CN113642453A - Obstacle detection method, device and system - Google Patents
Obstacle detection method, device and system Download PDFInfo
- Publication number
- CN113642453A CN113642453A CN202110917893.6A CN202110917893A CN113642453A CN 113642453 A CN113642453 A CN 113642453A CN 202110917893 A CN202110917893 A CN 202110917893A CN 113642453 A CN113642453 A CN 113642453A
- Authority
- CN
- China
- Prior art keywords
- image
- obstacle
- real
- detection
- determining
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000004888 barrier function Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 37
- 238000003860 storage Methods 0.000 claims description 14
- 230000003287 optical effect Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000011087 paperboard Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The disclosure relates to a method, a device and a system for detecting obstacles, and relates to the technical field of computers. The obstacle detection method comprises the following steps: determining an image to be identified according to real-time image data of a field to be detected; calculating the image difference between the image to be identified and a standard background image, wherein the standard background image is the image of the field to be detected without the barrier; and detecting whether an obstacle exists in the image to be recognized according to the image difference.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for detecting an obstacle, a system for detecting an obstacle, and a non-volatile computer-readable storage medium.
Background
At present, Automated Guided Vehicles (AGVs) are used in a wide variety of fields. Particularly, two-dimensional codes are adopted as a navigation mode, and the application in the market is the most common. In the goods-to-person picking mode, a common approach is to place the items on custom shelves.
For example, the shelf types are various, and the shelf can be tall or short, and large or small. The number of layers of the shelf, the number of the shelf grids and the sizes of the grids can be flexibly set according to actual operation needs.
The vast majority of the goods shelves are marked as the surfaces A or B, are designed to be open and are used as goods shelves for putting on or picking off; the other two sides are completely covered by the baffle plates to prevent the goods from falling off the shelf. There are also shelf designs that are open on four sides, especially in the operating scenario where there are many small items of merchandise.
However, in the process of unloading and carrying the racks with two or four open sides, the racks are inevitably subjected to the situation that the commodities fall off the racks, so that obstacles are formed in the AGV driving area.
In the related technology, the AGV stays in front of the obstacle until reaching the preset alarm time of the system, and gives an alarm that the AGV cannot normally reach; after the system gives an alarm, an operator determines which AGV sends an alarm and the current position on the system; when the obstacle is disposed at the position, the AGV can normally continue to travel.
Disclosure of Invention
The inventors of the present disclosure found that the following problems exist in the above-described related art: obstacles cannot be found in time, resulting in low service processing efficiency.
In view of this, the present disclosure provides a technical solution for detecting an obstacle, which can find the obstacle in time, thereby improving the service processing efficiency.
According to some embodiments of the present disclosure, there is provided a method of detecting an obstacle, including: determining an image to be identified according to real-time image data of a field to be detected; calculating the image difference between the image to be identified and a standard background image, wherein the standard background image is the image of the field to be detected without the barrier; and detecting whether an obstacle exists in the image to be recognized according to the image difference.
In some embodiments, determining the image to be recognized according to the real-time image data of the field to be detected includes: acquiring a real-time image from a monitoring video stream of a site to be detected; detecting whether a moving object exists in the real-time image; under the condition that a moving object exists, filtering the moving object in the real-time image to generate an image to be identified; and determining the real-time image as the image to be identified in the case that no moving object exists.
In some embodiments, detecting whether a moving object is present in the real-time image comprises: detecting whether a moving object exists or not by utilizing an optical flow method according to adjacent frame images of the real-time images in the monitoring video stream; in the presence of moving objects, filtering the moving objects comprises: and filtering the moving objects in the real-time image by using an optical flow method.
In some embodiments, calculating the image difference between the image to be recognized and the standard background image comprises: and carrying out image difference processing on the image to be identified and the standard background image, and determining a difference image as an image difference.
In some embodiments, detecting whether an obstacle exists in the image to be recognized according to the image difference comprises: and performing edge detection processing on the difference image, and determining the area of the obstacle in the difference image according to the size of the image area enclosed by the edges.
In some embodiments, performing edge detection processing on the difference image, and determining the area where the obstacle is located in the difference image according to the size of the image area surrounded by the edges includes: carrying out binarization processing on the difference image; performing edge detection on a binarization processing result, and determining an image area enclosed by each edge; and determining the image area as the area where the obstacle is located when the size of the image area is larger than the first threshold and smaller than the second threshold.
