CN113065381A - Reversing safety monitoring method and reversing safety monitoring system - Google Patents
Reversing safety monitoring method and reversing safety monitoring system Download PDFInfo
- Publication number
- CN113065381A CN113065381A CN201911424145.3A CN201911424145A CN113065381A CN 113065381 A CN113065381 A CN 113065381A CN 201911424145 A CN201911424145 A CN 201911424145A CN 113065381 A CN113065381 A CN 113065381A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- pedestrian
- exists
- platform
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 49
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000010223 real-time analysis Methods 0.000 claims abstract description 24
- 239000007787 solid Substances 0.000 claims abstract description 6
- 238000009434 installation Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2015/932—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles for parking operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The monitoring method comprises the following steps: according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not; if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle; determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result; if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result; and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm. In the process of stopping the freight car at the platform in the logistics park in the reversing way, the invention assists the driver of the freight car to reverse the car, provides safety early warning in advance before danger occurs, ensures the safety of pedestrians and simultaneously avoids damaging stacked goods.
Description
Technical Field
The invention relates to the technical field of logistics, in particular to a reversing safety monitoring method and device.
Background
The dock, also known as an entry and exit dock, is the entrance and exit of the goods at the logistics park, usually connected to the warehouse.
The platform has the basic functions of loading and unloading goods, temporarily storing goods in and out of a warehouse, stopping vehicles and realizing the connection and conversion of a network central line and nodes. The basic purpose of the device is to ensure that the cargo loading and unloading operation is efficient, orderly and labor-saving. The platform facility is not only a basic guarantee condition for the operation of the storeroom in the logistics park, but also a place where the high-efficiency operation of the storeroom is not negligible.
In practice, the platform area of the logistics park is often compact in space, and the reversing space reserved for drivers is small (in a common truck structure, a rear door needs to be aligned with the platform to be parked, so that goods can be loaded and unloaded conveniently). In addition, when no truck stops, the backing route can be used for pedestrians to pass through, the flow of people is large, some goods (such as left goods when a previous truck is loaded and unloaded) are also stacked in the platform leaning area of the platform area, and the backing difficulty of the platform area is further increased by the factors.
In the prior art, a truck driver is guided to back a car by a worker of a warehouse at a platform usually, but the effect is not ideal, the wall surfaces on two sides of the platform area are often damaged due to car backing errors, and even pedestrians or temporarily stacked goods are damaged in the process of car backing.
Disclosure of Invention
The technical problem solved by the invention is as follows: how to assist a truck driver to back a car in a platform area of a logistics park.
In order to solve the technical problem, an embodiment of the present invention provides a method for monitoring reversing safety, including:
acquiring a video of a platform area in real time through video acquisition equipment, wherein the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network during training in the acquisition process;
according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not;
if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle;
detecting a platform leaning area of the platform area in real time through a radar;
determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result;
if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result;
and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm.
Optionally, the method further includes: the SSD deep neural network is trained in advance.
Optionally, the method further includes: installing video acquisition equipment at a position capable of shooting a platform area of a logistics park in advance; and a radar is fixedly arranged in a platform area of the logistics park in advance.
Optionally, the radar is a sonic radar.
Optionally, the determining whether to issue an alarm and the content of the alarm by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection include: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
Optionally, the determining whether to issue an alarm and the content of the alarm by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection include: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
In order to solve the above technical problem, an embodiment of the present invention further provides a reverse safety monitoring system, including:
one or more dock areas;
a processor adapted to load and execute instructions of a software program;
a memory adapted to store a software program comprising instructions for performing the steps of:
acquiring a video of a platform area in real time through video acquisition equipment, wherein the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network during training in the acquisition process;
according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not;
if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle;
detecting a platform leaning area of the platform area in real time through a radar;
determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result;
if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result;
and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm.
Optionally, the method further includes: the SSD deep neural network is trained in advance.
Optionally, the method further includes: installing video acquisition equipment at a position capable of shooting a platform area of a logistics park in advance; and a radar is fixedly arranged in a platform area of the logistics park in advance.
Optionally, the determining whether to issue an alarm and the content of the alarm by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection include: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
Optionally, the determining whether to issue an alarm and the content of the alarm by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection include: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
in the process that a truck backs up and stops at a dock in a logistics park, according to a video stream collected by video collecting equipment, an SSD deep neural network algorithm is adopted to analyze image frames in the video stream in real time, and whether a vehicle exists or not and whether a pedestrian exists or not are determined; if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle; determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result; if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result; the real-time analysis result of the SSD deep neural network algorithm and the radar detection result are combined to determine whether to send out the warning and the content of the warning, so that a driver of the truck is assisted to back the truck, safety early warning is provided in advance before danger occurs, the safety of pedestrians is guaranteed, and meanwhile, stacked goods are prevented from being damaged.
