CN111429400A - Method, device, system and medium for detecting dirt of laser radar window - Google Patents
Method, device, system and medium for detecting dirt of laser radar window Download PDFInfo
- Publication number
- CN111429400A CN111429400A CN202010106656.7A CN202010106656A CN111429400A CN 111429400 A CN111429400 A CN 111429400A CN 202010106656 A CN202010106656 A CN 202010106656A CN 111429400 A CN111429400 A CN 111429400A
- Authority
- CN
- China
- Prior art keywords
- window
- laser radar
- preset
- point cloud
- cloud data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The embodiment of the invention provides a method, a device, a system and a medium for detecting dirt of a laser radar window, wherein the method comprises the following steps: acquiring point cloud data obtained by scanning the laser radar; the point cloud data comprises reflected light intensity; identifying the point cloud data to determine each obstacle; determining the obstacles in a preset distance range of the window position of the laser radar in all the obstacles as suspicious obstacles; and if the intensity of at least one reflected light in each suspicious shelter is greater than the first preset light intensity, determining that the shelter exists on the window of the laser radar. The embodiment of the invention provides a method, a device, a system and a medium for detecting laser radar window dirt, so as to realize detection of the laser radar window dirt.
Description
Technical Field
The invention relates to a laser radar technology, in particular to a method, a device, a system and a medium for detecting dirt on a laser radar window.
Background
The external structure of the laser radar has a mirror structure (or called a window, a filter cover, etc.), and the mirror structure is mainly used for filtering out interference light of a non-radar working laser wave band and also plays a role in protecting internal devices. In a harsh working environment, the mirror structure may be contaminated by various conditions, and the source of the contamination is usually dust, soil, water droplets or other liquid solids. The contaminated mirror surface can influence the transmission and the receipt of radar laser, leads to radar laser's range finding mistake to appear, and the radar can't normally work.
Traditional laser radar wiper mechanism needs artifical manual control wiper mechanism to begin work to the realization relies on the manpower to laser radar's washing, and this kind needs can increase the human cost, and because the manual work is periodic usually and inspects, can lead to laser radar's cleaning work to go on in time. Or, the pollution degree of the laser radar mirror surface needs to be sensed by corresponding hardware equipment, such as special laser radar mirror surface pollution degree sensing equipment, and then whether the cleaning mechanism is started or not is determined. This method requires additional equipment, increases costs, and is complicated.
Disclosure of Invention
The embodiment of the invention provides a method, a device, a system and a medium for detecting laser radar window dirt, so as to realize detection of the laser radar window dirt.
In a first aspect, an embodiment of the present invention provides a method for detecting contamination of a window of a laser radar, including:
acquiring point cloud data obtained by scanning the laser radar; the point cloud data comprises reflected light intensity;
identifying the point cloud data to determine each obstacle;
determining the obstacles in a preset distance range of the window position of the laser radar in all the obstacles as suspicious obstacles;
and if the intensity of at least one reflected light in each suspicious shelter is greater than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
In a second aspect, an embodiment of the present invention provides a device for detecting contamination of a window of a laser radar, including:
the point cloud data acquisition module is used for acquiring point cloud data obtained by scanning the laser radar; the point cloud data comprises reflected light intensity;
the obstacle identification module is used for identifying the point cloud data to determine each obstacle;
the suspicious shelter determining module is used for determining a barrier in a preset distance range of the window position of the laser radar in each barrier as a suspicious shelter;
and the shielding object determining module is used for determining that shielding objects exist on the window of the laser radar if the intensity of at least one reflected light in each suspicious shielding object is greater than a first preset light intensity.
In a third aspect, an embodiment of the present invention provides a laser radar cleaning system, including:
the laser radar cleaning mechanism is used for cleaning a window of the laser radar; and
the cleaning control equipment is connected with the laser radar cleaning mechanism and comprises a processor and a memory; the memory has stored therein a computer program such that the processor, when executing the computer program, implements the method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium, on which a computer program is stored, which when executed by a processor implements the method according to the first aspect.
According to the detection method for the laser radar window dirt, each obstacle is obtained according to point cloud data obtained through scanning of the obtained laser radar, the obstacle located in a preset distance range of the window position of the laser radar in each obstacle is determined to be a suspicious shelter, whether the shelter exists in each suspicious shelter is judged according to the intensity of reflected light, the intensity of the reflected light of at least one suspicious shelter is larger than the first preset light intensity, the shelter is determined to exist, and therefore the radar window pollution is judged.
Drawings
FIG. 1 is a flowchart of a method for detecting contamination of a lidar window according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a method for detecting contamination in a lidar window according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a method for detecting contamination in a lidar window according to a third embodiment of the present invention;
FIG. 4 is a flowchart of a method for detecting contamination in a lidar window according to a fourth embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a device for detecting contamination in a lidar window according to a fifth embodiment of the present invention;
fig. 6A is a schematic structural diagram of a laser radar cleaning system according to a sixth embodiment of the present invention;
fig. 6B is a schematic structural diagram of a cleaning control device in a laser radar cleaning system according to a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for detecting contamination on a laser radar window according to a first embodiment of the present invention, which is suitable for a situation where the contamination on the laser radar window is detected by point cloud data acquired by a laser radar. The method can be executed by a cleaning control device in the laser radar cleaning system of the embodiment of the invention, and the processing device can be realized in a software and/or hardware mode. As shown in fig. 1, the method specifically includes the following steps:
s101, point cloud data obtained by scanning of a laser radar is obtained; the point cloud data includes reflected light intensity.
The point cloud data may be a set of three-dimensional coordinate vectors recorded in the form of a point cloud when the laser radar scans a scene where the laser radar is located, and each three-dimensional coordinate vector may be represented by (x, y, z). The point cloud data may include a plurality of data points, and the point cloud data may also include a reflected light intensity value for each data point.
And S102, identifying the point cloud data to determine each obstacle.
