CN111604922A - Supermarket shelf rate inspection robot based on machine vision target recognition technology - Google Patents
Supermarket shelf rate inspection robot based on machine vision target recognition technology Download PDFInfo
- Publication number
- CN111604922A CN111604922A CN202010531864.1A CN202010531864A CN111604922A CN 111604922 A CN111604922 A CN 111604922A CN 202010531864 A CN202010531864 A CN 202010531864A CN 111604922 A CN111604922 A CN 111604922A
- Authority
- CN
- China
- Prior art keywords
- threaded rod
- lifting platform
- camera
- machine vision
- shelf
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 19
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000003028 elevating effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/023—Optical sensing devices including video camera means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J5/00—Manipulators mounted on wheels or on carriages
- B25J5/007—Manipulators mounted on wheels or on carriages mounted on wheels
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Warehouses Or Storage Devices (AREA)
Abstract
The invention discloses a supermarket shelf-life inspection robot based on a machine vision target recognition technology, which comprises a camera, a lifting device, a graphic calculation card, a control module and a wheeled trolley, wherein the lifting device is vertically arranged on the wheeled trolley, the lifting device comprises a lifting platform, two parallel slide rails and a threaded rod, the lower part of the threaded rod is arranged on a stepping motor through a coupler, the lifting platform can vertically slide along the slide rails under the rotation driving of the threaded rod, the camera and the graphic calculation card are arranged on the lifting platform, the camera acquires images, the figure calculating card identifies target commodities on the first row surface of the goods shelf through a machine vision algorithm and calculates the goods shelf rate, the shell of the wheeled trolley is circular, a control module and a network communication module are arranged in the wheeled trolley, three wheels are arranged at the bottom of the wheeled trolley, the network communication module sends the calculation result and the image to the server in real time when the vehicle walks and turns under the driving of the driving motor. The device can realize automatic calculation and report of the supermarket shelf availability, and compared with manual inspection, the device has the advantages of lower cost and more reliable result.
Description
Technical Field
The invention relates to the field of inspection robots, in particular to a supermarket shelf rate inspection robot based on a machine vision target recognition technology.
Background
The supermarket shelf availability ratio refers to the display condition of a specific commodity on the first row of shelves of a supermarket or a store, and is one of important indexes for determining commodity sales volume. Daily statistics on the shelf-loading rate of each store is an important link for the management of the sales process of manufacturers. The traditional inspection of the shelf-on rate is completed manually, and manufacturers send professional inspectors to go to each supermarket store every day, and record and photograph the shelf-on rate. However, the cost of manual inspection is high, and meanwhile, the possibility of people being lazy and falsified exists.
With the development of the robot technology and the machine vision technology, the inspection and statistics of the racking rate can be completed by adopting the robot. The existing inspection robot has advantages in the fields of electric power, medical treatment, security and the like. However, no robot product facing the supermarket shelf-life statistics exists in the market at present.
Disclosure of Invention
The invention provides a patrol robot which can automatically carry out supermarket shelf rate patrol and report based on a machine vision target identification technology aiming at the defects of a manual supermarket shelf rate patrol scheme.
In order to achieve the purpose, the invention adopts the following technical scheme:
a supermarket shelf-climbing inspection robot based on a machine vision target recognition technology comprises a camera, a lifting device, a graph calculation card, a control module and a wheel type trolley.
Furthermore, elevating gear includes lift platform, two parallel slide rails and a threaded rod, and the threaded rod lower part is installed on step motor through the shaft joint, and elevating gear is vertical to be installed on wheeled dolly.
Furthermore, the lifting platform is a round-angle triangular plate, two round holes and a threaded hole are formed in the round-angle triangular plate and respectively penetrate through the sliding rail and the threaded rod, the threaded rod is driven by the stepping motor to rotate, the lifting platform is pushed to vertically slide along the sliding rail, and the camera and the graphic calculation card are installed on the lifting platform.
Furthermore, the camera can move up and down through the lifting device to collect images, the graphic calculation card identifies target commodities on the first row of the goods shelf through a machine vision algorithm, and the calculation shelf rate is calculated.
Furthermore, the shell of the wheeled trolley is circular, a control module and a network communication module are arranged in the shell, three wheels are installed at the bottom of the shell, the wheeled trolley walks and turns under the driving of a driving motor, and the network communication module sends a calculation result and an image to a server in real time.
Further, the machine vision algorithm is to identify, count and mark the position of a specified commodity in the acquired image by using a trained regional convolutional neural network (R-CNN series algorithm), thereby calculating the commodity shelf life.
The invention has the beneficial effects that:
1. compared with the conventional manual supermarket inspection, the supermarket inspection robot provided by the invention can realize automatic inspection of the supermarket shelf availability, and has the advantages of reliable data, avoidance of falsification and low cost.