In some embodiments, determining the image to be recognized according to the real-time image data of the field to be detected includes: acquiring real-time image data of different areas by using image acquisition devices arranged in different areas of a detection field, wherein the real-time image data and corresponding images to be identified of the real-time image data are in corresponding relation with the areas; the detection method further comprises the following steps: and under the condition that any image to be detected has the obstacle, determining the area where the obstacle is located according to the corresponding relation.
In some embodiments, the detecting further comprises: and under the condition that the obstacle exists in the image to be detected, reporting the related information of the obstacle to an upper control system so that the upper control system can send out an early warning signal.
According to further embodiments of the present disclosure, there is provided a detection apparatus of an obstacle, including: the determining unit is used for determining an image to be identified according to the real-time image data of the field to be detected; the calculating unit is used for calculating the image difference between the image to be identified and a standard background image, wherein the standard background image is the image of the field to be detected without the barrier; and the detection unit is used for detecting whether the obstacle exists in the image to be identified according to the image difference.
According to still further embodiments of the present disclosure, there is provided a detection system of an obstacle, including: detection means for performing the detection method in any of the above embodiments; and the image acquisition device is used for acquiring real-time image data of the field to be detected.
In some embodiments, the image capturing devices are installed in different areas of the detection field, and each image capturing device has a unique identifier for identifying the captured real-time image data and the corresponding image to be recognized.
In some embodiments, the monitoring system further comprises: and the upper control system is used for sending out an early warning signal according to the related information of the obstacles reported by the detection device.
According to still further embodiments of the present disclosure, there is provided a detection apparatus of an obstacle, including: a memory; and a processor coupled to the memory, the processor configured to perform the method of detecting an obstacle of any of the above embodiments based on instructions stored in the memory device.
According to still further embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of detecting an obstacle in any of the above embodiments.
In the embodiment, the obstacles in the field to be detected are detected in time according to the image difference between the real-time image and the standard background image of the field to be detected, so that the service processing efficiency is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:
fig. 1 illustrates a flow diagram of some embodiments of a method of detecting an obstacle of the present disclosure;
fig. 2 shows a schematic diagram of some embodiments of a method of detecting an obstacle of the present disclosure;
FIG. 3 illustrates a flow diagram of further embodiments of the presently disclosed method of detecting an obstacle;
FIG. 4 illustrates a block diagram of some embodiments of an obstacle detection apparatus of the present disclosure;
FIG. 5 shows a block diagram of further embodiments of the obstacle detection apparatus of the present disclosure;
FIG. 6 illustrates a block diagram of still further embodiments of an obstacle detection apparatus of the present disclosure;
fig. 7 illustrates a block diagram of some embodiments of the obstacle detection system of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
As mentioned above, the goods are not placed neatly on the goods shelf and easily slide off to form obstacles; some commodities are wrapped with a clinker film, and the commodities are easy to slide and form obstacles.
Some shelves are open greatly, if the fish tape on the goods shelves is not tied well, or the fish tape drops off in the driving process and other uncontrollable factors, the situation that goods and the grid baffle of the goods shelves drop on the ground from the goods shelves in the actual operation process can be caused. There are also other non-rack items, such as cleaning implements, etc., that are lost to the area where the AGV operates due to some human factor.
These conditions can cause the AGV to detect a front obstacle while traveling. In order to ensure safety and prevent the AGV from colliding with a barrier, the AGV can automatically decelerate and stop in front of the barrier, and can continue to run after manual treatment for removing the barrier. This delays normal production operation.
In addition, the situation that the operation personnel do not operate according to the operation standard and the goods on the shelf are placed beyond the vertical surface of the shelf often occurs. When other AGVs pass by the goods shelf or meet other AGVs during the transportation and driving of the goods shelf by the AGVs, the goods exceeding the goods shelf or the goods shelves on the other AGVs are easily scratched, so that the AGVs are separated from the normal driving track, and influence is brought to production.
Due to the influence of some external force, the deviation of the goods shelf from the original storage position is too large, or the AGV has deviation when putting down the goods shelf. When other AGV carrying goods shelves pass through the position, the AGV carrying goods shelves are easy to scratch with the AGV carrying goods shelves.
If the material of the shelf baffle is made of the easily deformable material such as the hard paperboard, the paperboard can be broken and deformed in long-term use, so that the paperboard exceeds the vertical surface of the shelf. And the AGV and the goods shelf are easy to scratch during the driving process.
