Visual recognition-based cargo box size detection mechanism

Abstract

The utility model relates to the technical field of warehouse logistics detection equipment, concretely relates to the size detection mechanism of case based on visual identification, including support frame, the top of support frame is provided with the conveyer belt for conveying case, the top of conveyer belt is provided with two mutually symmetrical and is used for guiding the center part of case along the forward conveying of conveyer belt's guide plate, the guide end of guide plate is fixedly installed with the inclined guide plate, the fixed mounting of support frame has the U -shaped frame of the outside of conveyer belt, the top board body of U -shaped frame is fixedly installed with the cylinder, the telescopic axle end of cylinder is detachably installed with the inner frame body of the outside of conveyer belt, the inside of every side board body of inner frame body is fixedly installed with high -definition industrial camera and light source, and the side of support frame is provided with the data processing host computer for carrying out data processing operation. The utility model has the advantage of guiding when conveying case, is favorable for guaranteeing case anti -offset type conveying, is favorable for improving subsequent detection accuracy.

Description

Technical Field

[0001] This utility model relates to the field of warehousing and logistics testing equipment technology, and more specifically, to a cargo box size detection mechanism based on visual recognition. Background Technology

[0002] Cargo box dimensions are the core basis for warehouse sorting, stacking and space allocation. The accuracy of its detection directly affects the adaptability and efficiency of subsequent operations. Traditional manual inspection relies on tools such as tape measures, and the inspection of a single box takes more than 10 seconds. Moreover, it is prone to data deviation due to human error, and cannot meet the high-speed sorting needs of thousands of pieces per hour. To achieve efficient inspection, visual recognition-based cargo box size detection devices are commonly used to replace manual inspection. For example, the utility model patent with authorization announcement number CN217766049U discloses a robot visual recognition inspection device, which relates to the field of visual inspection technology. It includes a positioning base plate, a clamping mechanism installed on the top of the positioning base plate, an inspection item installed on one side of the clamping mechanism, two fixed frames fixedly installed on the top of the positioning base plate, an adjustment mechanism installed between the two fixed frames, an installation plate fixedly installed at the bottom of the adjustment mechanism, and an inspection head fixedly installed at the bottom of the installation plate. Through the cooperation of a second servo motor, a positive and negative screw, a first threaded block, an L-shaped plate, a telescopic frame, and a clamping plate, it can clamp inspection items of different sizes and prevent the inspection items from shifting during transportation. This not only improves the flexibility of the device but also, by using the cooperation of the first servo motor, the second servo motor, and the electric slide, it can detect different positions of the inspection items, thereby improving the inspection efficiency. While the aforementioned technical solutions have their advantages, most current mechanisms for detecting cargo box dimensions using multiple cameras still have some shortcomings. For example, most conveyor belts lack corresponding guiding components, causing the cargo box to shift position on the conveyor belt and fail to align with the center. This further results in the cargo box not being fully captured by multiple cameras, creating blind spots due to obstructed views and affecting detection efficiency. Therefore, we propose a vision-based cargo box dimension detection mechanism. Utility Model Content

[0003] The purpose of this invention is to provide a visual recognition-based cargo box size detection mechanism to address the deficiencies mentioned in the background art.

[0004] To achieve the above objectives, this utility model provides the following technical solution: The visual recognition-based cargo box size detection mechanism includes a support frame. A conveyor belt for transporting cargo boxes is installed above the support frame. Two symmetrical guide plates are installed above the conveyor belt to guide the cargo boxes forward along the center of the conveyor belt. An inclined guide plate is fixedly installed at the guide end of the guide plate. A U-shaped frame is fixedly installed on the support frame and fitted outside the conveyor belt. A cylinder is fixedly installed on the top plate of the U-shaped frame. An inner frame fitted on the conveyor belt is detachably installed at the end of the telescopic shaft of the cylinder. A high-definition industrial camera and a light source are fixedly installed on the inner side of each side plate of the inner frame. A data processing host for data processing operations is installed on one side of the support frame.

[0005] Preferably, two sets of symmetrical support beams are fixedly installed on the upper surface of the support frame, the conveyor belt is rotatably connected to the support beams via a rotating shaft, and the conveyor belt is driven to rotate by a stepper motor.