Optionally, there may be many methods for identifying point cloud data, and this embodiment is not limited thereto. The current point cloud data can be clustered by adopting a clustering method, and at least one obstacle in the current point cloud data is determined. The method can also be based on a pre-trained deep learning model, the current frame point cloud data is input into the target detection model, and the at least one obstacle corresponding to the current frame point cloud data can be obtained by operating the deep learning model. The obstacle can be a dynamic obstacle such as a pedestrian, a vehicle and an animal in a road, a static obstacle such as a street lamp, an indicator board and a garbage can in the road, or a shelter on a laser radar window. Wherein, the sheltering object on the laser radar window is the dirt.
S103, determining the obstacle in the preset distance range of the window position of the laser radar in all the obstacles as a suspicious shelter.
Wherein each obstacle may have a different distance, which is the distance of the obstacle from the center point of the lidar (i.e. the origin of the lidar coordinate system). The window of the lidar is fixed in position relative to the lidar and therefore its distance from the centre point of the lidar is known. Therefore, whether the obstacle is positioned on the window or belongs to an environmental obstacle independent of the outside of the window can be roughly determined by judging whether the distance of the obstacle is the same as or close to the distance of the window. It can be understood that when the distance of barrier is in the preset distance range of window position, also can tentatively judge it and shelter from the thing for suspicious to avoid because the missed measure problem that measuring error leads to, improve the precision that detects. For example, if the window position is 60mm, the obstacles within the range of ± 0.5mm can be preliminarily determined to be located on the window, that is, the obstacles within the range of 59.5mm to 60.5mm can be preliminarily determined to be located on the window, so as to determine that the obstacles are suspicious obstructions. It is understood that the preset distance deviation can be set according to the requirements of the laser radar such as size and accuracy, and is not limited to the above example.
For example, there may be many methods for obtaining the distance of the obstacle, and this embodiment is not limited thereto. For example, a time-of-flight method, a phase method, a frequency difference method, a trigonometric method, or the like can be used.
And S104, if the intensity of at least one reflected light in each suspicious shelter is greater than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
It can be understood that the laser beam emitted by the laser radar can be emitted out through the window without the part of the laser radar window which is shielded by the shielding object, and the light intensity reflected by the window is smaller; the part of the radar window, which is shielded by the shielding object, has larger light intensity when the laser beam emitted by the laser radar is reflected by the window.
In this step, if the intensity of the reflected light of a suspicious obstruction is greater than the first preset light intensity, it is determined that the obstruction exists on the window of the laser radar. Optionally, the number of the obstacles may be determined while determining whether the obstacles exist, that is, the number of the determined obstacles is counted. For example, if the intensity of the reflected light of N suspicious obstructions is greater than the first preset light intensity, it may be determined that N obstructions exist on the window of the lidar. N is an integer greater than or equal to 1.
Optionally, if the intensity of the reflected light of any one of the suspicious obstructions is less than or equal to the first preset light intensity, it is determined that no obstruction exists on the window of the laser radar.
Exemplarily, the first preset light intensity is 1 uw. The first predetermined light intensity may be set according to the intensity of reflected light formed when no blocking object is present on the window. The intensity of the reflected light can be tested in advance. In other embodiments, the contamination condition may be determined according to the application environment of the lidar, and the range of the reflected light intensity that the contamination can form when the window is viewed is set.
Illustratively, in this step, the suspected obstruction is formed by clustering a plurality of data points, and the intensity of the reflected light of the suspected obstruction corresponds to the average value of the intensities of the reflected light of the plurality of data points of the suspected obstruction. In other embodiments, the maximum, minimum, or median of the reflected light intensities of the data points corresponding to the suspicious occlusion may also be taken as the reflected light intensity of the suspicious occlusion. It will be appreciated that the overall reflection of the suspicious occlusion is better reflected than the maximum, minimum or median.
According to the detection method for the laser radar window dirt, each obstacle is obtained according to point cloud data obtained through scanning of the obtained laser radar, the obstacle located in a preset distance range of the window position of the laser radar in each obstacle is determined to be a suspicious shelter, then whether the shelter exists in each suspicious shelter or not is judged according to the intensity of reflected light, and when the intensity of the reflected light of at least one suspicious shelter is larger than first preset light intensity, the shelter exists on the window of the laser radar. According to the detection method for the dirt on the laser radar window, provided by the embodiment of the invention, the dirt is detected by directly utilizing the point cloud data acquired in the working process of the laser radar without manual detection or by means of special dirt detection equipment, so that the dirt on the laser radar window is judged, the cost is low, and the miniaturization of the laser radar is favorably realized.
Optionally, after step S104, if the ratio of the data points of the obstruction in the point cloud data is greater than the preset ratio, a cleaning instruction is generated to control the cleaning mechanism to clean the window. Wherein, wiper mechanism refers to laser radar's wiper mechanism, and wiper mechanism is used for wasing and gets rid of the filth on the laser radar window. Therefore, on the basis of the implementation mode, the steps can detect whether dirt exists on the laser radar window, and when the proportion of the data points of the shielding objects in point cloud data is larger than the preset proportion, the cleaning mechanism can be automatically started to clean the laser radar window to remove the shielding objects on the window, so that the cleaning is not required to be carried out by relying on manpower, the manpower is saved, and the timeliness of cleaning the shielding objects on the laser radar window is ensured. The size of the shielding object is determined by the ratio of the data points of the shielding object in the whole point cloud, so that the cleaning mechanism is controlled to clean when the ratio is larger than a certain ratio, and the problems that the cleaning mechanism is frequently triggered and the normal work of the laser radar is interfered due to the existence of the miscellaneous points on the window can be avoided.
Illustratively, the ratio of data points of the shielding object in point cloud data is greater than 30%, the shielding object is more on a laser radar window, the working influence on the laser radar is larger, the shielding object needs to be cleaned, and a cleaning instruction can be generated at the moment to control a cleaning mechanism to clean the window. The ratio of data points of the shielding object in point cloud data is less than or equal to 30%, the shielding object is less on a laser radar window, the influence on the work of a laser radar is small, the shielding object does not need to be cleaned, and a cleaning instruction is not generated.