When the AGV detects the obstacle, the AGV adopts a deceleration parking mode to prevent the collision with the obstacle, and the AGV cannot continue to run until the obstacle is manually processed. This can affect the efficiency of the manufacturing operation. Particularly, when the requirement on order processing timeliness is high, the order production is not timely, namely, the so-called 'hanging order' phenomenon is often caused.
Since a plurality of code points right in front of the obstacle may be locked by the current AGV but cannot continue to travel forward by itself, the locked code points cannot be unlocked in time. Thus, other AGVs driving to the position are prevented from running due to failure of the locking point; even large-area traffic jam can be often caused, and finally, the operation personnel are time-consuming and labor-consuming to process, and the cost is high.
The AGV pushes against a carrying goods shelf for a long time, so that great loss is caused in the aspect of self energy consumption, and the AGV cannot be charged in time. In some cases, it may even happen that the AGV is completely exhausted, and it is very difficult to process the AGV again.
The AGV is in a stop waiting state for a long time, so that the utilization rate of the AGV per se is reduced. Especially, when large-scale traffic jam is caused, the actual operation efficiency is greatly influenced.
To above-mentioned technical problem, through the technical scheme of this disclosure in the place of AGV activity, especially on the route that AGV normally traveles, there is any object that loses or the commodity that drops from the goods shelves, the system can discover rapidly to give the early warning in real time, remind work very first time to handle. For example, the technical solution of the present disclosure can be realized by the following embodiments.
Fig. 1 illustrates a flow diagram of some embodiments of a method of detecting an obstacle of the present disclosure.
As shown in fig. 1, in step 110, an image to be recognized is determined according to real-time image data of a field to be detected.
In some embodiments, a standard background image may be acquired on demand in advance. For example, a standard background image may be pre-processed into a subsequently required data format.
In some embodiments, the standard background map and the real-time image may be acquired in a synchronized process. For example, the system may obtain real-time images from a video stream in real-time; and acquiring real-time pictures from the video stream at regular time (the acquisition frequency can be determined according to actual requirements).
In some embodiments, a real-time image is obtained from a surveillance video stream of a site to be detected; detecting whether a moving object exists in the real-time image; under the condition that a moving object exists, filtering the moving object in the real-time image to generate an image to be identified; and determining the real-time image as the image to be identified in the case that no moving object exists.
For example, detecting whether a moving object exists or not by using an optical flow method according to adjacent frame images of the real-time image in the monitoring video stream; in the presence of moving objects, filtering the moving objects comprises: and filtering the moving objects in the real-time image by using an optical flow method.
For example, in a complex scene with moving objects, the moving objects can be identified and filtered out by using an optical flow method.
The video stream acquired in the field may have slight jitter, which may cause a situation that the standard background image and the real-time image are not completely consistent. Jitter displacement may be added to the image by the pixel compression process to simulate this situation for testing the technical solution of the present disclosure.
In step 120, an image difference between the image to be recognized and a standard background image is calculated, where the standard background image is an image of the field to be detected without the obstacle.
In some embodiments, the image difference processing is carried out on the image to be identified and the standard background image, and a difference image is determined as an image difference; and performing edge detection processing on the difference image, and determining the area of the obstacle in the difference image according to the size of the image area enclosed by the edges.
For example, firstly, the image to be recognized and the standard background image are subjected to gray processing (for example, an RGB component averaging mode is adopted); then, after Gaussian smoothing, median filtering and the like are adopted for processing, normalization processing is carried out; finally, image difference processing is performed.
For example, the image difference processing may be subtracting pixel values of pixel points at corresponding positions of two pictures to obtain a difference image.
In some embodiments, the difference image is subjected to binarization processing; and carrying out edge detection on the binarization processing result, and determining an image area enclosed by each edge.
For example, a gray threshold may be set, and two portions of the difference image with gray values greater than and less than the gray threshold may be determined; and processing the pixel points smaller than the gray threshold value into black, and not processing the pixel points larger than the gray threshold value. The binaryzation processing can filter out the whole position deviation caused by the shake during image acquisition, thereby improving the detection accuracy. For example, the grayscale threshold may be between 85 and 120.
In step 130, whether an obstacle exists in the image to be recognized is detected according to the image difference.
In some embodiments, in the case where the size of the image area is greater than the first threshold and less than the second threshold, the image area is determined to be the area where the obstacle is located.
