CN115489514A - Method and system for improving parking space recognition rate and parking capacity in dark light environment - Google Patents
Method and system for improving parking space recognition rate and parking capacity in dark light environment Download PDFInfo
- Publication number
- CN115489514A CN115489514A CN202210901651.2A CN202210901651A CN115489514A CN 115489514 A CN115489514 A CN 115489514A CN 202210901651 A CN202210901651 A CN 202210901651A CN 115489514 A CN115489514 A CN 115489514A
- Authority
- CN
- China
- Prior art keywords
- parking
- light
- parking space
- vehicle
- brightness
- 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 35
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000005286 illumination Methods 0.000 claims abstract description 15
- 230000009471 action Effects 0.000 claims abstract description 6
- 239000013589 supplement Substances 0.000 claims description 38
- 230000001502 supplementing effect Effects 0.000 claims description 20
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 17
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000003287 optical effect Effects 0.000 abstract 1
- 230000001360 synchronised effect Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 238000010191 image analysis Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/20—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/22—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle
- B60R1/23—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view
- B60R1/27—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view providing all-round vision, e.g. using omnidirectional cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a system for improving parking space recognition rate and parking capacity in a dark light environment. Earlier through optical line sensors, look around synchronous real-time collection vehicle of camera luminance and image around, and then judge whether activate the light filling lamp, the image of looking around the camera collection simultaneously carries out the analysis and forms the birds-eye view panorama, obtain the coordinate information of target parking stall according to the birds-eye view panorama again, and carry out luminance detection to its region of locating, judge whether the target parking stall is in the dim light region, if, then compensate the angle of illumination intensity and adjustment light filling lamp to the target parking stall through the light filling lamp, under guaranteeing that the target parking stall is in optimum luminance environment all the time, the parking stall spatial information who gathers according to the coordinate information of target parking stall and ultrasonic radar at last fuses, accomplish the action of parking. The invention can effectively improve the recognition accuracy and the recognition success rate of the automatic parking system to the parking space in the dark environment, and brings better parking experience to customers.
Description
Technical Field
The invention relates to the technical field of automatic parking of automobiles, in particular to a method and a system for improving the parking space recognition rate and the parking capacity in a dim light environment.
Background
Automatic parking is one of automatic driving technologies under low-speed working conditions of automobiles, and the requirements and the applications tend to be wide gradually. Under the current technical state, the automatic parking system can meet the parking requirements of most scenes, the vision perception part of the automatic parking system is composed of four all-round cameras, the requirement of the cameras on ambient light is high, the cameras with certain illumination cannot perceive the parking space line, the parking space recognition success rate is further influenced, and a large number of vision parking spaces cannot be released. Therefore, for indoor scenes such as underground parking lots, the existing automatic system has poor visual parking space identification precision, large identification error and even can not effectively identify visual parking spaces in the dark light environment of the parking lots, the use scenes of automatic parking are greatly limited, and user experience is influenced.
Disclosure of Invention
The method and the system for improving the parking space recognition rate and the parking capacity in the dim light environment can effectively improve the recognition accuracy and the recognition success rate of the automatic parking system for the parking space in the dim light environment, lay a good foundation for planning the parking path in the subsequent parking process, and bring better parking experience to customers.