Optionally, in the embodiment of the present invention, there are many methods for determining an obstacle located within a preset distance range of the window position of the laser radar in each obstacle as a suspicious obstruction, and this embodiment is not limited to this embodiment.
One possible implementation may be: acquiring multi-frame point cloud data acquired by multiple scanning of the laser radar. And determining the obstacles which are positioned in a preset distance range of the window position of the laser radar and have similar position distribution in at least two frames of adjacent point cloud data as suspicious shelters. Because the position of the shielding object on the window of the laser radar is fixed, on the basis of the preset distance range of the position of the window of the laser radar in each obstacle, the accuracy of suspicious shielding object judgment can be improved by combining the characteristic that the same obstacle has similar position distribution in at least two frames of adjacent point cloud data, and therefore the accuracy of the shielding object judgment can be improved. Therefore, the problem that the barrier which is instantly on the window and then falls off is determined as a suspicious shelter and then is determined as a shelter to trigger the cleaning mechanism to clean can be avoided.
Illustratively, in the first frame of point cloud data, an obstacle a is located in a preset distance range of the window position of the laser radar, and the obstacle a is located at position 1 of the upper left corner of the point cloud. In the second frame of point cloud data, the obstacle A is located in a preset distance range of a window position of the laser radar, and the obstacle A is located at a position 1 of the upper left corner of the point cloud. It is to be understood that the position 1 may be completely the same as the position 1, or a certain deviation may be allowed, and the obstacle a is determined as a suspicious obstacle as long as the obstacle can be determined to be at the position 1 within the deviation allowable range. In the first frame of point cloud data, the obstacle B is located in a preset distance range of a window position of the laser radar, and the obstacle B is located at a position 1 of the upper left corner of the point cloud. In the second frame of point cloud data, the obstacle B exceeds the preset distance range of the window position of the laser radar, and the obstacle B is located at the position 1 of the upper left corner of the point cloud. It will be appreciated that the obstruction B may originally be a blind on the window but later fall off automatically, or the obstruction B may be a dynamic obstruction so that the obstruction B is not a suspicious blind. In the first frame of point cloud data, the obstacle C is located in a preset distance range of a window position of the laser radar, and the obstacle C is located at a position 1 of the upper left corner of the point cloud. In the second frame of point cloud data, the obstacle C is located in a preset distance range of the window position of the laser radar, and the obstacle C is located at the position 2 of the upper right corner of the point cloud, so that the obstacle C is not a suspicious obstruction.
Another possible implementation may be: and determining the suspicious obstruction by the obstruction if the distance deviation of the obstruction in at least two continuous frames of point cloud data is smaller than a first distance within a preset distance range of the window position of the laser radar. Because the position of the shielding object on the window of the laser radar is fixed on the window, on the basis of the preset distance range of the position of the window of the laser radar in each obstacle, the characteristic that the distance deviation of the same obstacle in at least two frames of adjacent point cloud data is smaller than the first distance is combined, the accuracy of judging the suspicious shielding object can be improved, and the accuracy of judging the shielding object can be improved.
In the first frame of point cloud data, an obstacle D is located within a preset distance range of a window position of the laser radar, and the obstacle D is located at a distance 1 of the window position. In the second frame of point cloud data, the obstacle A is located in a preset distance range of a window position of the laser radar, and the obstacle D is located at a distance 2 of the window position. And the difference value between the distance 1 and the distance 2 is the distance deviation of the obstacle D in the first frame point cloud data and the second frame point cloud data, and when the distance deviation is smaller than the first distance, the obstacle is determined to be a suspicious obstruction. When the distance deviation is greater than or equal to the first distance, the obstacle is not a suspicious obstruction. Illustratively, the first distance is 1 cm.
Optionally, in step S103, the two methods described in the foregoing two possible embodiments may be simultaneously adopted, so as to further improve the accuracy of the determination.
Example two
Fig. 2 is a flowchart of a method for detecting contamination of a laser radar window according to a second embodiment of the present invention, and this embodiment is further optimized based on the above embodiments, and specifically provides a description of how to determine the type of an obstruction according to the intensity of reflected light of the obstruction. As shown in fig. 2, the operation process includes the following steps:
s201, point cloud data obtained by scanning of a laser radar is obtained; the point cloud data includes reflected light intensity.
S202, identifying the point cloud data to determine each obstacle.
And S203, determining the obstacle in the preset distance range of the window position of the laser radar in all the obstacles as a suspicious shelter.
S204, if the intensity of at least one reflected light in each suspicious shelter is larger than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
S205, if the intensity of the reflected light of the shielding object is greater than the first preset light intensity and less than or equal to the second preset light intensity, the shielding object is a partially transparent shielding object, and if the intensity of the reflected light of the shielding object is greater than the second preset light intensity, the shielding object is an opaque shielding object; and the second preset light intensity is greater than the first preset light intensity.
The intensity of the reflected light of the blocking object is the intensity of the reflected light of the suspicious blocking object determined as the blocking object in step S204. The light transmittance of the partially transparent shade is greater than that of the opaque shade, and the reflectivity of the partially transparent shade is less than that of the opaque shade.
By way of example, a partially transparent barrier is one that has a transmittance of greater than 30% and less than 60%. The partially transparent shade may be, for example, rain, snow, or the like. An opaque mask refers to a mask having a transmittance of less than or equal to 30%. The opaque shield can be, for example, dust, debris, etc.
Exemplarily, the second preset light intensity is 3 uw. The second preset light intensity may be determined according to the reflection intensity of dirt that may be present in the environment in which the laser radar is actually used, or the like.
In the embodiment of the present invention, after the blocking objects are determined in step S204, the type of the blocking object can be determined according to the intensity of the reflected light of each blocking object, specifically, a blocking object whose reflected light intensity is greater than the first preset light intensity and less than or equal to the second preset light intensity is a partially transparent blocking object, and a blocking object whose reflected light intensity is greater than the second preset light intensity is an opaque blocking object. In the embodiment of the invention, the type of the shielding object can be judged, so that the corresponding type of cleaning can be carried out according to the shielding object of the corresponding type, for example, the corresponding dust removing cleaning is carried out on dust (opaque shielding object), and the corresponding water removing cleaning is carried out on water drops (partial transparent shielding object).