For example, the boundaries in the binarized image may be found first; the boundaries are filtered, i.e. regions that are too small or too large, which may be noise-forming, are filtered out according to the size of the region enclosed by the boundaries.
If the outline of the obstacle is not identified in the area threshold range, the obstacle is not considered to appear, and the process is ended; if a plurality of goods fall off or the goods shelf moves on site, the area enclosed by the identified boundary can be a plurality of areas, and identification can be performed on the image by using the identification frame according to the position of the identified obstacle.
In some embodiments, real-time image data of different areas are acquired by using image acquisition devices installed in different areas of a detection field, and a corresponding relation is established between each real-time image data and a corresponding image to be identified and each area; and under the condition that any image to be detected has the obstacle, determining the area where the obstacle is located according to the corresponding relation.
For example, when the image to be detected has an obstacle, the information related to the obstacle is reported to the upper control system, so that the upper control system sends out an early warning signal.
Fig. 2 shows a schematic diagram of some embodiments of the method of detecting an obstacle of the present disclosure.
As shown in FIG. 2, the camera is installed above the AGV activity field, so that image data in the AGV activity field are collected in real time, and the image data are uploaded to an intelligent image identification system comprising a detection device.
Therefore, as long as any object is left in the range visible by the camera, the intelligent picture identification system can quickly give out positioning and immediately report the area where the object is located to the upper control system. For example, the upper level control system may include an AGV console system.
The upper control system can immediately give a very obvious early warning; operators can immediately know which region has the obstacle object to drop, and the manual treatment is only needed. If the obstacle clearing robot is arranged on site, the obstacle clearing robot can be directly called to a destination point to clear obstacles.
In some embodiments, a camera device may be installed above the AGV arena, and each camera is assigned a unique number; and setting a unique number for the fixed position where each camera is installed.
In some embodiments, a camera may be turned on to record live operation pictures in real time. For example, the image collector can decompose the video data into a picture according to frames and upload the picture to the image intelligent identification system in real time; the image recognition system can adopt a target recognition method based on a single frame to locate the position of the obstacle.
When the image intelligent recognition system finds that the obstacle is left in the field, the obstacle is reported to the upper control system according to the number of the current camera and the position of the current camera. And the upper control system gives real-time early warning.
For example, a large screen may be installed at a prominent position of the field to be detected, and a picture with an obstacle captured by the camera may be displayed on the large screen in real time. The operator can timely handle the left-over object or directly schedule the obstacle clearing robot to immediately clear.
Fig. 3 shows a flow chart of further embodiments of the obstacle detection method of the present disclosure.
As shown in fig. 3, in step 310, a standard background image may be acquired in advance as required. For example, a standard background image may be pre-processed into a subsequently required data format. The standard background image and the real-time image can be acquired in a synchronous processing mode. For example, the system may obtain real-time images from a video stream in real-time; and acquiring real-time pictures from the video stream at regular time (the acquisition frequency can be determined according to actual requirements).
In step 320, it may be determined whether a moving object exists in the image by using an optical flow method. Under the complex scene with moving objects, the moving objects can be identified by using an optical flow method, and the images to be detected are determined after the moving objects are filtered; in the case where there is no moving object, the image may be taken as an image to be detected.
In step 330, the image to be recognized and the standard background image are subjected to a gray scale process (e.g., an RGB component averaging process). For example, RGB (red green blue) component data may be read in accordance with image information to perform gradation processing.
In step 340, a picture morphology process is performed. For example, the normalization process may be performed after the process such as gaussian smoothing or median filtering is performed.
In step 350, image difference processing is performed. The image difference processing may be subtracting pixel values of pixel points at corresponding positions of the two pictures to obtain a difference image.
In step 360, the contour of the obstacle is detected. For example, a gray threshold may be set, and two portions of the difference image with gray values greater than and less than the gray threshold may be determined; and processing the pixel points smaller than the gray threshold value into black, and not processing the pixel points larger than the gray threshold value. The binaryzation processing can filter out the whole position deviation caused by the shake during image acquisition, thereby improving the detection accuracy. For example, the grayscale threshold may be between 85 and 120.
In step 370, it is determined whether the difference is greater than a threshold. For example, if no contour of an obstacle is identified within the area threshold range, no obstacle is considered to be present, and step 310 is repeatedly performed; if there are more than one item dropped or shelf moved in the field, the identified area bounded by the boundaries can be more than one and step 380 can be performed.
In step 380, an image is identified using an identification frame based on the location of the identified obstacle.
In the embodiment, the image recognition technology is combined with an AGV operation scene, the obstacle is positioned through the image recognition technology, and an alarm is sent out, so that the obstacle can be removed by a manual or obstacle clearing robot at the first time.
Thus, the technical problem that the falling problem of the article is difficult to find can be solved; the problem that the AGV stays in a certain area for a long time due to the fault of the AGV is solved; the problem of overlarge offset of the goods shelf and the storage position is found in time; the problem that the articles on the goods shelf are not placed orderly or exceed the vertical surface of the goods shelf is found in time; the problem that the hard paperboard of the goods shelf deforms and is damaged and exceeds the vertical surface of the goods shelf is found in time.
Fig. 4 illustrates a block diagram of some embodiments of an obstacle detection apparatus of the present disclosure.
As shown in fig. 4, the obstacle detection device 4 includes a determination unit 41, a calculation unit 42, and a detection unit 43.
The determining unit 41 determines an image to be identified according to the real-time image data of the field to be detected; the calculating unit 42 calculates the image difference between the image to be recognized and a standard background image, wherein the standard background image is an image of a to-be-detected field without an obstacle; the detection unit 43 detects whether an obstacle exists in the image to be recognized based on the image difference.
In some embodiments, the determining unit 41 obtains a real-time image from a surveillance video stream of the site to be detected; the detection unit 43 detects whether or not a moving object exists in the real-time image; the determining unit 41 filters the moving object in the real-time image to generate an image to be identified in the presence of the moving object; the determination unit 41 determines the real-time image as an image to be recognized in the absence of a moving object.
In some embodiments, the detection unit 43 detects whether there is a moving object by using an optical flow method based on the adjacent frame images of the real-time image in the monitoring video stream; the determination unit 41 filters the moving object in the real-time image using the optical flow method.
In some embodiments, the calculating unit 42 performs image difference processing on the image to be recognized and the standard background image, and determines a difference image as the image difference.
In some embodiments, the detecting unit 43 performs edge detection processing on the difference image, and determines the area where the obstacle is located in the difference image according to the size of the image area surrounded by the edges.
The detection unit 43 performs binarization processing on the difference image in some embodiments; performing edge detection on a binarization processing result, and determining an image area enclosed by each edge; and determining the image area as the area where the obstacle is located when the size of the image area is larger than the first threshold and smaller than the second threshold.
In some embodiments, the determining unit 41 obtains real-time image data of different areas by using image capturing devices installed in different areas of the detection site, where each real-time image data and its corresponding image to be identified establish a corresponding relationship with each area; when detecting that an obstacle exists in any one of the images to be detected, the determination unit 41 determines the area where the obstacle exists, based on the correspondence relationship.
In some embodiments, in the case that the detection unit 43 detects that there is an obstacle in the image to be detected, it reports the information about the obstacle to the upper control system, so that the upper control system sends out an early warning signal.
Fig. 5 shows a block diagram of further embodiments of the obstacle detection apparatus of the present disclosure.
As shown in fig. 5, the obstacle detection device 5 of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51, the processor 52 being configured to execute a method of detecting an obstacle in any one of the embodiments of the present disclosure based on instructions stored in the memory 51.
The memory 51 may include, for example, a system memory, a fixed nonvolatile storage medium, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader, a database, and other programs.
Fig. 6 shows a block diagram of still further embodiments of the obstacle detection apparatus of the present disclosure.
As shown in fig. 6, the obstacle detection device 6 of this embodiment includes: a memory 610 and a processor 620 coupled to the memory 610, the processor 620 being configured to perform the method of detecting an obstacle in any of the above embodiments based on instructions stored in the memory 610.
The memory 610 may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader, and other programs.
The obstacle detection device 6 may further include an input-output interface 630, a network interface 640, a storage interface 650, and the like. These interfaces 630, 640, 650 and the connections between the memory 610 and the processor 620 may be through a bus 660, for example. The input/output interface 630 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, a touch screen, a microphone, and a sound box. The network interface 640 provides a connection interface for various networking devices. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a usb disk.
Fig. 7 illustrates a block diagram of some embodiments of the obstacle detection system of the present disclosure.