The technical scheme of the invention is as follows:
a method for improving parking space recognition rate and parking capacity in a dark light environment comprises the following specific steps:
s1, after the automatic parking function of the vehicle is started, monitoring the ambient light brightness around the vehicle in real time through a light sensor, and acquiring images around the vehicle in real time through a panoramic camera;
s2, the automatic parking controller judges whether to start a light supplement lamp according to the collected ambient light brightness, and simultaneously processes the collected image to obtain a bird' S-eye view panoramic image;
s3, analyzing and calculating the aerial view panoramic image by the automatic parking controller to obtain coordinate information of all parking places in the image, and selecting the parking place closest to the position of the vehicle as a target parking place;
s4, forming a detection area on the aerial view panoramic image according to the coordinate information of the target parking space, and detecting the brightness of the detection area through Opencv;
s5, if the brightness does not accord with the set detection standard, judging that the target parking space is in a dark light area, and controlling a light supplement lamp to ensure that the target parking space is always in the set target illumination intensity range; otherwise, the target parking space is judged not to be in a dark light area, and the light supplement lamp is not required to be controlled;
s6, monitoring spatial information corresponding to the target parking space in real time through an ultrasonic radar, fusing the spatial information and coordinate information of the target parking space through an automatic parking controller, and judging and outputting an effective parking space according to confidence;
s7, the automatic parking controller plans a parking path according to the effective parking space and controls the vehicle to finish automatic parking in the effective parking space according to the parking path.
The light sensor and the all-round-looking camera synchronously acquire the light environment and images around the vehicle in real time, and when the brightness of the environment light is lower than a certain brightness, the light supplement lamp is activated to supplement light in real time, so that the images acquired by the all-round-looking camera are clearer; and then analyzing the image collected by the panoramic camera to form a bird's-eye view panoramic image, obtaining coordinate information of the target parking space according to the bird's-eye view panoramic image, detecting the brightness of the area where the target parking space is located, judging whether the target parking space is in a dark light area, if so, compensating illumination intensity of the target parking space and adjusting the illumination angle of the light supplement lamp through the light supplement lamp to ensure that the target parking space is always in the most suitable brightness environment, so that the recognition accuracy and the recognition success rate of the target parking space under the dark light environment are realized, and finally, the coordinate information of the target parking space is fused with the parking space information collected by the ultrasonic radar to complete the parking action.
Further, in step S2, if the ambient light brightness is less than the set brightness threshold and the duration is greater than the set duration threshold, turning on a light supplement lamp to illuminate the dim light area; otherwise, the light supplement lamp is not started.
The control of the light supplementing lamp and the control of the all-round looking camera are independent, whether the light supplementing lamp is turned on or not does not affect the real-time image acquisition of the all-round looking camera, and the light supplementing lamp is turned on when the light supplementing lamp is lower than the threshold value, so that the image acquisition definition of the all-round looking camera in a dark light environment is improved.
Further, the brightness threshold is 20Lux, and the duration threshold is 10 seconds. The two threshold conditions can be set according to actual conditions, and are not limited herein, and can be changed according to actual needs.
Further, in step S2, the process of processing the acquired image to obtain the bird' S-eye view panorama is as follows:
and (3) perspective viewing the multiple paths of images subjected to distortion correction and preprocessing to the same plane according to camera calibration data through overlooking transformation, and then obtaining the aerial view panoramic image after image splicing, color balance and brightness consistency processing.
Further, in step S3, the automatic parking controller analyzes and calculates the bird' S-eye view panorama, and a specific process of obtaining the coordinate information of all parking spots in the map is as follows:
and extracting an edge gray image according to the color information and gray gradient information of the aerial view panorama, then extracting a parking space line through Hough transformation, and further obtaining angular points through camera calibration and conversion detection of a pixel coordinate system and a vehicle coordinate system so as to obtain the angular points and parking space line coordinates of all parking spaces.
Further, in step S5, the detection criterion is that the brightness of the detection area is less than 20Lux for 10 consecutive frames. The detection standard can be set according to actual conditions, is not limited here, and can be changed according to actual needs.
Further, in step S5, the process of controlling the light supplement lamp is as follows:
and adjusting the luminous power of the light supplementing lamp according to the difference value between the brightness of the detection area and the detection standard and the compensation mechanism of increasing 0.5 watt every time when the Lux is reduced by 5Lux, and adjusting the position of the light emitted by the light supplementing lamp according to the coordinate information of the target parking space so as to ensure that the target parking space is always within the set target illumination intensity range.
Further, the target illumination intensity range is 80-120Lux. The range can be set according to actual conditions, is not limited in the above, and can be changed according to actual needs.