Optionally, in step S205, if the intensity of the reflected light of the blocking object is greater than the first preset light intensity and less than or equal to the second preset light intensity, the step of making the blocking object be a partially transparent blocking object includes: if the intensity of the reflected light of the shielding object is greater than the first preset light intensity and less than or equal to the second preset light intensity, and the shielding objects are uniformly distributed in the point cloud data, the shielding object is a partially transparent shielding object. Because some transparent shelters such as rain, snow often evenly distributed in all positions of laser radar window, consequently on the basis that the reflected light intensity of sheltering from the thing is greater than first predetermined luminous intensity and is less than or equal to second predetermined luminous intensity, combine the characteristic that some transparent shelters evenly distributed, can further increase the accuracy of judging.
Optionally, after step S205, if the ratio of the data point of the obstruction in the point cloud data is greater than the preset ratio, a cleaning instruction is generated to control the cleaning mechanism to clean the window. Wherein, wiper mechanism refers to laser radar's wiper mechanism, and wiper mechanism is used for wasing and gets rid of the filth on the laser radar window. Therefore, on the basis of the implementation mode, the steps can detect whether dirt exists on the laser radar window, and when the proportion of the data points of the shielding objects in point cloud data is larger than the preset proportion, the cleaning mechanism can be automatically started to clean the laser radar window to remove the shielding objects on the window, so that the cleaning is not required to be carried out by relying on manpower, the manpower is saved, and the timeliness of cleaning the shielding objects on the laser radar window is ensured.
EXAMPLE III
Fig. 3 is a flowchart of a method for detecting contamination in a lidar window according to a third embodiment of the present invention, and this embodiment is further optimized based on the foregoing embodiment, and specifically provides a description of how to automatically heat and clean a blocking object according to the temperature of the lidar window. As shown in fig. 3, the operation process includes the following steps:
s301, point cloud data obtained by scanning of the laser radar is obtained; the point cloud data includes reflected light intensity.
S302, identifying the point cloud data to determine each obstacle.
And S303, determining the obstacle in the preset distance range of the window position of the laser radar in all the obstacles as a suspicious shelter.
S304, if the intensity of at least one reflected light in each suspicious shelter is larger than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
S305, acquiring the temperature of the window of the laser radar.
The temperature of the window of the lidar may be obtained, for example, by a temperature sensor mounted near the window.
S306, heating the window of the laser radar when the temperature of the window of the laser radar is lower than a first preset temperature value.
Optionally, in this step, when the temperature of the window of the laser radar is lower than a first preset temperature, the heating instruction is started to heat the window of the laser radar. And when the temperature of the window of the laser radar is greater than or equal to a first preset temperature, not starting the heating instruction. There are many ways to heat the window, and the embodiment of the present invention is not limited thereto. In particular, the window of the lidar may be heated, for example, by thermal conduction or by thermal convection.
Illustratively, the first preset temperature is 4 degrees celsius. When the temperature is lower than 4 ℃, water vapor is easy to condense to form water drops on a window of the laser radar. Therefore, when the temperature of the window of the laser radar is lower than 4 ℃, the window of the laser radar is heated, so that water vapor is not easy to form on the window. On the other hand, the window of the laser radar is heated, so that formed water drops can be heated and evaporated, and the water drops formed on the window can be removed. If snow covers the window, the window of the laser radar is heated, so that the snow can be melted to form water drops, and finally the water drops are heated and evaporated, and the snow on the window is removed.
S307, when the temperature of the window of the laser radar is higher than a second preset temperature value, stopping heating the window of the laser radar; the second preset temperature value is greater than the first preset temperature value.
Optionally, in this step, when the temperature of the window of the laser radar is greater than a second preset temperature, the instruction for closing heating is started, and heating of the window of the laser radar is stopped. And when the temperature of the window of the laser radar is higher than or equal to the first preset temperature and lower than or equal to the second preset temperature, the heating closing instruction is not started, and the window of the laser radar is continuously heated.
Illustratively, the second preset temperature is 5 degrees celsius. And when the temperature is higher than 5 ℃, stopping heating the window of the laser radar.
Optionally, before step S305 (obtaining the temperature of the window of the lidar), the method for detecting contamination of the window of the lidar may further include: if the intensity of the reflected light of the shielding object is greater than the first preset light intensity and less than or equal to the second preset light intensity, the shielding object is a partially transparent shielding object, and if the intensity of the reflected light of the shielding object is greater than the second preset light intensity, the shielding object is an opaque shielding object; and the second preset light intensity is greater than the first preset light intensity. If the shelter is a partially transparent shelter, step S305 is executed. It should be noted that if the shielding object is an opaque shielding object, step S305 can be executed, but the effect of cleaning the shielding object by heating is not good when the shielding object is a partially transparent shielding object.
In the embodiment of the invention, when the temperature of the laser radar window is lower than the first preset temperature, the window is automatically heated, so that the temperature of the window is raised, and the shielding object is automatically heated and cleaned in a heating mode.
Example four
Fig. 4 is a flowchart of a method for detecting dirt on a laser radar window in a fourth embodiment of the present invention, and this embodiment is further optimized based on the foregoing embodiments, and specifically provides a description of how to perform cleaning according to the size of the obstruction and the specific position of the window. As shown in fig. 4, the operation process includes the following steps:
s401, point cloud data obtained by scanning of a laser radar is obtained; the point cloud data includes reflected light intensity.
S402, identifying the point cloud data to determine each obstacle.
And S403, determining the obstacle in the preset distance range of the window position of the laser radar in all the obstacles as a suspicious shelter.
S404, if the intensity of at least one reflected light in each suspicious shelter is larger than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
And S405, determining the size and the position of the obstruction in the window according to the data point of the obstruction.