2. The inspection robot of each supermarket can sign a contract with a plurality of companies, and therefore the apportioned cost is further reduced.
Drawings
FIG. 1 is a schematic view of a climbing-over type obstacle crossing optical cable inspection robot provided by the invention;
FIG. 2 is a detailed view of the fixing position between the lifting device and the wheeled cart
FIG. 3 is a schematic view of the elevating platform, the camera and the graphic calculating card
In the figure: 1. the system comprises a camera, a lifting device, a graphic calculation card, a control module, a wheel type trolley, a lifting platform, a sliding rail, a threaded rod, a coupler, a stepping motor, a network communication module, a wheel, a driving motor, a server, a round hole and a threaded hole, wherein the lifting device comprises a camera 2, the graphic calculation card 3, the control module 4, the wheel type trolley 5, the lifting platform 6, the sliding rail 7, the threaded rod 8, the coupler 9, the stepping motor 10, the network communication module 11, the wheel 12.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1, a supermarket shelf-loading rate inspection robot based on a machine vision target recognition technology comprises a camera 1, a lifting device 2, a graph calculation card 3, a control module 4 and a wheeled trolley 5, wherein the lifting device 2 is vertically installed on the wheeled trolley 5, the lifting device 2 comprises a lifting platform 6, two parallel sliding rails 7 and a threaded rod 8, the camera 1 and the graph calculation card 3 are installed on the lifting platform 6, the camera 1 collects images, the graph calculation card 3 recognizes target commodities on a first row of a shelf through a machine vision algorithm and calculates the shelf loading rate, the shell of the wheeled trolley 5 is circular, the control module 4 and a network communication module 11 are arranged in the shell, three wheels 12 are installed at the bottom of the wheeled trolley, the wheeled trolley walks and turns under the driving of a driving motor 13, and the network communication module 11 sends calculation results and images to a server 14 in real time.
Referring to fig. 2, the lifting device 2 structurally comprises a lifting platform 6, a threaded rod 8 and two parallel slide rails 7, wherein the lower part of the threaded rod 8 is mounted on a stepping motor 10 through a coupling 9 and is vertically mounted on the top of the wheeled trolley 5 together with the slide rails 7.
Referring to fig. 3, the lifting platform 6 is a rounded triangle plate, and has two round holes 15 and a threaded hole 16, which pass through the slide rail 7 and the threaded rod 8, respectively, the threaded rod 8 is driven by the stepping motor 10 to rotate, so as to push the lifting platform 6 to vertically slide along the slide rail 7, and the lifting platform 6 is provided with the camera 1 and the graphic calculation card 3. The camera 1 collects images, and the graphic calculation card 3 identifies target commodities on the first row of the shelves through a machine vision algorithm and calculates the shelf rate.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A supermarket shelf-climbing inspection robot based on a machine vision target recognition technology comprises a camera (1), a lifting device (2), a graph calculation card (3), a control module (4) and a wheel type trolley (5), wherein the lifting device (2) is vertically installed on the wheel type trolley (5), the lifting device (2) comprises a lifting platform (6), two parallel sliding rails (7) and a threaded rod (8), the lower part of the threaded rod (8) is installed on a stepping motor (10) through a coupling (9), the lifting platform (6) can vertically slide along the sliding rails (7) under the rotary driving of the threaded rod (8), the lifting platform (6) is provided with the camera (1) and the graph calculation card (3), the camera (1) collects images, the graph calculation card (3) recognizes target commodities on a first row face of a shelf through a machine vision algorithm and calculates the shelf rate, the shell of the wheeled trolley (5) is circular, a control module (4) and a network communication module (11) are arranged in the shell, three wheels (12) are installed at the bottom of the wheeled trolley and driven by a driving motor (13) to walk and turn, and the network communication module (11) sends a calculation result and an image to a server (14) in real time.
2. The supermarket shelf rate inspection robot according to claim 1, characterized in that: the robot walks according to a planned path by using a bottom wheeled trolley (5), the camera (1) can move up and down through the lifting device (2) to collect images, the graphic calculation card identifies target commodities on the first row of the goods shelf through a machine vision algorithm, the calculation result and the images are sent to the server (14) in real time through the network communication module (11) after the calculation result and the images are calculated.
3. Lifting device (2) according to claim 1, characterized in that: the structure comprises a lifting platform (6), a threaded rod (8) and two parallel sliding rails (7), wherein the lower part of the threaded rod (8) is arranged on a stepping motor (10) through a coupling (9) and is vertically arranged on the top of a wheel type trolley (5) together with the sliding rails (7); lifting platform (6) are fillet triangle-shaped board, have two round holes (15) and a screw hole (16) on, pass slide rail (7) and threaded rod (8) respectively, and threaded rod (8) are rotatory under step motor (10) drive, promote lifting platform (6) along the vertical slip of slide rail (7), install camera (1), figure calculation card (3) on lifting platform (6).