Further, in step S2, before processing the image, the automatic parking controller inputs the image collected by the panoramic camera into a preset deep learning neural network model, outputs an optimized image after optimizing the deep learning neural network model, and processes the optimized image to obtain a bird' S-eye view panorama; the deep learning neural network model is obtained by training image data acquired under various different conditions.
The images collected by the panoramic camera comprise parking space line images of horizontal parking spaces, vertical parking spaces and inclined parking spaces under the conditions of different brightness, different colors of parking space lines, different incomplete degrees, different lane line interference, different weather conditions, different field materials and the like of an indoor parking lot and an outdoor parking lot, the images are output and then output after being optimized on the basis of a neural network model of a deep learning algorithm, the recognition success rate of the parking space lines with different brightness, different colors of the parking space lines, different incomplete degrees, different lane line interference and the like in subsequent images can be effectively improved, and the accuracy of obtaining the coordinate information of the target parking space in subsequent image analysis and calculation is further improved.
The invention also provides a system for improving the recognition rate of the parking spaces and the parking capacity in the dark environment, which is used for realizing the method and comprises a light sensor, a light supplement lamp, a look-around camera, an ultrasonic radar and an automatic parking controller;
the light sensors and the light supplementing lamps are mounted on the rearview mirrors on the two sides of the vehicle, the light sensors are used for monitoring the ambient light brightness around the vehicle, and the light supplementing lamps are used for supplementing light in a dark light environment;
the all-round looking cameras are arranged at four positions of the vehicle and are used for collecting images around the vehicle;
the ultrasonic radar is arranged on both the front bumper and the rear bumper of the vehicle and used for sensing environmental information around the vehicle;
the automatic parking controller is used for controlling the vehicle to finish automatic parking action, and is respectively and electrically connected with the light sensor, the light supplement lamp, the all-round camera and the ultrasonic radar.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, through the cooperation of the light sensor, the light supplement lamp, the around-looking camera, the ultrasonic radar and the automatic parking controller, the ambient light brightness around the vehicle is sensed and the parking space image is collected, then the coordinate information of the target parking space under the condition of sufficient light is obtained through analysis and calculation and is fused with the parking space information collected by the ultrasonic radar, so that an effective parking space is output, and finally the automatic parking controller plans a parking route according to the effective parking space to finish automatic parking. The invention effectively improves the recognition precision and the recognition success rate of the parking space when the vehicle is automatically parked, thereby improving the parking experience of a user.
Drawings
FIG. 1 is a flow chart of a method for improving the parking space recognition rate and parking capacity in a dim light environment according to the present invention;
fig. 2 is a schematic diagram of a system for improving the parking space recognition rate and the parking capacity in the dim light environment according to the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted. The positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent.
Example 1:
as shown in fig. 1, the present embodiment provides a method for improving a parking space recognition rate and a parking capacity in a dark environment, which includes the following specific steps:
s1, after the automatic parking function of a vehicle is started, monitoring the ambient light brightness around the vehicle in real time through a light sensor, and acquiring images around the vehicle in real time through a panoramic camera;
s2, the automatic parking controller judges whether to start a light supplement lamp according to the collected ambient light brightness, and simultaneously processes the collected image to obtain a bird' S-eye view panoramic image;
s3, analyzing and calculating the aerial view panoramic image by the automatic parking controller to obtain coordinate information of all parking places in the image, and selecting the parking place closest to the position of the vehicle as a target parking place;
s4, forming a detection area on the aerial view panoramic image according to the coordinate information of the target parking space, and detecting the brightness of the detection area through Opencv;
s5, if the brightness does not accord with the set detection standard, judging that the target parking space is in a dark light area, and controlling a light supplement lamp to ensure that the target parking space is always in the set target illumination intensity range; otherwise, judging that the target parking space is not in a dim light area without controlling the light supplement lamp;
s6, monitoring spatial information corresponding to the target parking space in real time through an ultrasonic radar, fusing the spatial information and coordinate information of the target parking space through an automatic parking controller, and judging and outputting effective parking spaces according to confidence;
s7, the automatic parking controller plans a parking path according to the effective parking space and controls the vehicle to finish automatic parking in the effective parking space according to the parking path.