For example, the size of the obstruction can be determined by the number of data points corresponding to the obstruction, and the larger the number of data points corresponding to the obstruction, the larger the obstruction; the fewer the number of data points for a shade, the smaller the shade. The size of a shade refers to the area of the shade. The position of the obstruction in the window may be determined by the outer edges of the shape formed by the obstruction's corresponding data points in the point cloud and/or may be determined by the geometric center of the shape formed by the obstruction's corresponding data points in the point cloud.
And S406, when the area of the shielding object is larger than a preset value, generating a cleaning instruction to control a cleaning mechanism to clean the window.
In this step, when the area of the shielding object is larger than the preset value, a cleaning instruction can be generated to control the cleaning mechanism to clean the window.
In another embodiment, step S406 may also be that, when the obstruction is located in the working area of the window, a cleaning instruction may be generated to control the cleaning mechanism to clean the window. The working area of the window is an area through which laser emitted by the laser radar passes and an area through which the laser radar receives laser echo. When the shield is located in the work area, interference with the transmission and reception of the laser light may occur, requiring a cleaning mechanism to clean it.
In another embodiment, in step S406, when the area of the blocking object is larger than the preset value and the blocking object is located in the working area of the window, a cleaning instruction may be generated to control the cleaning mechanism to clean the window. That is, to avoid frequent activation of the cleaning mechanism, the cleaning mechanism is triggered to clean only when the barrier is in the working area and meets a certain size.
In another embodiment, step S406 may also be to obtain a cleaning criterion corresponding to the position according to the position, and generate the cleaning instruction when the size of the obstruction exceeds the cleaning criterion. In this embodiment, the window may be manually partitioned to configure different cleaning standards for different position areas of the lidar window, for example, the central area of the lidar window has a lower cleaning standard, and the area of the lidar window other than the central area has a higher cleaning standard. In the present application, the cleaning standard refers to a standard for triggering the cleaning mechanism to clean, and the standard may be a size standard or a reflection intensity standard. Therefore, in this case, the determination corresponding to the specific area may be performed according to the cleaning standard of different areas, and when the size of the blocking object located in the area exceeds the cleaning standard of the area, a cleaning instruction may be generated to clean the area, or the entire window of the laser radar may be cleaned.
Illustratively, the cleaning of the lidar window is applicable to any type of barrier, both partially transparent and opaque. The lidar window may be cleaned, for example, by means of a liquid, which may comprise volatile organic compounds. An alternative liquid for cleaning windows may be glass water, which includes water, alcohol, glycol, corrosion inhibitors and various surfactants. In its embodiments, the cleaning agent may also be a high pressure gas-liquid mixture, or assist in laser cauterization of the contaminants.
In the embodiment of the invention, when the area of the shielding object is larger than the preset value, a cleaning instruction can be generated to control the cleaning mechanism to clean the window; and/or, when the obstruction is in the working area of the window, a cleaning instruction can be generated to control a cleaning mechanism to clean the window. In addition, the cleaning instruction may be generated according to the cleaning standard of the different region when the size of the blocking object located in the region exceeds the cleaning standard.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a device for detecting contamination of a lidar window according to a fifth embodiment of the present invention, where the device is capable of executing a method for detecting contamination of a lidar window according to any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method. As shown in fig. 5, the apparatus specifically includes:
a point cloud data acquisition module 501, configured to acquire point cloud data obtained by scanning with a laser radar; the point cloud data includes reflected light intensity.
And an obstacle identification module 502, configured to identify the point cloud data to determine each obstacle.
And a suspicious obstruction determining module 503, configured to determine, as a suspicious obstruction, an obstruction located within a preset distance range of the window position of the laser radar in each obstruction.
And the obstruction determining module 504 is configured to determine that an obstruction exists on the window of the laser radar if the intensity of the reflected light of at least one suspicious obstruction is greater than the first preset light intensity.
Further, the apparatus further comprises: the shielding object type judging module is used for judging whether the intensity of the reflected light of the shielding object is greater than the first preset light intensity and less than or equal to the second preset light intensity or not, if so, the shielding object is a partially transparent shielding object, and if so, the shielding object is an opaque shielding object; and the second preset light intensity is greater than the first preset light intensity.
Further, the apparatus further comprises: and the cleaning control module is used for generating a cleaning instruction if the proportion of the data points of the shielding object in the point cloud data is greater than the preset proportion so as to control the cleaning mechanism to clean the window.
Further, the apparatus further comprises: the heating control module is used for acquiring the temperature of a window of the laser radar;
when the temperature of the window of the laser radar is lower than a first preset temperature value, heating the window of the laser radar;
when the temperature of the window of the laser radar is higher than a second preset temperature value, stopping heating the window of the laser radar; the second preset temperature value is greater than the first preset temperature value.
Further, the suspicious obstruction determining module 503 is further configured to determine, as a suspicious obstruction, an obstruction that is located within a preset distance range of the window position of the lidar and has similar position distribution in at least two frames of adjacent point cloud data among the obstacles.
Further, the suspicious obstruction determining module 503 is further configured to determine that the suspicious obstruction is located in a preset distance range of the window position of the laser radar in each obstacle and a distance deviation in at least two consecutive frames of point cloud data is smaller than a first distance.
Further, the cleaning control module is also used for determining the size and the position of the obstruction in the window according to the data point of the obstruction;
when the area of the shielding object is larger than a preset value and/or the shielding object is positioned in a working area of the window, generating a cleaning instruction to control a cleaning mechanism to clean the window; or
A cleaning criterion corresponding to the position is obtained according to the position, and a cleaning instruction is generated when the size of the obstruction exceeds the cleaning criterion.
EXAMPLE six
Fig. 6A is a schematic structural diagram of a laser radar cleaning system according to a sixth embodiment of the present invention, and fig. 6B is a schematic structural diagram of a cleaning control device in the laser radar cleaning system according to the sixth embodiment of the present invention. The cleaning system shown in fig. 6A includes a laser radar cleaning mechanism 61 and a cleaning control device 60. The laser radar cleaning mechanism 61 is used for cleaning a window of the laser radar. And a cleaning control device 60 connected to the laser radar cleaning mechanism 61. The wash control device 60 comprises a processor 601 and a memory 602. The memory 602 stores a computer program, so that the processor 601 executes the computer program to implement the method for detecting the window contamination of the lidar in the above-described embodiment. FIG. 6B illustrates a block diagram of an exemplary processing device 60 suitable for use in implementing embodiments of the present invention. The processing device 60 shown in fig. 6B is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention. As shown in fig. 6B, the processing device 60 is in the form of a general purpose computing device. The components of the processing device 60 may include, but are not limited to: one or more processors 601, a system memory 602, and a bus 603 that couples various system components (including the system memory 602 and the processors 601).