Drawings
Fig. 1 is a flowchart of a reversing safety monitoring method in an embodiment of the invention.
Detailed Description
According to analysis of the background art, the platform area of the logistics park is often compact in space, and the parking space reserved for drivers is small (due to the common truck structure, a rear door needs to be aligned with the platform to park, so that loading and unloading are facilitated). In addition, when no truck stops, the backing route can be used for pedestrians to pass through, the flow of people is large, some goods (such as left goods when a previous truck is loaded and unloaded) are also stacked in the platform leaning area of the platform area, and the backing difficulty of the platform area is further increased by the factors.
In the prior art, a truck driver is guided to back a car by a worker of a warehouse at a platform usually, but the effect is not ideal, the wall surfaces on two sides of the platform area are often damaged due to car backing errors, and even pedestrians or temporarily stacked goods are damaged in the process of car backing.
In the process that a truck backs up and stops at a platform in a logistics park, according to a video stream acquired by video acquisition equipment, an SSD deep neural network algorithm is adopted to analyze image frames in the video stream in real time, and whether a vehicle or a pedestrian exists is determined; if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle; determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result; if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result; the real-time analysis result of the SSD deep neural network algorithm and the radar detection result are combined to determine whether to send out the warning and the content of the warning, so that a driver of the truck is assisted to back the truck, safety early warning is provided in advance before danger occurs, the safety of pedestrians is guaranteed, and meanwhile, stacked goods are prevented from being damaged.
In order that those skilled in the art will better understand and realize the present invention, the following detailed description is given by way of specific embodiments with reference to the accompanying drawings.
Example one
As described below, an embodiment of the present invention provides a method for monitoring reversing safety.
The reversing safety monitoring method in the embodiment is suitable for installing the camera and the acoustic wave radar at the platform (or other goods handling places) of the logistics park, and judging whether warning needs to be sent out or not and the content of the warning by combining the analysis result of the video captured by the camera and the detection result of the radar.
Referring to a flowchart of a reversing safety monitoring method shown in fig. 1, the following detailed description is provided through specific steps:
and S101, installing the video acquisition equipment at a position where a platform area of the logistics park can be shot in advance.
S102, training the SSD deep neural network in advance.
The training of deep neural networks for the target detection class is well established in the prior art and will not be described herein.
And S103, acquiring the video of the platform area in real time through video acquisition equipment.
And in the acquisition process, the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network.
And S104, analyzing image frames in the video stream in real time by adopting an SSD deep neural network algorithm according to the video stream acquired by the video acquisition equipment, and determining whether vehicles and pedestrians exist.
That is, the SSD deep neural network algorithm is used to perform real-time analysis on the image frames in the video stream.
And S105, if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reverse path of the vehicle.
The foregoing steps S101 to S105 analyze the image frames in the video stream through the SSD deep neural network algorithm, and the following steps S106 to S109 analyze the result of the sonic radar detection, which may be executed in parallel without interfering with each other.
And S106, fixedly installing a radar in the platform area of the logistics park in advance.
In particular, in some embodiments, the radar is a sonic radar.
And S107, detecting the abutment area of the platform area in real time through a radar.
And S108, determining whether the platform area of the platform area has an obstacle or not according to the radar detection result.
And S109, if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result.
S110, combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result, and determining whether to send out a warning and the content of the warning.
Specifically, in some embodiments, the determining whether to issue the warning and the content of the warning by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection includes: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
In other embodiments, the combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to issue the warning, and the content of the warning includes: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
The form of warning may include flashing of an LED light, a horn broadcast, and the like.
The above description of the technical solution shows that: in the embodiment, in the process that a truck backs up and stops at a dock in a logistics park, according to a video stream acquired by video acquisition equipment, an SSD deep neural network algorithm is adopted to analyze image frames in the video stream in real time, and whether a vehicle or a pedestrian exists is determined; if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle; determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result; if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result; the real-time analysis result of the SSD deep neural network algorithm and the radar detection result are combined to determine whether to send out the warning and the content of the warning, so that a driver of the truck is assisted to back the truck, safety early warning is provided in advance before danger occurs, the safety of pedestrians is guaranteed, and meanwhile, stacked goods are prevented from being damaged.
Example two
As described below, embodiments of the present invention provide a reverse safety monitoring system.
The reversing safety monitoring system comprises:
one or more dock areas;
a processor adapted to load and execute instructions of a software program;
a memory adapted to store a software program comprising instructions for performing the steps of:
acquiring a video of a platform area in real time through video acquisition equipment, wherein the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network during training in the acquisition process;
according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not;
if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle;
detecting a platform leaning area of the platform area in real time through a radar;
determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result;
if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result;
and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm.