According to the invention, the light environment and images around the vehicle are synchronously acquired in real time through the light sensor and the all-round-looking camera, and when the brightness of the environment is lower than a certain brightness, the light supplementing lamp is activated to supplement light in real time, so that the images acquired by the all-round-looking camera are clearer; and then analyzing the image collected by the panoramic camera to form a bird's-eye view panoramic image, obtaining coordinate information of the target parking space according to the bird's-eye view panoramic image, detecting the brightness of the area where the target parking space is located, judging whether the target parking space is in a dark light area, if so, compensating illumination intensity of the target parking space and adjusting the illumination angle of the light supplement lamp through the light supplement lamp to ensure that the target parking space is always in the most suitable brightness environment, so that the recognition accuracy and the recognition success rate of the target parking space under the dark light environment are realized, and finally, the coordinate information of the target parking space is fused with the parking space information collected by the ultrasonic radar to complete the parking action.
In step S2 of this embodiment, if the ambient light brightness is less than the set brightness threshold and the duration is greater than the set duration threshold, the light supplement lamp is turned on to illuminate the dim light area; otherwise, the light supplement lamp is not started. Wherein the brightness threshold is 20Lux, and the duration threshold is 10 seconds.
The control of the light supplement lamp and the control of the all-round looking camera are independent, whether the light supplement lamp is turned on or not does not affect the real-time image acquisition of the all-round looking camera, and the light supplement lamp is turned on when the light supplement lamp is lower than the threshold value condition, so that the image acquisition definition of the all-round looking camera in a dark light environment is improved. The brightness threshold and the duration threshold can be set according to actual conditions, are not limited here, and can be changed according to actual needs.
In step S2 of this embodiment, the process of processing the acquired image to obtain the bird' S-eye view panorama is as follows:
and 4 paths of images subjected to distortion correction and preprocessing are transmitted to the same plane through overlook transformation according to camera calibration data, and then the bird's-eye view panoramic image is obtained after image splicing, color balance and brightness consistency processing.
In step S3 of this embodiment, the automatic parking controller performs analysis and calculation on the bird' S-eye view panoramic image, and a specific process of obtaining coordinate information of all parking spaces in the image is as follows:
and extracting an edge gray-scale image according to the color information and gray-scale gradient information of the aerial view panoramic image, then extracting a parking space line through Hough transform, and further obtaining angular points through camera calibration and conversion detection of a pixel coordinate system and a vehicle coordinate system so as to obtain the angular points and parking space line coordinates of all parking spaces.
In this embodiment, the technical means for performing luminance detection on the detection area by Opencv is well known to those skilled in the art and will not be described here.
In step S5 of this embodiment, the detection criterion is that the luminance of the detection region is less than 20Lux for 10 consecutive frames. The detection standard can be set according to actual conditions, is not limited here, and can be changed according to actual needs.
In step S5, the light supplement lamp is controlled as follows:
and adjusting the luminous power of the light supplementing lamp according to the difference value between the brightness of the detection area and the detection standard and the compensation mechanism of increasing 0.5 watt every time when the Lux is reduced by 5Lux, and adjusting the position of the light emitted by the light supplementing lamp according to the coordinate information of the target parking space so as to ensure that the target parking space is always within the set target illumination intensity range.
During specific operation, the automatic parking controller sends a command to control the light supplementing lamp to adjust the light emitting position and the light emitting power of the light supplementing lamp, wherein the light emitting position corresponds to the dark light area.
In this embodiment, the target illumination intensity range may be set to 80-120Lux, which may be set according to actual situations, and is not limited herein, and may be changed according to actual needs.