The processing device 60 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by processing device 60 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 602 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)604 and/or cache memory 605. The processing device 60 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 606 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6B and commonly referred to as a "hard drive"). Although not shown in FIG. 6B, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 603 by one or more data media interfaces. System memory 602 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 608 having a set (at least one) of program modules 607 may be stored, for example, in system memory 602, such program modules 607 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 607 generally perform the functions and/or methods of the described embodiments of the invention.
EXAMPLE seven
The seventh embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, can implement the method for detecting window contamination of a laser radar according to the foregoing embodiments.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious modifications, rearrangements, combinations and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for detecting dirt on a laser radar window is characterized by comprising the following steps:
acquiring point cloud data obtained by scanning the laser radar; the point cloud data comprises reflected light intensity;
identifying the point cloud data to determine each obstacle;
determining the obstacles in a preset distance range of the window position of the laser radar in all the obstacles as suspicious obstacles;
and if the intensity of at least one reflected light in each suspicious shelter is greater than the first preset light intensity, determining that the shelter exists on the window of the laser radar.
2. The method of claim 1, further comprising:
if the intensity of the reflected light of the shielding object is greater than the first preset light intensity and less than or equal to the second preset light intensity, the shielding object is a partially transparent shielding object, and if the intensity of the reflected light of the shielding object is greater than the second preset light intensity, the shielding object is an opaque shielding object; wherein the second preset light intensity is greater than the first preset light intensity.
3. The method of claim 1 or 2, further comprising:
and if the proportion of the data points of the shielding objects in the point cloud data is larger than the preset proportion, generating a cleaning instruction to control a cleaning mechanism to clean the window.
4. The method of claim 1, further comprising:
acquiring the temperature of a window of the laser radar;
when the temperature of the window of the laser radar is lower than a first preset temperature value, heating the window of the laser radar;
when the temperature of the window of the laser radar is higher than a second preset temperature value, stopping heating the window of the laser radar; the second preset temperature value is greater than the first preset temperature value.
5. The method of claim 1, further comprising obtaining multiframe point cloud data collected by multiple scans of the lidar;
the method for determining the obstacle in the preset distance range of the window position of the laser radar in all the obstacles as the suspicious shelter comprises the following steps: and determining the obstacles which are positioned in the preset distance range of the window position of the laser radar and have similar position distribution in at least two frames of adjacent point cloud data as suspicious shelters.
6. The method according to claim 1, wherein the determining of the obstacle in the preset distance range of the window position of the lidar as the suspicious obstruction comprises:
and determining the barrier as a suspicious shelter if the distance deviation of each barrier in the preset distance range of the window position of the laser radar in at least two continuous frames of the point cloud data is smaller than a first distance.
7. The method of claim 1, further comprising:
determining the size and the position of the shelter in the window according to the data points of the shelter;
when the area of the shielding object is larger than a preset value and/or the shielding object is positioned in the working area of the window, generating a cleaning instruction to control a cleaning mechanism to clean the window; or
And acquiring a cleaning standard corresponding to the position according to the position, and generating a cleaning instruction when the size of the obstruction exceeds the cleaning standard.
8. A detection device for laser radar window dirt is characterized by comprising:
the point cloud data acquisition module is used for acquiring point cloud data obtained by scanning the laser radar; the point cloud data comprises reflected light intensity;
the obstacle identification module is used for identifying the point cloud data to determine each obstacle;
the suspicious shelter determining module is used for determining a barrier in a preset distance range of the window position of the laser radar in each barrier as a suspicious shelter;
and the shielding object determining module is used for determining that shielding objects exist on the window of the laser radar if the intensity of at least one reflected light in each suspicious shielding object is greater than a first preset light intensity.
9. A lidar cleaning system, comprising:
the laser radar cleaning mechanism is used for cleaning a window of the laser radar; and
the cleaning control equipment is connected with the laser radar cleaning mechanism and comprises a processor and a memory; the memory has stored therein a computer program such that the processor, when executing the computer program, implements the method of any of claims 1-7.