4. The machine vision algorithm of claim 1, wherein the commodity rate is calculated by identifying, counting and marking the positions of the specified commodities in the acquired images by using a trained regional convolutional neural network (R-CNN series algorithm).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531864.1A CN111604922A (en) | 2020-06-11 | 2020-06-11 | Supermarket shelf rate inspection robot based on machine vision target recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531864.1A CN111604922A (en) | 2020-06-11 | 2020-06-11 | Supermarket shelf rate inspection robot based on machine vision target recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111604922A true CN111604922A (en) | 2020-09-01 |
Family
ID=72194723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010531864.1A Pending CN111604922A (en) | 2020-06-11 | 2020-06-11 | Supermarket shelf rate inspection robot based on machine vision target recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111604922A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109760008A (en) * | 2019-01-29 | 2019-05-17 | 丽水学院 | One kind replenishes robot |
| US20200068126A1 (en) * | 2018-08-24 | 2020-02-27 | Bossa Nova Robotics Ip, Inc. | Shelf-Viewing Camera With Multiple Focus Depths |
| WO2020048376A1 (en) * | 2018-09-07 | 2020-03-12 | 杭州海康威视数字技术股份有限公司 | Shelf analysis method and apparatus, system, and electronic device |
| CN210680518U (en) * | 2019-09-30 | 2020-06-05 | 韶关学院 | Large supermarket cloud shopping machine device |
| CN213674137U (en) * | 2020-06-11 | 2021-07-13 | 合肥立木科技有限责任公司 | Supermarket shelf rate inspection robot based on machine vision target recognition technology |
-
2020
- 2020-06-11 CN CN202010531864.1A patent/CN111604922A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200068126A1 (en) * | 2018-08-24 | 2020-02-27 | Bossa Nova Robotics Ip, Inc. | Shelf-Viewing Camera With Multiple Focus Depths |
| WO2020048376A1 (en) * | 2018-09-07 | 2020-03-12 | 杭州海康威视数字技术股份有限公司 | Shelf analysis method and apparatus, system, and electronic device |
| CN109760008A (en) * | 2019-01-29 | 2019-05-17 | 丽水学院 | One kind replenishes robot |
| CN210680518U (en) * | 2019-09-30 | 2020-06-05 | 韶关学院 | Large supermarket cloud shopping machine device |
| CN213674137U (en) * | 2020-06-11 | 2021-07-13 | 合肥立木科技有限责任公司 | Supermarket shelf rate inspection robot based on machine vision target recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108960737B (en) | Automatic warehouse inspection system and method based on machine vision | |
| CN213674137U (en) | Supermarket shelf rate inspection robot based on machine vision target recognition technology | |
| CN105522583B (en) | A kind of self-action books based on RFID technique are intelligently made an inventory restocking robot | |
| CN109636272B (en) | Intelligent detection device and detection method for goods shortage of goods shelf | |
| CN106044645A (en) | Cargo pallet accessing system capable of positioning based on QR code and cargo pallet accessing method capable of positioning based on QR code | |
| CN211197464U (en) | Carrying device and carrying robot with same | |
| WO2022105360A1 (en) | Storage and retrieval management guiding system for steel pipe warehouse, and ground rail type inspection robot | |
| CN111881894A (en) | Method, system, equipment and storage medium for collecting goods selling information of container | |
| CN103630221A (en) | Method for remotely monitoring vehicle weighing cheating by using video analyzing | |
| CN111620014A (en) | Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV | |
| CN112651694A (en) | Intelligent management system and intelligent management method for warehouse goods | |
| CN107037815A (en) | Intelligent carriage logistics system | |
| CN111604922A (en) | Supermarket shelf rate inspection robot based on machine vision target recognition technology | |
| CN111598514A (en) | Intelligent warehouse management system and method based on Internet of things technology | |
| CN208466527U (en) | A kind of three-dimensional sorting system based on intelligent shuttle | |
| CN210682019U (en) | Intelligent-oriented infrared digital panoramic system and warehouse thereof | |
| CN114162555A (en) | Intelligent carrying robot with visual tracking function and implementation method thereof | |
| CN206848813U (en) | Intelligent carriage logistics system | |
| CN215796173U (en) | Seat part storage sorting device | |
| CN214187213U (en) | Machine station inspection robot system | |
| CN210162601U (en) | Warehouse cargo transportation robot | |
| CN210155739U (en) | Unmanned automatic weighing system applied to smart park | |
| CN217463803U (en) | Robot is patrolled and examined in figure collection | |
| CN210806532U (en) | Inspection device for power transformation and distribution equipment | |
| CN111453282A (en) | Stable and efficient intelligent electronic commerce distribution shelf |
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 |