[0006] Preferably, the inclined guide plate forms an angle of 15 to 30 degrees with the conveying direction, and both the guide plate and the inclined guide plate are fixedly installed on the support frame by side supports; This feature allows the tilting guide plate to guide the box forward along the middle of the conveyor belt.

[0007] Preferably, the inclined guide plate has two symmetrical end plates fixedly installed at the end away from the guide plate, and the two end plates are rotatably connected by a rotating shaft. This feature allows the box to move more smoothly between the two inclined guide plates along the guide rollers.

[0008] Preferably, an anti-slip layer is provided on the surface of the conveyor belt, and the thickness of the anti-slip layer is between 0.3mm and 0.6mm; This feature increases the friction between the conveyor belt and the box, making it less likely for the box to slip during transport.

[0009] Preferably, a rectangular plate is fixedly installed at the end of the telescopic shaft of the cylinder, and the inner frame is detachably installed on the bottom surface of the rectangular plate.

[0010] Preferably, two symmetrical guide rods are fixedly installed on the top surface of the inner frame, and the guide rods pass through the top plate of the U-shaped frame and are slidably connected to the U-shaped frame; This feature makes the internal frame more stable and smooth when moving up and down.

[0011] Compared with the prior art, the beneficial effects of this utility model are: 1. This utility model achieves precise guidance and position correction of the cargo boxes on the conveyor belt by setting symmetrical guide plates at the front and rear and inclined guide plates with guide rollers. The inclined guide plates are at an angle of 15 degrees to 30 degrees with the conveying direction, and the guide rollers can reduce the resistance when the cargo boxes enter. This ensures that the cargo boxes are always conveyed forward along the center of the conveyor belt, thereby avoiding the positional deviation of the cargo boxes and eliminating the detection blind spots caused by the obstruction of the viewing angle.

[0012] 2. This utility model, by setting up an inner frame that is driven to lift by a cylinder, and cooperating with a high-definition industrial camera and light source on the side plate of the inner frame, and with the guide rod ensuring the stability of the inner frame's up and down movement, realizes the ability to flexibly adjust the height of the detection components according to the height of the cargo box. This allows the high-definition industrial camera to fully capture cargo box image information from multiple angles, achieving the effect of adapting to the detection needs of cargo boxes of different sizes and improving detection accuracy and efficiency.

[0013] 3. This utility model increases the friction between the conveyor belt and the cargo box by setting a 0.3mm~0.6mm thick anti-slip layer on the surface of the conveyor belt. At the same time, the conveyor belt is driven by a stepper motor to ensure a stable conveying rhythm, thus realizing the smooth transmission of the cargo box during the conveying process and avoiding slippage or position changes. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the overall structure of this utility model; Figure 2 This is one of the partial structural schematic diagrams of this utility model; Figure 3 This is the second partial structural schematic diagram of the present utility model; Figure 4 This is the third partial structural schematic diagram of this utility model; The meanings of the labels in the diagram are as follows: 1. Support frame; 10. Support beam; 11. Conveyor belt; 111. Anti-slip layer; 2. Guide plate; 20. Inclined guide plate; 21. End plate; 22. Guide roller; 23. Side support frame; 3. U-shaped frame; 30. Cylinder; 31. Rectangular plate; 32. Inner frame; 33. High-definition industrial camera; 34. Light source; 35. Guide rod; 4. Data processing host. Detailed Implementation

[0015] The technical solutions of the present utility model will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present utility model, and not all embodiments. Based on the embodiments of the present utility model, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the present utility model.

[0016] In the description of this utility model, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this utility model and simplifying the description, and are not intended to indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this utility model.

[0017] Please see Figures 1-4 This utility model provides a technical solution: a visual recognition-based cargo box size detection mechanism, including a support frame 1. A conveyor belt 11 for transporting cargo boxes is arranged above the support frame 1. Two symmetrical guide plates 2 are arranged above the conveyor belt 11 to guide the cargo boxes forward along the center of the conveyor belt 11. An inclined guide plate 20 is fixedly installed at the guiding end of the guide plate 2 to guide the cargo boxes forward along the center of the conveyor belt 11. The guide plates 2 and the inclined guide plates 20 are arranged along the length of the conveyor belt 11. The distance between the bottom surface of the guide plates 2 and the inclined guide plates 20 and the conveyor belt 11 is between 3cm and 5cm, so that the guide plates 2 and the inclined guide plates 20 will not rub against the conveyor belt 11. At the same time, the arrangement of the guide plates 2 and the inclined guide plates 20 also avoids the effect of the boxes falling off the side of the conveyor belt 11.