10. A computer storage medium on which a computer program is stored, which program, when executed by a processor, carries out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010106656.7A CN111429400B (en) | 2020-02-21 | 2020-02-21 | Method, device, system and medium for detecting dirt of laser radar window |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010106656.7A CN111429400B (en) | 2020-02-21 | 2020-02-21 | Method, device, system and medium for detecting dirt of laser radar window |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111429400A true CN111429400A (en) | 2020-07-17 |
| CN111429400B CN111429400B (en) | 2021-04-20 |
Family
ID=71547077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010106656.7A Active CN111429400B (en) | 2020-02-21 | 2020-02-21 | Method, device, system and medium for detecting dirt of laser radar window |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111429400B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112731412A (en) * | 2020-12-28 | 2021-04-30 | 南京苏美达智能技术有限公司 | Ultrasonic obstacle avoidance method and automatic walking equipment |
| WO2021169717A1 (en) * | 2020-02-25 | 2021-09-02 | 华为技术有限公司 | Radar shielding object detection method and apparatus |
| CN113409279A (en) * | 2021-06-24 | 2021-09-17 | 北京车和家信息技术有限公司 | Effect evaluation method, device, equipment and medium of laser radar cleaning system |
| CN113635864A (en) * | 2021-07-27 | 2021-11-12 | 际络科技(上海)有限公司 | Cleaning method and device for vehicle-mounted laser radar, electronic equipment and storage medium |
| CN114012783A (en) * | 2021-10-12 | 2022-02-08 | 深圳优地科技有限公司 | Robot fault detection method, robot and storage medium |
| CN114755642A (en) * | 2022-03-23 | 2022-07-15 | 广州文远知行科技有限公司 | Radar line detection method and device, vehicle and storage medium |
| CN115359121A (en) * | 2022-08-17 | 2022-11-18 | 湖南大学无锡智能控制研究院 | Laser radar shielding judgment and cleaning method and device |
| WO2022252057A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Detection method and apparatus |
| CN115728734A (en) * | 2021-08-31 | 2023-03-03 | 深圳市速腾聚创科技有限公司 | Laser radar shielding detection method and device, storage medium and laser radar |
| CN115792870A (en) * | 2023-02-09 | 2023-03-14 | 图达通智能科技(苏州)有限公司 | Window occlusion detection method and device for laser radar |
| CN116047540A (en) * | 2023-02-07 | 2023-05-02 | 湖南大学无锡智能控制研究院 | Laser radar self-shielding judging method and device based on point cloud intensity information |
| WO2023070583A1 (en) * | 2021-10-29 | 2023-05-04 | 华为技术有限公司 | Laser radar device, cleaning method, and vehicle |
| CN116125437A (en) * | 2023-04-19 | 2023-05-16 | 山东鼎瞰智能科技发展有限公司 | Safety laser scanner and optical window detection method thereof |
| DE102022000235A1 (en) | 2022-01-24 | 2023-07-27 | Mercedes-Benz Group AG | Method for cleaning a viewing window of a lidar |
| CN117572458A (en) * | 2023-11-08 | 2024-02-20 | 探维科技(苏州)有限公司 | Dirt shielding detection method for laser radar window and related equipment thereof |
| EP4386431A1 (en) | 2022-12-15 | 2024-06-19 | Mettler-Toledo GmbH | Method for diagnosing erroneous distance measurement of a laser rangefinder unit, laser rangefinder unit and computer program |
| WO2024131976A1 (en) * | 2022-12-22 | 2024-06-27 | Hesai Technology Co., Ltd. | Obstruction detection methods and obstruction detection devices for lidars, and lidars |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5745050A (en) * | 1994-10-21 | 1998-04-28 | Mitsubishi Denki Kabushiki Kaisha | Obstacle detection apparatus for vehicles |
| JPH10142335A (en) * | 1996-11-07 | 1998-05-29 | Omron Corp | Apparatus for detecting information of object |
| JP2000035479A (en) * | 1998-07-16 | 2000-02-02 | Nec Corp | Inter-vehicle distance detecting device |
| JP2001318146A (en) * | 2000-05-11 | 2001-11-16 | Omron Corp | Body information detecting device |
| US20050184259A1 (en) * | 2004-02-19 | 2005-08-25 | Takekazu Terui | Object detection apparatus for a vehicle |
| US20080158555A1 (en) * | 2006-12-28 | 2008-07-03 | Hokuyo Automatic Co., Ltd. | Optical window contamination detecting device for optical apparatus |
| JP2018151286A (en) * | 2017-03-14 | 2018-09-27 | オムロンオートモーティブエレクトロニクス株式会社 | Object detector |
| CN110208772A (en) * | 2019-05-27 | 2019-09-06 | 驭势科技（北京）有限公司 | Laser radar protective cover and laser radar apparatus |
| WO2019233919A1 (en) * | 2018-06-07 | 2019-12-12 | Robert Bosch Gmbh | Apparatus for recognizing soiling of a transmitting window and/or a receiving window of a lidar device and corresponding method |
-
2020
- 2020-02-21 CN CN202010106656.7A patent/CN111429400B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5745050A (en) * | 1994-10-21 | 1998-04-28 | Mitsubishi Denki Kabushiki Kaisha | Obstacle detection apparatus for vehicles |
| JPH10142335A (en) * | 1996-11-07 | 1998-05-29 | Omron Corp | Apparatus for detecting information of object |
| JP2000035479A (en) * | 1998-07-16 | 2000-02-02 | Nec Corp | Inter-vehicle distance detecting device |
| JP2001318146A (en) * | 2000-05-11 | 2001-11-16 | Omron Corp | Body information detecting device |
| US20050184259A1 (en) * | 2004-02-19 | 2005-08-25 | Takekazu Terui | Object detection apparatus for a vehicle |
| US20080158555A1 (en) * | 2006-12-28 | 2008-07-03 | Hokuyo Automatic Co., Ltd. | Optical window contamination detecting device for optical apparatus |
| JP2018151286A (en) * | 2017-03-14 | 2018-09-27 | オムロンオートモーティブエレクトロニクス株式会社 | Object detector |
| WO2019233919A1 (en) * | 2018-06-07 | 2019-12-12 | Robert Bosch Gmbh | Apparatus for recognizing soiling of a transmitting window and/or a receiving window of a lidar device and corresponding method |
| CN110208772A (en) * | 2019-05-27 | 2019-09-06 | 驭势科技（北京）有限公司 | Laser radar protective cover and laser radar apparatus |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021169717A1 (en) * | 2020-02-25 | 2021-09-02 | 华为技术有限公司 | Radar shielding object detection method and apparatus |
| CN112731412A (en) * | 2020-12-28 | 2021-04-30 | 南京苏美达智能技术有限公司 | Ultrasonic obstacle avoidance method and automatic walking equipment |
| CN112731412B (en) * | 2020-12-28 | 2023-09-15 | 南京苏美达智能技术有限公司 | Ultrasonic obstacle avoidance method and automatic walking equipment |