According to the invention, through the cooperation of the light sensor, the light supplement lamp, the around-looking camera, the ultrasonic radar and the automatic parking controller, the ambient light brightness around the vehicle is sensed and the parking space image is collected, then the coordinate information of the target parking space under the condition of sufficient light is obtained through analysis and calculation and is fused with the parking space information collected by the ultrasonic radar, so that an effective parking space is output, and finally the automatic parking controller plans a parking route according to the effective parking space to finish automatic parking. The invention effectively improves the recognition precision and the recognition success rate of the parking space when the vehicle is parked automatically, thereby improving the parking experience of users.
Example 2:
as shown in fig. 2, this embodiment provides a system for improving the recognition rate of parking spaces and the parking capability in a dim light environment, where the system is used to implement the method in embodiment 1, and the system includes a light sensor, a fill-in light, a look-around camera, an ultrasonic radar, and an automatic parking controller;
the rearview mirrors on two sides of the vehicle are respectively provided with a light sensor and a light supplement lamp, the light sensors are used for monitoring the ambient light brightness around the vehicle, and the light supplement lamps are used for supplementing light in a dark light environment;
the all-around cameras are arranged in four directions of the vehicle and are used for collecting images around the vehicle;
the front bumper and the rear bumper of the vehicle are both provided with ultrasonic radars which are used for sensing environmental information around the vehicle;
the automatic parking controller is used for controlling the vehicle to finish automatic parking action and is respectively and electrically connected with the light sensor, the light supplement lamp, the all-round camera and the ultrasonic radar.
In this embodiment, 4 look around cameras are installed respectively in the front air grid of vehicle, left/right rear-view mirror and rear bumper license plate department, are equipped with 12 ultrasonic radar simultaneously, and wherein 6 install in the front bumper shouldering, 6 install in rear bumper to realize all-round perception vehicle's environmental information all around.
In this embodiment, the panoramic camera is a 360 ° fisheye camera.
Example 3:
the embodiment is similar to the embodiment 1, except that in step S2, before processing the image, the automatic parking controller inputs the image collected by the all-round-looking camera into a preset deep learning neural network model, outputs an optimized image after optimizing the deep learning neural network model, and processes the optimized image to obtain the bird' S-eye view panorama.
In the present embodiment, the deep learning neural network model is obtained by training image data collected under various conditions.
The images collected by the panoramic camera comprise parking space line images of horizontal parking spaces, vertical parking spaces and inclined parking spaces under the conditions of different brightness, different colors of parking space lines, different incomplete degrees, different lane line interference, different weather conditions, different field materials and the like of an indoor parking lot and an outdoor parking lot, the images are output and then output after being optimized on the basis of a neural network model of a deep learning algorithm, the recognition success rate of the parking space lines with different brightness, different colors of the parking space lines, different incomplete degrees, different lane line interference and the like in subsequent images can be effectively improved, and the accuracy of obtaining the coordinate information of the target parking space in subsequent image analysis and calculation is further improved.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A method for improving parking space recognition rate and parking capacity in a dark environment is characterized by comprising the following specific steps:
s1, after the automatic parking function of the vehicle is started, monitoring the ambient light brightness around the vehicle in real time through a light sensor, and acquiring images around the vehicle in real time through a panoramic camera;
s2, the automatic parking controller judges whether to start a light supplement lamp according to the collected ambient light brightness, and simultaneously processes the collected image to obtain a bird' S-eye view panoramic image;
s3, analyzing and calculating the aerial view panoramic image by the automatic parking controller to obtain coordinate information of all parking places in the image, and selecting the parking place closest to the position of the vehicle as a target parking place;
s4, forming a detection area on the aerial view panoramic image according to the coordinate information of the target parking space, and detecting the brightness of the detection area through Opencv;
s5, if the brightness does not accord with the set detection standard, judging that the target parking space is in a dark light area, and controlling a light supplement lamp to ensure that the target parking space is always in the set target illumination intensity range; otherwise, judging that the target parking space is not in a dim light area without controlling the light supplement lamp;
s6, monitoring spatial information corresponding to the target parking space in real time through an ultrasonic radar, fusing the spatial information and coordinate information of the target parking space through an automatic parking controller, and judging and outputting effective parking spaces according to confidence;
s7, the automatic parking controller plans a parking path according to the effective parking space and controls the vehicle to finish automatic parking in the effective parking space according to the parking path.
