopted to identify the position information codes of the effective L ED array lamps, so that the influence of the jelly effect generated during the high-speed running of the mobile vehicle is eliminated, and the accuracy of identifying the position information codes of the effective L ED array lamps is improved.
5. The visible light communication-based mobile vehicle positioning method as claimed in claim 1, wherein a geometric distance measurement algorithm based on pinhole imaging is adopted to calculate the distance between the mobile vehicle and the effective L ED array lamps, and the identified coordinate information of the position information code of the effective L ED array lamps is combined to realize high-precision positioning of the mobile vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010344463.5A CN111505577A (en) | 2020-04-27 | 2020-04-27 | Mobile vehicle positioning method based on visible light communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010344463.5A CN111505577A (en) | 2020-04-27 | 2020-04-27 | Mobile vehicle positioning method based on visible light communication |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111505577A true CN111505577A (en) | 2020-08-07 |
Family
ID=71871433
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010344463.5A Pending CN111505577A (en) | 2020-04-27 | 2020-04-27 | Mobile vehicle positioning method based on visible light communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111505577A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112034423A (en) * | 2020-09-08 | 2020-12-04 | 湖南大学 | High-precision mobile vehicle positioning method based on LED visible light communication |
CN113132006A (en) * | 2021-04-23 | 2021-07-16 | 湖南大学 | High-precision visible light positioning method for moving vehicle based on image sensor |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106524995A (en) * | 2016-11-02 | 2017-03-22 | 长沙神弓信息科技有限公司 | Positioning method for detecting spatial distances of target objects on basis of visible-light images in real time |
CN106650641A (en) * | 2016-12-05 | 2017-05-10 | 北京文安智能技术股份有限公司 | Traffic light positioning and identification method, device and system |
CN107395279A (en) * | 2017-08-16 | 2017-11-24 | 华南理工大学 | A kind of monocular localization method and its system based on visible light communication |
CN108681539A (en) * | 2018-05-07 | 2018-10-19 | 内蒙古工业大学 | A kind of illiteracy Chinese nerve interpretation method based on convolutional neural networks |
CN109861752A (en) * | 2019-01-07 | 2019-06-07 | 华南理工大学 | A kind of underground garage path guiding system and method based on visible light-seeking |
US20190258885A1 (en) * | 2018-02-19 | 2019-08-22 | Avigilon Corporation | Method and system for object classification using visible and invisible light images |
CN110228413A (en) * | 2019-06-10 | 2019-09-13 | 吉林大学 | Oversize vehicle avoids pedestrian from being involved in the safety pre-warning system under vehicle when turning |
CN110554356A (en) * | 2019-08-09 | 2019-12-10 | 清华大学 | Equipment positioning method and system in visible light communication |
WO2020037492A1 (en) * | 2018-08-21 | 2020-02-27 | SZ DJI Technology Co., Ltd. | Distance measuring method and device |
-
2020
- 2020-04-27 CN CN202010344463.5A patent/CN111505577A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106524995A (en) * | 2016-11-02 | 2017-03-22 | 长沙神弓信息科技有限公司 | Positioning method for detecting spatial distances of target objects on basis of visible-light images in real time |
CN106650641A (en) * | 2016-12-05 | 2017-05-10 | 北京文安智能技术股份有限公司 | Traffic light positioning and identification method, device and system |
CN107395279A (en) * | 2017-08-16 | 2017-11-24 | 华南理工大学 | A kind of monocular localization method and its system based on visible light communication |
US20190258885A1 (en) * | 2018-02-19 | 2019-08-22 | Avigilon Corporation | Method and system for object classification using visible and invisible light images |
CN108681539A (en) * | 2018-05-07 | 2018-10-19 | 内蒙古工业大学 | A kind of illiteracy Chinese nerve interpretation method based on convolutional neural networks |
WO2020037492A1 (en) * | 2018-08-21 | 2020-02-27 | SZ DJI Technology Co., Ltd. | Distance measuring method and device |
CN109861752A (en) * | 2019-01-07 | 2019-06-07 | 华南理工大学 | A kind of underground garage path guiding system and method based on visible light-seeking |
CN110228413A (en) * | 2019-06-10 | 2019-09-13 | 吉林大学 | Oversize vehicle avoids pedestrian from being involved in the safety pre-warning system under vehicle when turning |
CN110554356A (en) * | 2019-08-09 | 2019-12-10 | 清华大学 | Equipment positioning method and system in visible light communication |
Non-Patent Citations (1)
Title |
---|
侯文佐等: "基于LED光源的室内高精度成像定位新方法", 《激光与光电子学进展》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112034423A (en) * | 2020-09-08 | 2020-12-04 | 湖南大学 | High-precision mobile vehicle positioning method based on LED visible light communication |
CN112034423B (en) * | 2020-09-08 | 2023-12-26 | 湖南大学 | High-precision mobile vehicle positioning method based on LED visible light communication |
CN113132006A (en) * | 2021-04-23 | 2021-07-16 | 湖南大学 | High-precision visible light positioning method for moving vehicle based on image sensor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110570429B (en) | Lightweight real-time semantic segmentation method based on three-dimensional point cloud | |
KR101873202B1 (en) | The one shot camera for artificial intelligence fuction by using neuromorphic chip | |
US20200285866A1 (en) | Class labeling system for autonomous driving | |
CN109389046B (en) | All-weather object identification and lane line detection method for automatic driving | |
CN111914797B (en) | Traffic sign identification method based on multi-scale lightweight convolutional neural network | |
CN111505577A (en) | Mobile vehicle positioning method based on visible light communication | |
CN112949633B (en) | Improved YOLOv 3-based infrared target detection method | |
TWI401473B (en) | Night time pedestrian detection system and method | |
CN111190141B (en) | Method for determining light source emission sequence based on image superposition in visible light indoor positioning | |
CN114495029B (en) | Traffic target detection method and system based on improved YOLOv4 | |
CN108288289B (en) | LED visual detection method and system for visible light positioning | |
CN101154267A (en) | Method for zone location and type judgment of two-dimensional bar code | |
CN113269040A (en) | Driving environment sensing method combining image recognition and laser radar point cloud segmentation | |
CN110674672B (en) | Multi-scene people counting method based on tof camera | |
CN111008979A (en) | Robust night image semantic segmentation method | |
CN116486368A (en) | Multi-mode fusion three-dimensional target robust detection method based on automatic driving scene | |
CN115294483A (en) | Small target identification method and system for complex scene of power transmission line | |
Zhang et al. | Gc-net: Gridding and clustering for traffic object detection with roadside lidar | |
CN115661777A (en) | Semantic-combined foggy road target detection algorithm | |
CN112101108A (en) | Left-right-to-pass sign identification method based on pole position characteristics of graph | |
CN111597913A (en) | Lane line picture detection and segmentation method based on semantic segmentation model | |
CN112989985B (en) | Urban built-up area extraction method integrating night light data and Landsat8OLI images | |
CN116758045B (en) | Surface defect detection method and system for semiconductor light-emitting diode | |
CN112329666A (en) | Face recognition method and device, electronic equipment and storage medium | |
CN116071725B (en) | Pavement marking recognition method and system |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200807 |
|
WD01 | Invention patent application deemed withdrawn after publication |