Intelligent tracking sorting trolley for machine vision

Abstract

The utility model discloses an intelligent tracking sorting trolley for machine vision, which relates to the technical field of intelligent sorting trolleys and comprises a frame body, a six-axis attitude sensor is arranged in the frame body, two Mecanum wheels are rotatably mounted at two side end parts of the frame body, and the two Mecanum wheels are rotatably mounted on two side end parts of the frame body. A mounting plate is movably mounted at the side end of the frame body, a supporting plate is slidably mounted at the top end of the mounting plate, a rotating shaft at the side end of the frame body is driven by a motor to rotate, the rotating shaft is in butt joint with a connecting shaft and drives the connecting shaft to rotate, and meanwhile the tail end of the connecting shaft is connected with a threaded rod through a bevel gear. The rotating threaded rod generates thrust on the supporting plate, so that the supporting plate vertically ascends and descends in the mounting plate, meanwhile, movement of the supporting plate drives the two connecting lines to stretch, the height is adjusted through the two camera assemblies, different shooting view angles can be provided according to different heights, and a more appropriate depression angle or elevation angle can be obtained by adjusting the height of the camera assemblies.

Description

TECHNICAL FIELD

[0001] The utility model relates to intelligent sorting trolley technical field, especially a kind of intelligent tracking sorting trolley for machine vision. BACKGROUND

[0002] With the rapid development of modern science and technology, people's demand for intelligent is increasing day by day, intelligent vehicle is a comprehensive system integrating environment perception, planning and decision, multi-level auxiliary driving and other functions, which concentrates the use of computer, modern sensing, information fusion, communication, artificial intelligence and automatic control technologies, and is a typical high-tech complex.In practical applications, edible agricultural products traceability precision scanning equipment usually needs the following technologies:

[0003] 1. Car body structure, used to support the weight and load of the entire trolley;

[0004] 2. Drive system, provides power for the trolley;

[0005] 3. Tracking system, used to detect markers or lines on the trolley driving path;

[0006] 4. Control system, usually uses microprocessor or single-chip microcomputer, responsible for the control and coordination of the entire trolley;

[0007] Usually uses photoelectric sensor, infrared sensor or camera as tracking sensor, when the sensor detects tracking line, corresponding electrical signal will be generated, the control system of the trolley processes and analyzes these signals to determine the position and direction of the trolley relative to the tracking line, and adjusts the speed and direction of the drive motor of the trolley according to the feedback information of the sensor, so that the trolley can travel along the tracking line;

[0008] The camera can obtain the boundary information of the road and identify the position of the road centerline relative to the vehicle body during the operation of the vehicle model, and correct the position of the vehicle, first, the transmission of data has delay, and only through the mainboard to process data, which leads to the processing of data is not timely, and affects the speed of tracking recognition and passing of the trolley. UTILITY MODEL CONTENT

[0009] (I) Technical problem solved

[0010] In view of the shortcomings of the prior art, the utility model provides an intelligent tracking sorting trolley for machine vision, which solves the technical problem that the transmission of data has delay, and only through the mainboard to process data, which leads to the processing of data is not timely, and affects the speed of tracking recognition and passing of the trolley.

[0011] (II) Technical scheme

[0012] To achieve the above purpose, the utility model is realized by the following technical scheme:

[0013] An intelligent tracking and sorting vehicle for machine vision includes a frame body, a six-axis attitude sensor is installed inside the frame body, two Mecanum wheels are rotatably mounted on two side ends of the frame body, a mounting plate is movably mounted on the side ends of the frame body, a support plate is slidably mounted on the top of the mounting plate, and two camera components are provided on the side ends of the support plate.