2. The method for improving the recognition rate and the parking capacity of the parking spaces in the dim light environment according to claim 1, wherein in the step S2, if the ambient light brightness is smaller than a set brightness threshold value and the duration is longer than a set duration threshold value, a light supplement lamp is turned on to irradiate a dim light area; otherwise, the light supplement lamp is not started.
3. The method for improving the recognition rate of the parking spaces and the parking capacity in the dim light environment according to claim 2, wherein the brightness threshold is 20Lux, and the duration threshold is 10 seconds.
4. The method for improving the parking space recognition rate and the parking capacity in the dim light environment according to claim 1, wherein in the step S2, the process of processing the collected image to obtain the bird' S-eye view panorama is as follows:
and (3) perspective viewing the multiple paths of images subjected to distortion correction and preprocessing to the same plane according to camera calibration data through overlooking transformation, and then obtaining the aerial view panoramic image after image splicing, color balance and brightness consistency processing.
5. The method for improving the parking space recognition rate and the parking capacity in the dim light environment according to claim 1, wherein in step S3, the automatic parking controller analyzes and calculates the bird' S-eye view panorama, and the specific process of obtaining the coordinate information of all the parking spaces in the map is as follows:
and extracting an edge gray-scale image according to the color information and gray-scale gradient information of the aerial view panoramic image, then extracting a parking space line through Hough transform, and further obtaining angular points through camera calibration and conversion detection of a pixel coordinate system and a vehicle coordinate system so as to obtain the angular points and parking space line coordinates of all parking spaces.
6. The method as claimed in claim 1, wherein in step S5, the detection criterion is that the brightness of the detection area is less than 20Lux for 10 consecutive frames.
7. The method for improving the recognition rate and the parking capacity of the parking spaces in the dim light environment according to claim 6, wherein in the step S5, the process of controlling the light supplement lamp is as follows:
and adjusting the luminous power of the light supplementing lamp according to the difference value between the brightness of the detection area and the detection standard and the compensation mechanism of increasing 0.5 watt every time when the Lux is reduced by 5Lux, and adjusting the position of the light emitted by the light supplementing lamp according to the coordinate information of the target parking space so as to ensure that the target parking space is always within the set target illumination intensity range.
8. The method for improving the recognition rate and parking capacity of the parking spaces in the dim light environment according to claim 7, wherein the target illumination intensity is in the range of 80-120Lux.
9. The method for improving the parking space recognition rate and the parking capacity in the dim light environment according to claim 1, wherein in step S2, before the images are processed, the automatic parking controller inputs the images collected by the panoramic camera into a preset deep learning neural network model, outputs optimized images after the images are optimized by the deep learning neural network model, and processes the optimized images to obtain a bird' S-eye view panorama; the deep learning neural network model is obtained by training image data acquired under various different conditions.