[0018] In this embodiment, a U-shaped frame 3 is fixedly installed on the support frame 1 and sleeved on the outside of the conveyor belt 11. A cylinder 30 is fixedly installed on the top plate of the U-shaped frame 3. An inner frame 32 sleeved on the conveyor belt 11 is detachably installed at the end of the telescopic shaft of the cylinder 30. A high-definition industrial camera 33 and a light source 34 are fixedly installed on the inner side of each side plate of the inner frame 32. A data processing host 4 for data processing operations is provided on one side of the support frame 1, so that the dimensions of the cargo box can be collected by the high-definition industrial camera 33, the light source 34 can provide illumination, the data processing host 4 can process the data, and calculate the length, width and height of the cargo box.

[0019] like Figure 1As shown, two sets of symmetrical support beams 10 are fixedly installed on the upper surface of the support frame 1. The conveyor belt 11 is rotatably connected to the support beams 10 through a rotating shaft. The conveyor belt 11 is driven to rotate by a stepper motor, so that the conveyor belt 11 is rotatably connected to the support beams 10 through the rotating shaft. The conveyor belt 11 is driven by a stepper motor, which provides a stable installation support foundation for the transport of the cargo box, and ensures the smooth operation of the conveyor belt 11 and the controllability of the transport rhythm.

[0020] Specifically, the inclined guide plate 20 is at an angle of 15 to 30 degrees to the conveying direction. Both the guide plate 2 and the inclined guide plate 20 are fixedly installed on the support frame 1 by the side support frame 23, so that the inclined guide plate 20 can guide the box to move forward along the middle of the conveyor belt 11. Two symmetrical end plates 21 are fixedly installed at the end of the inclined guide plate 20 away from the guide plate 2. The two end plates 21 are rotatably connected by a guide roller 22 through a rotating shaft, which reduces the resistance of the box entering and can guide the box to enter between the two inclined guide plates 20 more smoothly along the guide roller 22, avoiding the displacement of the box position.

[0021] like Figure 2 As shown, an anti-slip layer 111 is provided on the surface of the conveyor belt 11. The thickness of the anti-slip layer 111 is between 0.3mm and 0.6mm, which increases the friction between the conveyor belt 11 and the cargo box. In conjunction with the conveyor belt 11 driven by the stepper motor, it effectively avoids slippage during cargo box transportation and further ensures the stability of cargo box transportation.

[0022] like Figure 4 As shown, a rectangular plate 31 is fixedly installed at the end of the telescopic shaft of the cylinder 30, and the inner frame 32 is detachably installed on the bottom surface of the rectangular plate 31 by multiple fastening bolts, which facilitates the fixing, installation and disassembly operations.

[0023] like Figure 4 As shown, two symmetrical guide rods 35 are fixedly installed on the top surface of the inner frame 32. The guide rods 35 pass through the top plate of the U-shaped frame 3 and slide between the U-shaped frame 3 and the U-shaped frame 3, making the inner frame 32 more stable when moving up and down. The cylinder 30 drives the inner frame 32 to rise and fall, so that the high-definition industrial camera 33 and the light source 34 can be adapted to the height adjustment of the cargo box, fully capture image information, and improve the detection accuracy.

[0024] It is worth noting that the high-definition industrial camera 33 has a resolution of ≥24 million pixels and is equipped with a wide-angle lens; the data processing host 4 is equipped with an embedded processor, a data transmission module, and a storage module. The embedded processor uses an industrial-grade CPU and integrates a size detection algorithm, which can perform distortion correction, edge extraction, and 3D reconstruction on multi-view images, calculate the length, width, and height of the cargo box, with a detection accuracy of ±1mm and a data output cycle of ≤0.2 seconds; the data transmission module supports both Ethernet and RS485 protocols, which can transmit the detection data to the sorting robot control system or warehouse management system in real time to realize the linkage between detection and grasping; the storage module can cache 100,000 detection data, support the export of historical data and the marking of abnormal data, which is convenient for later traceability and equipment debugging.

[0025] Finally, it should be noted that the cylinder 30, the corresponding air source, the control system, the high-definition industrial camera 33, the light source 34, the data processing host 4, and the corresponding external power supply of this utility model are all general standard parts or parts known to those skilled in the art. Their structure and principle can be known to those skilled in the art through technical manuals or conventional experimental methods. In the idle space of this device, all the above-mentioned electrical components, which refer to power elements, electrical components, and the adapted controller and power supply, are connected by wires. The specific connection method should refer to the working principle of this utility model. The electrical connections between each electrical component are completed in the order of operation. The detailed connection methods are all technologies known in the art.

[0026] When using the visual recognition-based cargo box size detection mechanism of this utility model, the support frame 1 is fixed in the storage station, the conveyor belt 11 on the support beam 10 is installed in place through the rotating shaft to ensure that the surface anti-slip layer 1111 is flat, the guide plate 2 and the inclined guide plate 20 are fixed through the side support frame 23, the U-shaped frame 3 is fixed on the support frame 1, the telescopic shaft of the cylinder 30 is connected to the inner frame 32 through the rectangular plate 31, the guide rod 35 is inserted into the top of the U-shaped frame, the high-definition industrial camera 33, the light source 34 and the data processing host 4 are electrically connected to calibrate the camera parameters; The stepper motor drives the conveyor belt 11. The cargo box is guided by the guide roller 22 of the inclined guide plate 20 and moves towards the center of the conveyor belt along the guide plate 2. According to the estimated height of the cargo box, the cylinder 30 drives the inner frame 32 to rise and fall along the guide rod 35 to adjust the camera height. When the cargo box passes through the inner frame 32, the light source 34 provides supplementary light. The high-definition industrial camera 33 collects multi-view images. The data is transmitted to the data processing host 4 in real time. After algorithm correction and three-dimensional reconstruction, the length, width and height data are output. The data processing host 4 synchronizes the size data to the sorting robot or warehousing system via Ethernet / RS485 protocol to achieve coordinated operation, and the storage module caches the data for easy traceability.

[0027] The foregoing has shown and described the basic principles, main features, and advantages of this utility model. Those skilled in the art should understand that this utility model is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the utility model. Various changes and modifications can be made to this utility model without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed utility model. The scope of protection of this utility model is defined by the appended claims and their equivalents.

Claims

1. A visual recognition-based cargo box size detection mechanism, comprising a support frame (1), characterized in that: A conveyor belt (11) for conveying cargo boxes is provided above the support frame (1). Two guide plates (2) are provided above the conveyor belt (11) and are symmetrical to each other to guide the cargo boxes forward along the center of the conveyor belt (11). An inclined guide plate (20) is fixedly installed at the guide end of the guide plate (2). A U-shaped frame (3) is fixedly installed on the support frame (1) and sleeved on the outside of the conveyor belt (11). A cylinder (30) is fixedly installed on the top plate of the U-shaped frame (3). An inner frame (32) sleeved on the conveyor belt (11) is detachably installed at the end of the telescopic shaft of the cylinder (30). A high-definition industrial camera (33) and a light source (34) are fixedly installed on the inner side of each side plate of the inner frame (32). A data processing host (4) for data processing operations is provided on one side of the support frame (1).

2. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: Two sets of symmetrical support beams (10) are fixedly installed on the upper surface of the support frame (1). The conveyor belt (11) is rotatably connected to the support beams (10) through a rotating shaft. The conveyor belt (11) is driven to rotate by a stepper motor.

3. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: The inclined guide plate (20) is at an angle of 15 to 30 degrees to the conveying direction. Both the guide plate (2) and the inclined guide plate (20) are fixedly installed on the support frame (1) by the side support frame (23).

4. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: The inclined guide plate (20) is fixedly installed with two symmetrical end plates (21) at the end away from the guide plate (2), and the two end plates (21) are rotatably connected by a rotating shaft to a guide roller (22).

5. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: The surface of the conveyor belt (11) is provided with an anti-slip layer (111), the thickness of which is between 0.3mm and 0.6mm.

6. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: A rectangular plate (31) is fixedly installed at the end of the telescopic shaft of the cylinder (30), and the inner frame (32) is detachably installed on the bottom surface of the rectangular plate (31).

7. The cargo box size detection mechanism based on vision recognition according to claim 1, characterized in that: Two symmetrical guide rods (35) are fixedly installed on the top surface of the inner frame (32). The guide rods (35) pass through the top plate of the U-shaped frame (3) and are slidably connected to the U-shaped frame (3).

Images