Specifically, in some embodiments, the determining whether to issue the warning and the content of the warning by combining the result of the real-time analysis of the SSD deep neural network algorithm with the result of the radar detection includes: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
In some embodiments, the combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to issue the warning, and the content of the warning includes: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
The above description of the technical solution shows that: in the embodiment, in the process that a truck backs up and stops at a dock in a logistics park, according to a video stream acquired by video acquisition equipment, an SSD deep neural network algorithm is adopted to analyze image frames in the video stream in real time, and whether a vehicle or a pedestrian exists is determined; if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle; determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result; if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result; the real-time analysis result of the SSD deep neural network algorithm and the radar detection result are combined to determine whether to send out the warning and the content of the warning, so that a driver of the truck is assisted to back the truck, safety early warning is provided in advance before danger occurs, the safety of pedestrians is guaranteed, and meanwhile, stacked goods are prevented from being damaged.
In some embodiments, further comprising: the SSD deep neural network is trained in advance.
In some embodiments, further comprising: installing video acquisition equipment at a position capable of shooting a platform area of a logistics park in advance; and a radar is fixedly arranged in a platform area of the logistics park in advance.
Those skilled in the art will understand that, in the methods of the embodiments, all or part of the steps can be performed by hardware associated with program instructions, and the program can be stored in a computer-readable storage medium, which can include: ROM, RAM, magnetic or optical disks, and the like.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (11)
1. A reversing safety monitoring method is characterized by comprising the following steps:
acquiring a video of a platform area in real time through video acquisition equipment, wherein the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network during training in the acquisition process;
according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not;
if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle;
detecting a platform leaning area of the platform area in real time through a radar;
determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result;
if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result;
and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm.
2. The reversing safety monitoring method according to claim 1, further comprising: the SSD deep neural network is trained in advance.
3. The reversing safety monitoring method according to claim 1, further comprising: installing video acquisition equipment at a position capable of shooting a platform area of a logistics park in advance; and a radar is fixedly arranged in a platform area of the logistics park in advance.
4. A method of reversing safety according to claim 1, wherein the radar is a sonic radar.
5. The reverse safety monitoring method according to claim 1, wherein the step of combining the real-time analysis result of the SSD deep neural network algorithm and the radar detection result to determine whether to issue a warning and the content of the warning comprises the following steps: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
6. The reverse safety monitoring method according to claim 1, wherein the step of combining the real-time analysis result of the SSD deep neural network algorithm and the radar detection result to determine whether to issue a warning and the content of the warning comprises the following steps: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
7. A reversing safety monitoring system, comprising:
one or more dock areas;
a processor adapted to load and execute instructions of a software program;
a memory adapted to store a software program comprising instructions for performing the steps of:
acquiring a video of a platform area in real time through video acquisition equipment, wherein the installation height and the angle of the video acquisition equipment are kept the same as those of the first deep neural network during training in the acquisition process;
according to a video stream acquired by video acquisition equipment, analyzing image frames in the video stream in real time by adopting an SSD (solid State disk) deep neural network algorithm, and determining whether a vehicle exists or not and whether a pedestrian exists or not;
if the vehicle exists and the pedestrian exists, determining whether the vehicle position, the pedestrian position and the pedestrian position are on a reversing route of the vehicle;
detecting a platform leaning area of the platform area in real time through a radar;
determining whether an obstacle exists in a platform leaning area of the platform area or not according to a radar detection result;
if the obstacle exists, determining the size and the position of the obstacle according to the radar detection result;
and combining the real-time analysis result of the SSD deep neural network algorithm with the radar detection result to determine whether to send out an alarm and the content of the alarm.
8. The reversing safety monitoring system according to claim 7, further comprising: the SSD deep neural network is trained in advance.
9. The reversing safety monitoring system according to claim 7, further comprising: installing video acquisition equipment at a position capable of shooting a platform area of a logistics park in advance; and a radar is fixedly arranged in a platform area of the logistics park in advance.
10. The reverse safety monitoring system according to claim 7, wherein the combining the real-time analysis result of the SSD deep neural network algorithm and the radar detection result to determine whether to issue the warning and the content of the warning comprises: if the vehicle is available and the pedestrian is located on the reverse path of the vehicle, a warning is given, and the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and prompting the pedestrian to pay attention to safety.