10. A system for improving the recognition rate and parking capacity of the parking spaces in the dim light environment, which is characterized by being used for realizing the method for improving the recognition rate and parking capacity of the parking spaces in the dim light environment according to any one of claims 1 to 9, wherein the system comprises a light sensor, a light supplement lamp, a look-around camera, an ultrasonic radar and an automatic parking controller;
the light sensors and the light supplementing lamps are mounted on the rearview mirrors on the two sides of the vehicle, the light sensors are used for monitoring the ambient light brightness around the vehicle, and the light supplementing lamps are used for supplementing light in a dark light environment;
the all-around cameras are arranged on four directions of the vehicle and are used for collecting images around the vehicle;
the ultrasonic radar is arranged on both the front bumper and the rear bumper of the vehicle and used for sensing environmental information around the vehicle;
the automatic parking controller is used for controlling the vehicle to finish automatic parking action, and is respectively and electrically connected with the light sensor, the light supplement lamp, the all-round camera and the ultrasonic radar.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901651.2A CN115489514A (en) | 2022-07-28 | 2022-07-28 | Method and system for improving parking space recognition rate and parking capacity in dark light environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901651.2A CN115489514A (en) | 2022-07-28 | 2022-07-28 | Method and system for improving parking space recognition rate and parking capacity in dark light environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115489514A true CN115489514A (en) | 2022-12-20 |
Family
ID=84467306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210901651.2A Pending CN115489514A (en) | 2022-07-28 | 2022-07-28 | Method and system for improving parking space recognition rate and parking capacity in dark light environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115489514A (en) |
-
2022
- 2022-07-28 CN CN202210901651.2A patent/CN115489514A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110781883B (en) | Parking space size recognition system and method based on 360-degree looking-around camera | |
| AU2018282304B2 (en) | Systems and methods for positioning vehicles under poor lighting conditions | |
| JP4970516B2 (en) | Surrounding confirmation support device | |
| CN103770708B (en) | The dynamic reversing mirror self adaptation dimming estimated by scene brightness is covered | |
| JP4612635B2 (en) | Moving object detection using computer vision adaptable to low illumination depth | |
| CN110651301A (en) | Method and system for automatically coloring night vision images | |
| CN114228491B (en) | System and method for enhancing virtual reality head-up display with night vision | |
| CN107316488B (en) | Signal lamp identification method, device and system | |
| CN108650495A (en) | A kind of automobile-used panoramic looking-around system and its adaptive light compensation method | |
| CN111462522B (en) | Visual parking space detection method capable of eliminating influence of strong ground reflected light | |
| CN208479822U (en) | A kind of automobile-used panoramic looking-around system | |
| JPWO2019194256A1 (en) | Arithmetic processing unit, object identification system, learning method, automobile, vehicle lighting equipment | |
| CN112001208B (en) | Target detection method and device for vehicle blind area and electronic equipment | |
| CN112364707B (en) | System and method for performing beyond-the-horizon perception on complex road conditions by intelligent vehicle | |
| Jiang et al. | Target detection algorithm based on MMW radar and camera fusion | |
| CN111323767A (en) | Night unmanned vehicle obstacle detection system and method | |
| CN114905512A (en) | Panoramic tracking and obstacle avoidance method and system for intelligent inspection robot | |
| US11580695B2 (en) | Method for a sensor-based and memory-based representation of a surroundings, display device and vehicle having the display device | |
| CN115489514A (en) | Method and system for improving parking space recognition rate and parking capacity in dark light environment | |
| DE102013220839B4 (en) | A method of dynamically adjusting a brightness of an image of a rear view display device and a corresponding vehicle imaging system | |
| CN113538967B (en) | Vehicle-road cooperation device and method under crossroad scene | |
| CN114445791A (en) | Roadside data acquisition and vehicle control integrated system based on machine vision and laser radar | |
| CN116258740A (en) | Vehicle-mounted forward-looking multi-target tracking method based on multi-camera pixel fusion | |
| CN211628409U (en) | Large scene recognition camera based on fisheye lens | |
| KR101934345B1 (en) | Field analysis system for improving recognition rate of car number reading at night living crime prevention |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: No. 633, Jinshan Avenue East Road, Guangzhou, Guangdong, Panyu District Applicant after: Guangzhou Automobile Group Co.,Ltd. Address before: No. 633, Jinshan Avenue East Road, Guangzhou, Guangdong, Panyu District Applicant before: Guangzhou Automobile Passenger Car Co.,Ltd. Country or region before: China |