[0014] Preferably: two docking frames are fixedly installed on the side end of the mounting plate; a connecting shaft is rotatably installed on the side end of the mounting plate; a threaded rod is rotatably installed on the top end of the mounting plate; two connecting lines are fixedly installed on the bottom end of the support plate; guide strips are fixedly installed on both side ends of the support plate; two bayonets are installed on the side end of the frame body to dock with the docking frames; a drive rod is rotatably installed on the side end of the frame body to dock with the connecting shaft; a three-axis accelerometer and a three-axis angular velocity meter are installed inside the six-axis attitude sensor; the required attitude angle can be calculated by merging the data of the two using complementary filtering and quaternion fusion algorithms; and a drive motor, power supply, and control motherboard are installed inside the frame body.

[0015] (III) Beneficial Effects

[0016] 1. Typically, camera components are used, with two camera components installed on the side end of the support plate. The two camera components have different tilt height angles. The camera components can detect specific marking lines, colors, or other features on the ground. When the camera component detects the tracking line, it transmits a signal back to the main circuit board. After obtaining the left and right boundaries of the track using the eight-neighborhood algorithm, the center position of the track can be obtained through the coordinates of the left and right boundaries. This is used to correct the position of the vehicle body, realize tracking, and achieve closed-loop control using the Pid algorithm. By integrating multiple methods and innovating data processing methods, the vehicle can be guaranteed to run quickly and track effectively, thus achieving better intelligent tracking and sorting performance.

[0017] 2. The side end shaft of the frame body is driven by a motor to rotate. The shaft is connected to the connecting shaft, which drives the connecting shaft to rotate. At the same time, the end of the connecting shaft is connected to the threaded rod through a bevel gear. The rotating threaded rod generates a thrust on the support plate, allowing the support plate to rise and fall vertically inside the mounting plate. The movement of the support plate also causes the two connecting lines to stretch. The height can be adjusted by two camera components. Different heights can provide different shooting angles. Adjusting the height of the camera components can obtain a more suitable downward or upward angle. Attached Figure Description

[0018] The above description is only an overview of the technical solution of this utility model. In order to better understand the technical means of this utility model and to implement it in accordance with the contents of the specification, the preferred embodiments of this utility model are described in detail below with reference to the accompanying drawings.

[0019] Figure 1 It is the structural diagram of the frame body of the utility model;

[0020] Figure 2 It is the structural diagram of the mounting plate of the utility model;

[0021] Figure 3 It is the structural diagram of the support plate of the utility model;

[0022] Figure 4 It is the structural diagram of the camera assembly of the utility model;

[0023] Figure 5 It is the control system diagram of the utility model;

[0024] Figure 6 It is the equipment principle diagram of the utility model.

[0025] Legend: 11, frame body; 12, Mecanum wheel; 13, mounting plate; 14, support plate; 15, camera assembly; 16, six-axis attitude sensor; 17, threaded rod; 18, connecting shaft; 19, butt joint frame; 21, connecting line; 22, guide bar. DETAILED DESCRIPTION

[0026] The embodiment of the application provides an intelligent tracking and sorting trolley for machine vision, effectively solves the problem of data transmission delay, and only processes data through the mainboard, so that the data processing is not timely, the tracking and recognition speed of the trolley is affected, usually adopts a camera assembly, and two camera assemblies are installed at the side ends of the support plate, the tilt angles of the two camera assemblies are different, the camera assembly can detect specific mark lines, colors or other features on the ground, when the camera assembly detects the tracking line, signals are transmitted to the circuit mainboard, after the left and right boundaries of the track are obtained by using the eight-neighborhood algorithm, the center position of the track can be obtained through the left and right boundary coordinates, so as to correct the position of the trolley body, realize tracking, and realize the intelligent tracking and sorting effect of the trolley through Pid algorithm closed-loop control, fusion of multiple methods, innovative data processing mode, and guaranteeing the fast tracking operation of the trolley.

[0027] EMBODIMENT

[0028] As Figures 1-6 shown, the technical scheme in the embodiment of the application effectively solves the technical problem that data transmission is delayed and only data processing is performed through the mainboard, so that the data processing is not timely and the tracking and recognition speed of the trolley is affected, and the overall idea is as follows:

[0029] In view of the problems in the prior art, the utility model provides a kind of intelligent tracking sorting trolley for machine vision, including car body 11, the inside of car body 11 is provided with six-axis attitude sensor 16, two mecanum wheels 12 are rotatably installed in the both side ends of car body 11, mounting plate 13 is movably installed in the side end of car body 11, support plate 14 is slidably installed in the top end of mounting plate 13, two camera assemblies 15 are provided in the side end of support plate 14, camera assembly 15 is generally used, and two camera assemblies 15 are installed in the side end of support plate 14, the inclination of two camera assemblies 15 is different, camera assembly 15 can detect specific mark line, color or other features on ground, when camera assembly 15 detects tracking line, signal is transmitted to circuit mainboard.

[0030] The side end of mounting plate 13 is fixedly installed with two docking frames 19, the side end of mounting plate 13 is rotatably installed with connecting shaft 18, the top end of mounting plate 13 is rotatably installed with threaded rod 17, the bottom end of support plate 14 is fixedly installed with two connecting lines 21, the both side ends of support plate 14 are fixedly installed with guide strip 22, the side end of car body 11 is installed with two sockets and is docked with docking frame 19, the side end of car body 11 is rotatably installed with driving rod and is docked with connecting shaft 18, by rotating the bolt of the side end of mounting plate 13, the fixation of mounting plate 13 is released, by pulling mounting plate 13, mounting plate 13 drives docking frame 19 to move, docking frame 19 and the socket of the side end of car body 11 slide friction, docking frame 19 leaves the side end of car body 11, simultaneously, mounting plate 13 drives connecting shaft 18 and the shaft of the side end of car body 11 to disconnect, by moving mounting plate 13, mounting plate 13 and car body 11 are modularized, each module can be independently maintained and upgraded.

[0031] Three-axis accelerometer and three-axis angular velocity meter are installed in the inside of six-axis attitude sensor 16, complementary filtering and quaternion fusion algorithm are used to merge the data of both, that is, the required attitude angle can be calculated, driving motor, power supply and control mainboard are installed in the inside of car body 11.

[0032] Working principle:

[0033] First, usually with camera assembly 15, and in the side end of the support plate 14 is installed with two camera assembly 15, two camera assembly 15 different angle of inclination pair high, camera assembly 15 can detect the ground on the specific mark line, color or other characteristics, when camera assembly 15 detects the tracking line, back to the signal to the circuit board, using eight neighborhood algorithm, for finding the boundary point in the image, the image find the first non zero pixel point, then this point is a boundary point, clockwise search the first non zero pixel point encountered in the eight neighborhood of the point, make this point as the starting point, then clockwise search in the neighborhood, the starting point is the point just reached the previous zero point, using eight neighborhood algorithm to obtain the left and right boundary of the track, then the left and right boundary coordinates can be used to obtain the track center position, so as to correct the vehicle position, realize tracking, at the same time, the main board of the device uses OpenArt mini to run neural network model, which uses the existing mobilenet_v2 model in EIQ, the resolution is set to 96x96, and the weights pre trained based on ImageNet dataset are used for transfer learning.

[0034] At the same time, the inside of the vehicle frame body 11 is installed with a six-axis attitude sensor 16, which includes a three-axis accelerometer and a three-axis angular velocity meter. The data of the two is combined by using complementary filtering and quaternion fusion algorithm, so as to solve the required attitude. Through Pid algorithm closed loop control, the control parameters are independent of each other, and the selection of parameters is relatively simple, etc. In the closed loop of intelligent vehicle, pid algorithm plays a key role, which can ensure that the vehicle driving speed is executed according to the target speed set by you, and improves the stability of vehicle driving.

[0035] Second, through the motor drive multiple Mecanum wheels 12 to rotate, push the vehicle frame body 11 to move, the rim of the Mecanum wheel 12 is obliquely distributed with many small rollers, so the wheel can slide horizontally, the generatrix of the small roller is very special, when the wheel rotates around the fixed hub shaft, the envelope of each small roller is cylindrical surface, so the wheel can continuously roll forward, the structure is compact, and the omnidirectional movement function can be realized more flexibly and conveniently. At the same time, the side end of the vehicle frame body 11 is driven to rotate by the motor, the rotating shaft is connected with the connecting shaft 18, the connecting shaft 18 is driven to rotate, the end of the connecting shaft 18 is connected with the threaded rod 17 through the bevel gear, the threaded rod 17 is pushed to rotate in the inside of the mounting plate 13, the rotating threaded rod 17 generates a pushing force on the support plate 14, the side end of the support plate 14 is installed with two guide strips 22, the movement of the support plate 14 is guided, so that the support plate 14 can vertically ascend and descend in the inside of the mounting plate 13, the movement of the support plate 14 drives the two connecting lines 21 to stretch, the height of the two camera assemblies 15 is adjusted, different height can provide different shooting angle, adjusting the height of the camera assembly 15 can obtain more appropriate angle of depression or angle of elevation.

[0036] At the same time, the fixing of the mounting plate 13 is released by rotating the bolts of the side end of the mounting plate 13, the mounting plate 13 is pulled to move the docking frame 19, the docking frame 19 slides and rubs with the side end of the frame body 11, the docking frame 19 leaves the side end of the frame body 11, and the mounting plate 13 disconnects the connecting shaft 18 from the rotating shaft of the side end of the frame body 11, the mounting plate 13 is modularized with the frame body 11 by moving the mounting plate 13, each module can be independently maintained and upgraded, and the whole system is not greatly affected. This makes the maintenance work more flexible and convenient, and reduces the maintenance cost.

[0037] Finally, it should be noted that: obviously, the above examples are only examples for clearly illustrating the utility model, and are not limited to the implementation. For ordinary skilled in the art, on the basis of the above description, other different forms of changes or variations can be made. Here, it is not necessary and impossible to enumerate all the implementation. The obvious changes or variations derived therefrom are still within the protection scope of the utility model.

Claims

1. An intelligent tracking sorting trolley for machine vision, comprising a trolley body (11), characterized in that, The inside of the frame body (11) is provided with a six-axis attitude sensor (16), both side ends of the frame body (11) are rotatably provided with two Mecanum wheels (12), the side end of the frame body (11) is movably provided with a mounting plate (13), the top end of the mounting plate (13) is slidably provided with a support plate (14), and both side ends of the support plate (14) are provided with two camera assemblies (15).

2. The intelligent tracking and sorting trolley for machine vision according to claim 1, wherein, The side end of the mounting plate (13) is fixedly provided with two butt joint frames (19), and the side end of the mounting plate (13) is rotatably provided with a connecting shaft (18).

3. The intelligent tracking and sorting trolley for machine vision of claim 1, wherein, The top end of the mounting plate (13) is rotatably provided with a threaded rod (17).

4. The intelligent tracking and sorting trolley for machine vision of claim 1, wherein, The bottom end of the support plate (14) is fixedly provided with two connecting lines (21).

5. The intelligent tracking and sorting trolley for machine vision of claim 1, wherein, Both side ends of the support plate (14) are fixedly provided with guide strips (22).

6. An intelligent tracking and sorting trolley for machine vision as claimed in claim 1 wherein, Both side ends of the frame body (11) are provided with two bayonets which are butt jointed with the butt joint frames (19), and the side end of the frame body (11) is rotatably provided with a driving rod which is butt jointed with the connecting shaft (18).

7. An intelligent tracking and sorting trolley for machine vision as claimed in claim 1 wherein, The inside of the six-axis attitude sensor (16) is provided with a three-axis accelerometer and a three-axis angular velocity meter, the data of both is combined by using a complementary filtering and a quaternion fusion algorithm, so that the required attitude angle can be solved.

8. The intelligent tracking and sorting trolley for machine vision of claim 1, wherein, The inside of the frame body (11) is provided with a driving motor, a power supply and a control mainboard.

Images