11. The reverse safety monitoring system according to claim 7, wherein the combining the real-time analysis result of the SSD deep neural network algorithm and the radar detection result to determine whether to issue the warning and the content of the warning comprises: and if the platform leaning area of the platform area has obstacles, giving out a warning, wherein the content of the warning comprises prompting a driver of the vehicle to stop the vehicle and reporting the size and the position of the obstacles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424145.3A CN113065381A (en) | 2019-12-30 | 2019-12-30 | Reversing safety monitoring method and reversing safety monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424145.3A CN113065381A (en) | 2019-12-30 | 2019-12-30 | Reversing safety monitoring method and reversing safety monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065381A true CN113065381A (en) | 2021-07-02 |
Family
ID=76557929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911424145.3A Pending CN113065381A (en) | 2019-12-30 | 2019-12-30 | Reversing safety monitoring method and reversing safety monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065381A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113870554A (en) * | 2021-09-06 | 2021-12-31 | 北京中交兴路信息科技有限公司 | Vehicle safety monitoring method and device, storage medium and terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106458480A (en) * | 2014-05-02 | 2017-02-22 | 亚萨合莱自动门系统有限公司 | Systems and methods for automatically controlling loading dock equipment |
| CN107458306A (en) * | 2017-07-28 | 2017-12-12 | 奇瑞汽车股份有限公司 | Vehicle safety method for early warning and device |
| US20180089616A1 (en) * | 2016-09-26 | 2018-03-29 | Cybernet Systems Corp. | Path and load localization and operations supporting automated warehousing using robotic forklifts or other material handling vehicles |
| CN109085824A (en) * | 2018-07-09 | 2018-12-25 | 深圳市易成自动驾驶技术有限公司 | Garden paths planning method, device and computer readable storage medium |
| US20190096246A1 (en) * | 2017-09-25 | 2019-03-28 | Continental Automotive Systems, Inc. | Compact modular wireless sensing radar infrastructure device |
-
2019
- 2019-12-30 CN CN201911424145.3A patent/CN113065381A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106458480A (en) * | 2014-05-02 | 2017-02-22 | 亚萨合莱自动门系统有限公司 | Systems and methods for automatically controlling loading dock equipment |
| US20180089616A1 (en) * | 2016-09-26 | 2018-03-29 | Cybernet Systems Corp. | Path and load localization and operations supporting automated warehousing using robotic forklifts or other material handling vehicles |
| CN107458306A (en) * | 2017-07-28 | 2017-12-12 | 奇瑞汽车股份有限公司 | Vehicle safety method for early warning and device |
| US20190096246A1 (en) * | 2017-09-25 | 2019-03-28 | Continental Automotive Systems, Inc. | Compact modular wireless sensing radar infrastructure device |
| CN109085824A (en) * | 2018-07-09 | 2018-12-25 | 深圳市易成自动驾驶技术有限公司 | Garden paths planning method, device and computer readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113870554A (en) * | 2021-09-06 | 2021-12-31 | 北京中交兴路信息科技有限公司 | Vehicle safety monitoring method and device, storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105809964A (en) | Traffic warning method and device | |
| CN110239522B (en) | Automatic parking method, device and equipment | |
| CN112002131A (en) | In-road parking behavior detection method and device | |
| CN113515985B (en) | Self-service weighing system, weighing detection method, weighing detection equipment and storage medium | |
| CN110956818A (en) | Method and device for controlling unmanned vehicle to drive and unmanned vehicle | |
| CN109466433B (en) | Method, device, equipment, computer readable storage medium and vehicle for providing out-of-vehicle reminder | |
| CN103886753B (en) | A kind of signal lamp control crossroad exception parking reason quickly confirms system and method | |
| DE102013223951A1 (en) | Apparatus for sensing a minor collision of a vehicle and method therefor | |
| CN112124317B (en) | Parking abnormality correction method, parking abnormality correction device, computer device, and storage medium | |
| CN111391791B (en) | Sensor cleaning method and device, unmanned vehicle for mine and readable storage medium | |
| CN112289070A (en) | Parking space detection method and device, vehicle and readable medium | |
| US20190054880A1 (en) | Method And System For Detecting An Incident , Accident And/Or Scam Of A Vehicle | |
| US20200255000A1 (en) | Method and device for safeguarding a movement of a motor vehicle on an inclined ramp | |
| CN113065381A (en) | Reversing safety monitoring method and reversing safety monitoring system | |
| US20160280135A1 (en) | Animal Detection System for a Vehicle | |
| CN111767850A (en) | Method and device for monitoring emergency, electronic equipment and medium | |
| CN108556851A (en) | A kind of front truck starting prompt system and method | |
| CN117480071A (en) | Method and inspection system for inspecting a vehicle | |
| US20230017327A1 (en) | Tailgate Position Management Systems And Methods | |
| CN109544935A (en) | Intelligent garage control method for stopping, device and storage medium | |
| CN111798666B (en) | Vehicle snapshot method and device | |
| CN114997801A (en) | Vehicle abnormity monitoring method and device and server | |
| JP2019127073A (en) | Automatic driving vehicle, parking support device, parking support method, program, and non-temporary recording medium | |
| CN110329246B (en) | Intelligent driving system and method with automatic parking function | |
| CN113879289A (en) | Parking method, system, readable storage medium and vehicle |
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 |