Intelligent cleaning vehicle based on Opencv object recognition technology
By integrating Opencv object recognition technology and six-degree of freedom robotic arm on sanitation trucks, combining lidar and ant algorithm modules, intelligent classification and recycling of garbage is realized, solving the problems of inconvenient operation and low garbage classification efficiency of existing sanitation trucks , improves work efficiency and practicality.
Patent Information
- Application Number
- CN202420377268.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-29
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2034-02-28
AI Technical Summary
The existing sanitation trucks have problems such as inconvenient operation, large turning radius and poor flexibility in the garbage sorting and recycling process, which leads to low efficiency of garbage sorting and requires multiple labor participation to achieve garbage sorting, which increases the workload.
Intelligent cleaning vehicle based on Opencv object recognition technology is equipped with a six-degree of freedom robot arm, depth camera, lidar and ant algorithm module. It can identify garbage types through Opencv and control robot arms for automatic classification and recycling, realizing efficient garbage classification and recycling .
The intelligent classification and recycling of garbage has been realized, which has greatly liberated labor, improved work efficiency, and improved the practicality and efficiency of garbage disposal.
Smart Images

Figure CN222098630U_ABST
Abstract
Description
Technical Field
[0001] The utility model relates to a cleaning vehicle, in particular to an intelligent cleaning vehicle based on Opencv object recognition technology. Background Art
[0002] The current sanitation trucks are inconvenient to operate, with long wheelbase, large turning radius, and insufficient driving flexibility. Garbage is mainly classified into: recyclable garbage, hazardous waste, kitchen waste and other garbage. Different types of garbage require different recycling methods.
[0003] As disclosed in the publication (announcement) number: CN208701570U, the publication (announcement) date: 2019-04-05, a sanitation cleaning vehicle is disclosed, comprising a rear plate, the rear plate is provided with a garbage inlet, the garbage inlet is provided with a movable plate for flipping a garbage can, the movable plate is adapted to the garbage inlet, one end of the movable plate is hingedly connected to the lower end of the garbage inlet, a baffle is provided on the movable plate to prevent the liquid in the garbage can from flowing out of the box body, a driving mechanism for driving the movable plate to flip is provided below the movable plate, a clamping device is provided at the other end of the movable plate to prevent the garbage can from moving when flipping, the clamping device can adjust the clamping length, and the device can adapt to garbage cans of different models in different regions by adopting the above-mentioned technical scheme, thereby enhancing the versatility of the utility model, and in the process of flipping the movable plate, if there is liquid in the garbage can, it will flow along the direction of the movable plate to avoid the liquid from spilling in the air and causing secondary pollution, and at the same time, a baffle is provided on the movable plate to prevent the liquid from flowing out of the box body.
[0004] In the prior art including the above-mentioned patent, the existing cleaning vehicles dump all the garbage into a unified storage bin, which results in repeated garbage sorting work, wastes unnecessary labor, and fails to achieve garbage recycling and garbage sorting at the same time. The simultaneous dumping of garbage increases the burden of garbage sorting, resulting in a reduction in overall practicality. Utility Model Content
[0005] The purpose of the utility model is to provide an intelligent cleaning vehicle based on Opencv object recognition technology to solve the above problems.
[0006] In order to achieve the above-mentioned purpose, the utility model provides the following technical solutions: an intelligent cleaning vehicle based on Opencv object recognition technology, comprising a six-degree-of-freedom mechanical arm mounted on a body and a depth camera with a collection end facing the forward direction of the body, the six-degree-of-freedom mechanical arm comprising a gripping mechanism, and a camera assembly arranged at the collection end toward the clamping direction of the gripping mechanism;
[0007] It also includes a garbage collection box mounted on the body, and laser radars arranged according to a predetermined rule are respectively provided on both sides of the body and the garbage collection box;
[0008] It also includes an Arduino single-chip microcomputer and an ant algorithm module connected to the input end of the Arduino single-chip microcomputer, and the output end of the depth camera and the plurality of laser radars are connected to the input end of the ant algorithm module;
[0009] The Arduino single chip microcomputer collects image data based on the camera assembly to control the six-degree-of-freedom robotic arm.
[0010] Preferably, it also includes a semi-trailer body mounted on the main body, wherein:
[0011] One end of the garbage collection box is rotated on the semi-trailer body, and the other end is movably connected through an electric push rod rotatably arranged on the semi-trailer body.
[0012] Preferably, the interior of the garbage collection box forms two independent chambers through a classification baffle;
[0013] A hatch for the six-degree-of-freedom mechanical arm to be put into the two cavities is opened on one side of the garbage collection box, and a collection box door is arranged on one side of the hatch.
[0014] Preferably, the six-degree-of-freedom robotic arm is connected to a robotic arm gimbal movably arranged on the main body.
[0015] Preferably, an Opencv recognition module is provided in the camera assembly.
[0016] In the above technical scheme, the utility model provides an intelligent cleaning vehicle based on Opencv object recognition technology, which has the following beneficial effects: using the ant colony algorithm to achieve the optimal solution of the working path, using Opencv to identify the corresponding objects and transmit the signal to the robotic arm, allowing the robotic arm to dump the urban garbage into the collection box area designated by the rear storage vehicle, and finally return to the landfill, and dump the urban garbage into the designated area through the self-unloading device, making it intelligent, highly integrated and integrated, greatly liberating labor and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present utility model. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0018] Figure 1 It is a schematic diagram of the overall structure of the utility model;
[0019] Figure 2 It is a left side schematic diagram of the overall structure of the utility model;
[0020] Figure 3 It is a schematic diagram of the shortest distance of the ant algorithm module of the utility model;
[0021] Figure 4 It is a schematic diagram of the connection of the overall structural modules of the utility model.