As shown in fig. 7, the obstacle detection system 7 includes: a detection device 71 for performing the detection method in any of the above embodiments; and the image acquisition device 72 is used for acquiring real-time image data of the field to be detected.
In some embodiments, the image capturing devices 72 are installed in different areas of the inspection site, and each image capturing device 72 has a unique identifier for identifying the real-time image data captured by the image capturing device and the corresponding image to be recognized.
In some embodiments, the monitoring system 7 further comprises: and the upper control system 73 is used for sending out an early warning signal according to the relevant information of the obstacle reported by the detection device.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.
So far, the detection method of an obstacle, the detection apparatus of an obstacle, the detection system of an obstacle, and the nonvolatile computer-readable storage medium according to the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (14)
1. A method of detecting an obstacle, comprising:
determining an image to be identified according to real-time image data of a field to be detected;
calculating the image difference between the image to be recognized and a standard background image, wherein the standard background image is the image of the field to be detected without the barrier;
and detecting whether an obstacle exists in the image to be identified according to the image difference.
2. The detection method according to claim 1, wherein the determining the image to be recognized according to the real-time image data of the field to be detected comprises:
acquiring a real-time image from the monitoring video stream of the site to be detected;
detecting whether a moving object exists in the real-time image;
under the condition that a moving object exists, filtering the moving object in the real-time image to generate the image to be identified;
and determining the real-time image as the image to be identified in the case of no moving object.
3. The detection method according to claim 2, wherein the detecting whether a moving object exists in the real-time image comprises:
detecting whether a moving object exists or not by utilizing an optical flow method according to adjacent frame images of the real-time image in the monitoring video stream;
the filtering of the moving objects in the presence of the moving objects comprises:
and filtering the moving objects in the real-time image by using an optical flow method.
4. The detection method of claim 1, wherein the calculating an image difference between the image to be recognized and a standard background image comprises:
and carrying out image difference processing on the image to be identified and the standard background image, and determining a difference image as the image difference.
5. The detection method according to claim 4, wherein the detecting whether an obstacle exists in the image to be recognized according to the image difference comprises:
and performing edge detection processing on the differential image, and determining the area of the obstacle in the differential image according to the size of the image area enclosed by the edges.
6. The detection method according to claim 5, wherein the performing edge detection processing on the difference image and determining a region where an obstacle is located in the difference image according to a size of an image region surrounded by edges comprises:
carrying out binarization processing on the differential image;
performing edge detection on a binarization processing result, and determining an image area enclosed by each edge;
and determining the image area as the area where the obstacle is located when the size of the image area is larger than the first threshold and smaller than the second threshold.
7. The detection method according to any one of claims 1 to 6, wherein the determining the image to be recognized according to the real-time image data of the field to be detected comprises:
acquiring real-time image data of different areas by using image acquisition devices arranged in different areas of the detection field, wherein the real-time image data and the corresponding image to be identified are in corresponding relation with the areas;
further comprising:
and under the condition that any image to be detected has an obstacle, determining the area where the obstacle is located according to the corresponding relation.
8. The detection method according to any one of claims 1-6, further comprising:
and under the condition that the obstacle exists in the image to be detected, reporting the related information of the obstacle to an upper control system so that the upper control system can send out an early warning signal.
9. An obstacle detection device comprising:
the determining unit is used for determining an image to be identified according to the real-time image data of the field to be detected;
the calculation unit is used for calculating the image difference between the image to be identified and a standard background image, wherein the standard background image is the image of the field to be detected without the barrier;
and the detection unit is used for detecting whether an obstacle exists in the image to be identified according to the image difference.
10. A system for detecting an obstacle, comprising:
detection means for performing the detection method of any one of claims 1-8;
and the image acquisition device is used for acquiring real-time image data of the field to be detected.
11. The detection system according to claim 10, wherein the plurality of image capturing devices are respectively installed in different areas of the detection site, and each image capturing device has a unique identifier for identifying the real-time image data captured by the image capturing device and the corresponding image to be identified.
12. The detection system of claim 10, further comprising:
and the upper control system is used for sending out an early warning signal according to the related information of the obstacle reported by the detection device.
13. An obstacle detection device comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of detecting an obstacle of any one of claims 1-8 based on instructions stored in the memory.
14. A non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of detecting an obstacle according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110917893.6A CN113642453A (en) | 2021-08-11 | 2021-08-11 | Obstacle detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110917893.6A CN113642453A (en) | 2021-08-11 | 2021-08-11 | Obstacle detection method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642453A true CN113642453A (en) | 2021-11-12 |
Family
ID=78420762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110917893.6A Pending CN113642453A (en) | 2021-08-11 | 2021-08-11 | Obstacle detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642453A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007188268A (en) * | 2006-01-12 | 2007-07-26 | Univ Of Tokyo | On-image mobile object tracking method and device |
| CN103366374A (en) * | 2013-07-12 | 2013-10-23 | 重庆大学 | Fire fighting access obstacle detection method based on image matching |
| CN104331910A (en) * | 2014-11-24 | 2015-02-04 | 沈阳建筑大学 | Track obstacle detection system based on machine vision |
| CN108898055A (en) * | 2018-05-24 | 2018-11-27 | 长安大学 | A kind of mobile robot obstacle detection method of detection information fusion |
| JP2019057197A (en) * | 2017-09-22 | 2019-04-11 | 株式会社Ｓｕｂａｒｕ | Moving object recognition device |
| CN112163446A (en) * | 2020-08-12 | 2021-01-01 | 浙江吉利汽车研究院有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
-
2021
- 2021-08-11 CN CN202110917893.6A patent/CN113642453A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007188268A (en) * | 2006-01-12 | 2007-07-26 | Univ Of Tokyo | On-image mobile object tracking method and device |
| CN103366374A (en) * | 2013-07-12 | 2013-10-23 | 重庆大学 | Fire fighting access obstacle detection method based on image matching |
| CN104331910A (en) * | 2014-11-24 | 2015-02-04 | 沈阳建筑大学 | Track obstacle detection system based on machine vision |
| JP2019057197A (en) * | 2017-09-22 | 2019-04-11 | 株式会社Ｓｕｂａｒｕ | Moving object recognition device |
| CN108898055A (en) * | 2018-05-24 | 2018-11-27 | 长安大学 | A kind of mobile robot obstacle detection method of detection information fusion |
| CN112163446A (en) * | 2020-08-12 | 2021-01-01 | 浙江吉利汽车研究院有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 肖贵平 等: "《十二五普通高等教育本科国家级规划教材 交通安全工程 第3版》", 31 January 2012, 北京：中国铁道出版社, pages: 271 - 276 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10692231B1 (en) | Composite agent representation | |
| CN111461107B (en) | Material handling method, apparatus and system for identifying a region of interest | |
| US11625854B2 (en) | Intelligent forklift and method for detecting pose deviation of container | |
| CN106573381B (en) | The visualization of truck unloader | |
| JP6630485B2 (en) | Video tracking based method for automatically ordering vehicles in drive-through applications | |
| US10810539B1 (en) | Re-establishing tracking of a user within a materials handling facility | |
| CN111310645A (en) | Overflow bin early warning method, device, equipment and storage medium for cargo accumulation amount | |
| WO2021249406A1 (en) | Cargo box extraction and device, system, robot, and storage medium | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| JP6549400B2 (en) | System and method for video-based detection of drive and pedestrian walk-offs in trains of vehicles and pedestrians | |
| US11875570B1 (en) | Updating agent position information | |
| CN105893940A (en) | Method for realizing container hoisting crashproof aligning system based on edge detection | |
| US10679177B1 (en) | Using depth sensing cameras positioned overhead to detect and track a movement of a user within a materials handling facility | |
| AU2011290557B2 (en) | Sensor data processing | |
| EP3434623B1 (en) | Projection indicator, cargo assortment system, and projection indicating method | |
| US11205270B1 (en) | Collecting user pattern descriptors for use in tracking a movement of a user within a materials handling facility | |
| US10586203B1 (en) | Segmenting a user pattern into descriptor regions for tracking and re-establishing tracking of a user within a materials handling facility | |
| CN110415221B (en) | Automatic detection method for preventing container truck from being lifted based on image feature point matching | |
| US20130027550A1 (en) | Method and device for video surveillance | |
| CN114170252A (en) | Truck head anti-smashing protection system and method based on machine vision | |
| WO2021129608A1 (en) | Pickup robot, pickup method, and computer-readable storage medium | |
| CN113642453A (en) | Obstacle detection method, device and system | |
| CN117437264A (en) | Behavior information identification method, device and storage medium | |
| CN115953759A (en) | Method and device for detecting parking space limiter, electronic equipment and storage medium | |
| WO2018110377A1 (en) | Video monitoring device |
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 |