| WO2022252057A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Detection method and apparatus |
| CN113409279A (en) * | 2021-06-24 | 2021-09-17 | 北京车和家信息技术有限公司 | Effect evaluation method, device, equipment and medium of laser radar cleaning system |
| CN113635864A (en) * | 2021-07-27 | 2021-11-12 | 际络科技(上海)有限公司 | Cleaning method and device for vehicle-mounted laser radar, electronic equipment and storage medium |
| CN113635864B (en) * | 2021-07-27 | 2023-08-15 | 际络科技(上海)有限公司 | Vehicle-mounted laser radar cleaning method and device, electronic equipment and storage medium |
| CN115728734B (en) * | 2021-08-31 | 2024-05-31 | 深圳市速腾聚创科技有限公司 | Laser radar shielding detection method and device, storage medium and laser radar |
| CN115728734A (en) * | 2021-08-31 | 2023-03-03 | 深圳市速腾聚创科技有限公司 | Laser radar shielding detection method and device, storage medium and laser radar |
| CN114012783A (en) * | 2021-10-12 | 2022-02-08 | 深圳优地科技有限公司 | Robot fault detection method, robot and storage medium |
| WO2023070583A1 (en) * | 2021-10-29 | 2023-05-04 | 华为技术有限公司 | Laser radar device, cleaning method, and vehicle |
| CN117295967A (en) * | 2021-10-29 | 2023-12-26 | 华为技术有限公司 | Laser radar apparatus, cleaning method, and vehicle |
| DE102022000235B4 (en) | 2022-01-24 | 2024-05-29 | Mercedes-Benz Group AG | Method for cleaning a viewing window of a lidar |
| DE102022000235A1 (en) | 2022-01-24 | 2023-07-27 | Mercedes-Benz Group AG | Method for cleaning a viewing window of a lidar |
| CN114755642B (en) * | 2022-03-23 | 2023-03-10 | 广州文远知行科技有限公司 | Radar line detection method and device, vehicle and storage medium |
| CN114755642A (en) * | 2022-03-23 | 2022-07-15 | 广州文远知行科技有限公司 | Radar line detection method and device, vehicle and storage medium |
| WO2024037144A1 (en) * | 2022-08-17 | 2024-02-22 | 湖南大学无锡智能控制研究院 | Laser radar occlusion determination and cleaning method and apparatus |
| CN115359121B (en) * | 2022-08-17 | 2023-05-12 | 湖南大学无锡智能控制研究院 | Laser radar shielding judging and cleaning method and device |
| CN115359121A (en) * | 2022-08-17 | 2022-11-18 | 湖南大学无锡智能控制研究院 | Laser radar shielding judgment and cleaning method and device |
| EP4386431A1 (en) | 2022-12-15 | 2024-06-19 | Mettler-Toledo GmbH | Method for diagnosing erroneous distance measurement of a laser rangefinder unit, laser rangefinder unit and computer program |
| WO2024131976A1 (en) * | 2022-12-22 | 2024-06-27 | Hesai Technology Co., Ltd. | Obstruction detection methods and obstruction detection devices for lidars, and lidars |
| CN116047540A (en) * | 2023-02-07 | 2023-05-02 | 湖南大学无锡智能控制研究院 | Laser radar self-shielding judging method and device based on point cloud intensity information |
| CN116047540B (en) * | 2023-02-07 | 2024-03-22 | 湖南大学无锡智能控制研究院 | Laser radar self-shielding judging method and device based on point cloud intensity information |
| CN115792870A (en) * | 2023-02-09 | 2023-03-14 | 图达通智能科技(苏州)有限公司 | Window occlusion detection method and device for laser radar |
| CN116125437B (en) * | 2023-04-19 | 2023-07-14 | 山东鼎瞰智能科技发展有限公司 | Safety laser scanner and optical window detection method thereof |
| CN116125437A (en) * | 2023-04-19 | 2023-05-16 | 山东鼎瞰智能科技发展有限公司 | Safety laser scanner and optical window detection method thereof |
| CN117572458A (en) * | 2023-11-08 | 2024-02-20 | 探维科技(苏州)有限公司 | Dirt shielding detection method for laser radar window and related equipment thereof |
| CN117572458B (en) * | 2023-11-08 | 2024-05-31 | 探维科技(苏州)有限公司 | Dirt shielding detection method for laser radar window and related equipment thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111429400B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111429400B (en) | Method, device, system and medium for detecting dirt of laser radar window | |
| US11372101B2 (en) | Method and apparatus for determining relative pose, device and medium | |
| CN109284348B (en) | Electronic map updating method, device, equipment and storage medium | |
| US11372098B2 (en) | Method, apparatus, device, and medium for determining angle of yaw | |
| US11226200B2 (en) | Method and apparatus for measuring distance using vehicle-mounted camera, storage medium, and electronic device | |
| JP2020098188A (en) | Obstacle detection method, obstacle detection device, electronic apparatus, vehicle and storage medium | |
| CN112513679B (en) | Target identification method and device | |
| US9129523B2 (en) | Method and system for obstacle detection for vehicles using planar sensor data | |
| CN109814114B (en) | Ultrasonic radar array, obstacle detection method and system | |
| CN110346825B (en) | Vehicle positioning method and device, vehicle and storage medium | |
| CN108859952B (en) | Vehicle lane change early warning method and device and radar | |
| JP2021514457A (en) | Rain filtering techniques for autonomous vehicles | |
| CN111942374A (en) | Obstacle map generation method and device, vehicle and storage medium | |
| CN112613424A (en) | Rail obstacle detection method, rail obstacle detection device, electronic apparatus, and storage medium | |
| WO2020147518A1 (en) | Ultrasonic radar array, and obstacle detection method and system | |
| CN112485801A (en) | Obstacle position determination method, system, computer equipment and storage medium | |
| CN115643809A (en) | Signal processing method of point cloud detection system and point cloud detection system | |
| CN110133624B (en) | Unmanned driving abnormity detection method, device, equipment and medium | |
| CN110430361B (en) | Window cleaning method and device | |
| CN113570622A (en) | Obstacle determination method and device, electronic equipment and storage medium | |
| KR20210097418A (en) | Apparatus and method for removing lidar noise | |
| CN113763260B (en) | Water drop noise-based noise filtering method, device, equipment and storage medium | |
| CN104331684A (en) | Hyper-spectral image target detection system based on dual-computer communication | |
| CN110308460B (en) | Parameter determination method and system of sensor | |
| KR20220019538A (en) | Pollution detecting device for vehicle and pollution detecting method using the same |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |