CN114882435A - Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium - Google Patents

Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium Download PDF

Info

Publication number
CN114882435A
CN114882435A CN202210542349.2A CN202210542349A CN114882435A CN 114882435 A CN114882435 A CN 114882435A CN 202210542349 A CN202210542349 A CN 202210542349A CN 114882435 A CN114882435 A CN 114882435A
Authority
CN
China
Prior art keywords
human
vehicle
target
distance
grid
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
Application number
CN202210542349.2A
Other languages
Chinese (zh)
Inventor
元方
朱瑞
贺吉沛
王集思
张凡超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Enc Data Service Co ltd
Original Assignee
Enc Data Service Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Enc Data Service Co ltd filed Critical Enc Data Service Co ltd
Priority to CN202210542349.2A priority Critical patent/CN114882435A/en
Publication of CN114882435A publication Critical patent/CN114882435A/en
Pending legal-status Critical Current

Links

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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a storage scene human-vehicle safety distance identification method, electronic equipment and a storage medium, wherein key frames are periodically extracted from storage operation real-time monitoring video data; detecting human targets and vehicle targets in the key frames through a pre-trained target detection model; taking a plurality of continuous key frames to judge whether the detected vehicle target is moving, if so, executing the next step; and calculating the distance between the vehicle target and the human target in the last frame and the subsequent frames of the plurality of continuous key frames, wherein if the distance meets the preset condition, the human-vehicle distance is safe, otherwise, the human-vehicle distance is unsafe. The invention can accurately identify whether the distance between a person and a vehicle is safe or not in a warehousing operation scene without additional manpower and additional equipment.

Description

Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium
Technical Field
The invention belongs to the technical field of storage scene safety, and particularly relates to a storage scene human-vehicle safety distance identification method, electronic equipment and a storage medium.
Background
In the daily warehousing operation process, two high-frequency scenes exist. One scenario is where large items are transported into a warehouse and the items are handled in designated areas and designated stacking specifications, accomplished by human and vehicle cooperation. Another scenario is where warehouse inventory is shipped out of the warehouse, also by human cooperation with the vehicle. On outdoor roads, the rules of people and vehicles are restricted by traffic rules, for example, a vehicle actively waits for pedestrians to cross the road, and people are not allowed to shuttle around the road. However, in an indoor scene such as a warehouse, a working area of a worker is large, and the worker needs to shuttle back and forth, and it is necessary to identify a safe distance between the worker and a vehicle, so that a corresponding prompt and warning can be given according to an identification result.
If the safe distance is identified in a manpower monitoring mode, extra manpower is consumed, waste and manpower redundancy are caused, or the vehicle and the person respectively carry one internet of things sensing device, so that mutual distance information can be sensed, but extra internet of things sensing devices need to be purchased.
Disclosure of Invention
Based on the above, the storage scene human-vehicle safe distance identification method, the electronic device and the storage medium are provided for solving the technical problems.
The technical scheme adopted by the invention is as follows:
on the one hand, the storage scene human-vehicle safe distance identification method is provided, and comprises the following steps:
s101, periodically extracting key frames from warehousing operation real-time monitoring video data;
s102, detecting human targets and vehicle targets in the key frames through a pre-trained target detection model;
s103, taking a plurality of continuous key frames to judge whether the detected car target is moving, and if so, executing the next step;
and S104, calculating the distance between the vehicle target and the human target in the last frame and the subsequent frames of the plurality of continuous key frames, wherein if the distance meets a preset condition, the human-vehicle distance is safe, otherwise, the human-vehicle distance is unsafe.
In another aspect, an electronic device is provided, which includes a storage module including instructions loaded and executed by a processor, where the instructions, when executed, cause the processor to execute the above-mentioned storage scene human-vehicle safe distance identification method.
In yet another aspect, a computer readable storage medium is provided, which stores one or more programs, which when executed by a processor, implement a storage scenario human-vehicle safe distance identification method as described above.
The invention can accurately identify whether the distance between a person and a vehicle is safe or not in a warehousing operation scene under the condition of not needing additional manpower and additional equipment.
Drawings
The invention is described in detail below with reference to the following figures and detailed description:
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of the present invention.
Detailed Description
As shown in fig. 1, an embodiment of the present specification provides a storage scene human-vehicle safe distance identification method, including:
s101, periodically extracting key frames from the warehousing operation real-time monitoring video data.
In the present embodiment, the period of extracting the key frame is 1 frame per second.
S102, detecting human targets and vehicle targets in the key frames through a pre-trained target detection model.
Wherein, train the target detection model through the sample picture, the extraction process of sample picture includes:
firstly, collecting storage operation historical monitoring video data, then extracting key frames from the collected storage operation historical monitoring video data, and then cleaning all the extracted key frames, wherein the cleaning means that repeated pictures, pictures of a flower screen and pictures of a green screen are deleted, and a human target and a vehicle target are marked in each cleaned key frame, and the vehicle target is a motor vehicle target, a crane target, a forklift target and the like.
S103, taking a plurality of continuous key frames to judge whether the detected car target moves, and if so, executing the next step.
After the human target and the vehicle target in the keyframes are detected by the target detection model, if the human target and the vehicle target are detected, each target has one detection frame, based on which, the moving distance of the vehicle target in a plurality of consecutive keyframes is calculated according to the detection frame information (representing the position of the detection frame in the keyframes) of the vehicle target in a plurality of consecutive keyframes (such as 2 consecutive keyframes), and if the moving distance is greater than or equal to a threshold, the vehicle target is moving.
Taking 2 consecutive key frames as an example, the distance that the vehicle moves in 2 seconds at the normal operation moving speed in the warehousing operation site can be used as the threshold value.
And if the central point of any subsequent vehicle target frame of 2 continuous frames does not change in the moving state of the vehicle, modifying the moving state of the vehicle to be a static state, and after the static state, continuously judging whether the distance between the person and the vehicle is safe or not.
And S104, calculating the distance between the vehicle target and the human target in the last frame and the subsequent frames of the plurality of continuous key frames, wherein if the distance meets the preset condition, the human-vehicle distance is safe, otherwise, the human-vehicle distance is unsafe.
Some parameters of the multi-view camera may be used to calculate the distance between the car target and the person target in the video frame. However, the monocular camera lacks these parameters, so the distance between the car target and the human target in the video picture of the monocular camera cannot be calculated, in order to solve the problem, the length and the width of the storage operation field are measured in advance, and grid marks are set, for example, four corner points of the grid are marked, a square grid with the length and the width of 3 meters by 3 meters is used for partitioning, the square grid has the advantage that the later-stage calculation complexity can be reduced, and the rectangular grid can also be used. The key frame extracted in this way is a gridded picture.
Based on the gridded key frame, whether the human-vehicle distance is safe can be judged by using the grid where the human target is located and the grid where the vehicle target is located, see fig. 2:
a. determining a grid where the human target is located and a grid where the vehicle target is located:
because the camera is often arranged obliquely downwards, the grid where the lower limb part of the human target is located is used as the grid where the human target is located, and then, the angular point D which is closest to the lower limb part in four angular points (four angular points of a vehicle target detection frame) of the vehicle target is determined min Finally, the corner point D is defined min The grid where the vehicle target is located is used as the grid where the vehicle target is located, so that the judgment of the grid where the human target is located and the judgment of the grid where the vehicle target is located on the human-vehicle distance are more accurate.
In the present embodiment, as shown in fig. 2, the midpoint D at the lower 1/3 of the human target (at the lower 1/3 of the human target detection frame) is taken as 0 The lower limb portion of the human target is represented, although other points may be used to represent the lower limb portion of the human target.
b. If the grid where the human target is located is adjacent to the grid where the vehicle target is located, the human-vehicle distance is unsafe, and otherwise, the human-vehicle distance is safe.
In an actual scene, although the grid where the human target is located is adjacent to the grid where the vehicle target is located, the human target or the vehicle target may be located at the edge of the grid where the human target or the vehicle target is located, and therefore, it may be inaccurate to use only the adjacent grid as a basis for judging that the human-vehicle distance is unsafe, so when the grid where the human target is located is adjacent to the grid where the vehicle target is located, further judgment is performed:
a. the pixel distance d1 of the lower limb portion from the nearest corner point is calculated.
In this embodiment, D1 is D 0 And D min The pixel distance of (2).
b. If d1 is less than or equal to d2, the distance between the man and the vehicle is unsafe, otherwise, the distance between the man and the vehicle is safe.
If the grid where the human target is located is diagonally adjacent to the grid where the car target is located, d2 takes the length of the side of the human target in the up-down direction of the grid where the human target is located, if the grid where the human target is located is horizontally adjacent to the grid where the car target is located, d2 takes the length of the side of the human target in the left-right direction of the grid where the human target is located, and if the grid where the human target is located is vertically adjacent to the grid where the car target is located, d2 takes the length of the side of the human target in the up-down direction of the grid where the human target is located.
Based on the same inventive concept, an embodiment of the present specification further provides an electronic device, including a storage module, where the storage module includes instructions loaded and executed by a processor, and the instructions, when executed, cause the processor to perform the steps according to the various exemplary embodiments of the present invention described in the above section of the method for identifying a storage scene human-vehicle safe distance.
The memory module may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM) and/or a cache memory unit, and may further include a read only memory unit (ROM).
Based on the same inventive concept, embodiments of the present specification further provide a computer-readable storage medium storing one or more programs which, when executed by a processor, implement the steps according to various exemplary embodiments of the present invention described in the above section of the method for identifying a storage scene human-vehicle safe distance.
A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium include an electrical connection based on 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.
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, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
However, those skilled in the art should realize that the above embodiments are illustrative only and not limiting to the present invention, and that changes and modifications to the above described embodiments are intended to fall within the scope of the appended claims, provided they fall within the true spirit of the present invention.

Claims (13)

1. A storage scene human-vehicle safety distance identification method is characterized by comprising the following steps:
s101, periodically extracting key frames from warehousing operation real-time monitoring video data;
s102, detecting human targets and vehicle targets in the key frames through a pre-trained target detection model;
s103, taking a plurality of continuous key frames to judge whether the detected car target is moving, and if so, executing the next step;
and S104, calculating the distance between the vehicle target and the human target in the last frame and the subsequent frames of the plurality of continuous key frames, wherein if the distance meets a preset condition, the human-vehicle distance is safe, otherwise, the human-vehicle distance is unsafe.
2. The storage scene human-vehicle safe distance identification method according to claim 1, wherein the period of extracting the key frames is 1 frame per second.
3. The storage scene human-vehicle safe distance identification method according to claim 1, wherein the target detection model is trained through a sample picture, and the extraction process of the sample picture comprises the following steps:
collecting historical monitoring video data of warehousing operation;
extracting key frames from the warehousing operation historical monitoring video data;
and cleaning all the extracted key frames, and marking human targets and car targets in each cleaned key frame.
4. The storage scene human-vehicle safe distance identification method according to claim 3, wherein the cleaning the extracted key frames further comprises:
and deleting the repeated pictures, the pictures of the flower screen and the pictures of the green screen.
5. The method according to claim 2, wherein the determining whether the detected car target is moving by taking a plurality of consecutive key frames further comprises:
calculating the moving distance of the car target in the plurality of continuous key frames according to the detection frame information of the car target in the plurality of continuous key frames;
and if the moving distance is larger than or equal to the threshold value, the vehicle target moves.
6. The method according to claim 5, wherein the plurality of consecutive keyframes is 2 consecutive keyframes.
7. The storage scene human-vehicle safety distance identification method according to claim 1, wherein a grid mark is preset on a storage operation site, and the key frame is a grid picture.
8. The storage scene human-vehicle safe distance identification method according to claim 7, wherein the S104 further comprises:
determining a grid where the human target is located and a grid where the vehicle target is located;
and if the grid where the human target is located is adjacent to the grid where the vehicle target is located, the human-vehicle distance is unsafe, otherwise, the human-vehicle distance is safe.
9. The method according to claim 8, wherein the determining of the grid where the human target is located and the grid where the car target is located further comprises:
taking the grid where the lower limb part of the human target is located as the grid where the human target is located;
determining the corner point closest to the lower limb part in the four corner points of the vehicle target;
and taking the grid where the corner point closest to the vehicle target is located as the grid where the vehicle target is located.
10. The method of claim 9, wherein the lower limb portion of the human target is represented by a midpoint at 1/3 below the human target.
11. The method according to claim 10, wherein if the grid where the human target is located is adjacent to the grid where the car target is located, the human-vehicle distance is unsafe, further comprising:
calculating the pixel distance d1 between the lower limb part and the corner point closest to the lower limb part;
if d1 is not more than d2, the distance between the people and the vehicle is unsafe, otherwise, the distance between the people and the vehicle is safe;
if the grid where the human target is located is diagonally adjacent to the grid where the car target is located, d2 takes the length of the.
12. An electronic device comprising a storage module comprising instructions loaded and executed by a processor, the instructions when executed cause the processor to perform a storage scenario human-vehicle safe distance identification method according to any one of claims 1-11.
13. A computer readable storage medium storing one or more programs, which when executed by a processor, implement a storage scenario human-vehicle safe distance identification method of any one of claims 1-11.
CN202210542349.2A 2022-05-17 2022-05-17 Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium Pending CN114882435A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210542349.2A CN114882435A (en) 2022-05-17 2022-05-17 Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210542349.2A CN114882435A (en) 2022-05-17 2022-05-17 Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114882435A true CN114882435A (en) 2022-08-09

Family

ID=82676149

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210542349.2A Pending CN114882435A (en) 2022-05-17 2022-05-17 Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114882435A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117854211A (en) * 2024-03-07 2024-04-09 南京奥看信息科技有限公司 Target object identification method and device based on intelligent vision

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117854211A (en) * 2024-03-07 2024-04-09 南京奥看信息科技有限公司 Target object identification method and device based on intelligent vision
CN117854211B (en) * 2024-03-07 2024-05-28 南京奥看信息科技有限公司 Target object identification method and device based on intelligent vision

Similar Documents

Publication Publication Date Title
CN103927762B (en) Target vehicle automatic tracking method and device
CN103745484B (en) Worker target safety early-warning method for hot-line work on electric power facility
US20230005176A1 (en) Throwing position acquisition method and apparatus, computer device and storage medium
CN107316462A (en) A kind of flow statistical method and device
CN113240682B (en) Overturn-preventing construction driving map generation method and system for crawler crane
CN112539704A (en) Method for measuring distance between hidden danger in transmission line channel and lead
CN115326661B (en) Atmospheric environment-based monitoring method and system and readable storage medium
CN112383756B (en) Video monitoring alarm processing method and device
CN112633722A (en) Vehicle-mounted road safety risk assessment system and method
CN114882435A (en) Storage scene human-vehicle safety distance identification method, electronic equipment and storage medium
CN114972490B (en) Automatic data labeling method, device, equipment and storage medium
CN112764013A (en) Method, device and equipment for testing automatic driving vehicle perception system and storage medium
CN116110012A (en) Dangerous violation identification method and system for intelligent construction site
KR20130133596A (en) Method and apparatus for measuring slope of poles
CN115271612A (en) Logistics park safety monitoring method, device, equipment and storage medium
CN115139303A (en) Grid well lid detection method, device, equipment and storage medium
CN115272656A (en) Environment detection alarm method and device, computer equipment and storage medium
CN116358528A (en) Map updating method, map updating device, self-mobile device and storage medium
CN114842223A (en) Method and device for identifying warehouse entry and exit and computer readable storage medium
CN115240101A (en) Medical sample forwarding and monitoring system based on scene analysis
CN115171220A (en) Abnormal traffic early warning method and device and electronic equipment
CN114596706A (en) Detection method and device of roadside sensing system, electronic equipment and roadside equipment
CN112686162A (en) Method, device, equipment and storage medium for detecting clean state of warehouse environment
CN112861701A (en) Illegal parking identification method and device, electronic equipment and computer readable medium
CN102724397A (en) Name card automatic detection method and device thereof

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