[0022] Description of reference numerals:
[0023] 1. Main body; 2. Semi-trailer body; 3. Depth camera; 4. Garbage collection box; 5. LiDAR; 6. Electric push rod; 7. Classification baffle; 8. Collection box door; 9. Six-degree-of-freedom robotic arm; 10. Robotic arm gimbal; 11. Camera assembly. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0025] like Figure 1-4 As shown, an intelligent cleaning vehicle based on Opencv object recognition technology includes a six-degree-of-freedom mechanical arm 9 mounted on a body 1 and a depth camera 3 whose acquisition end faces the forward direction of the body 1. The six-degree-of-freedom mechanical arm 9 includes a gripping mechanism and a camera assembly 11 whose acquisition end is arranged in the clamping direction of the gripping mechanism;
[0026] It also includes a garbage collection box 4 mounted on the body 1, and laser radars 5 arranged according to a predetermined rule are respectively arranged on both sides of the body 1 and the garbage collection box 4;
[0027] It also includes an Arduino single-chip microcomputer and an ant algorithm module connected to the input end of the Arduino single-chip microcomputer, and the output ends of the depth camera 3 and the plurality of laser radars 5 are connected to the input end of the ant algorithm module;
[0028] The Arduino single chip microcomputer collects image data based on the camera assembly 11 to control the six-degree-of-freedom robotic arm 9 .
[0029] Specific, combined Figure 4It can be seen that the camera component 11 in the above embodiment can better identify the garbage grabbed by the grabbing mechanism by identifying the color and shape of the object based on Opencv. The depth camera 3 is used for virtual reality, augmented reality, and intelligent manufacturing, and is a camera device that can obtain scene distance information. It collects reflected light through technologies such as speckle, structured light or time of flight, and calculates the distance information of the object, thereby realizing three-dimensional modeling of the entire scene. Through the two independent collection boxes of the garbage collection box 4, after Opencv recognition, the six-degree-of-freedom robotic arm 9 implements different operation plans for different types of garbage, and pours the garbage into a specific collection box. In the process of garbage recycling, simple classification can be realized simultaneously, saving unnecessary labor. Through the laser radar 5, map surveying and environmental modeling are carried out to realize obstacle detection and obstacle avoidance functions, so that the depth camera 3 cooperates with the laser radar 5 to realize intelligent driving. The garbage collection box 4 is used to lift the collection box to a certain angle to facilitate garbage dumping. The classification baffle 7 is used for the two garbage collection boxes 4. The garbage collection box 4 is separated in the middle by an independent collection box, and the two collection box doors 8 of the garbage collection box 4 are controlled by a motor. After arriving at the designated area, the collection box door 8 of one of the garbage collection boxes 4 is opened, and a direct-push lifting mechanical structure is adopted to make the garbage collection box 4 dump the garbage backward in batches, so as to play a simple garbage sorting function. The garbage collection box 4 is opened and closed by the collection box door 8, so that the garbage inside the garbage collection box 4 can be easily poured out when the garbage is dumped. The garbage objects are grabbed by the six-degree-of-freedom mechanical arm 9, and the steering operation of the six-degree-of-freedom mechanical arm 9 is realized by the mechanical arm pan / tilt 10. The camera assembly 11 is connected to the six-degree-of-freedom mechanical arm 9, and the six-degree-of-freedom mechanical arm 9 is assisted in grabbing objects by recognizing the color, shape, etc. of the object, so as to classify the garbage.
[0030] Further, combined with Figure 3 It can be seen that in order to control the moving cleaning car, achieve various performance indicators, and fully reflect our system, the intelligent IoT city appearance cleaning car adopts a solution with a single-chip microcomputer as the main board and Arduino as the main control chip, which can be controlled simply and robustly. In order to realize the driving function of the sanitation car, L293D motor drive, laser radar 5 and depth camera 3 are used. In different areas, the optimal path for the sanitation car to work on the garbage bin is not the shortest distance. In order to achieve the most efficient work, this project considers using the ant algorithm module to realize the planning of the working path. The ant algorithm module is a swarm intelligence algorithm. In the process of looking for food, ants will release more "hormones" on a shorter path. Other ants will carry food along the path with high concentration of the hormone, thus forming positive feedback, so as to obtain the optimal solution on the path. Combining the ant algorithm module with the working path of the sanitation car, it can be obtained that when the sanitation car is in this area, there are N garbage stations, and the distance through each station is calculated to calculate the shortest total distance.
[0031] Design of the grabbing function of the intelligent cleaning vehicle based on Opencv object recognition technology: connect the microcontroller and the Python serial port, input the initial data. Read the target object and the surrounding environment through the camera component 11, and after a series of image processing, perform color recognition of the target object, and on this basis, perform Canny edge detection, find the contour, and finally display the contour, and judge whether it is the reserved data in the database. After receiving the corresponding data, the corresponding data will be sent to the host, and the host will send these data to the robotic arm, and the robotic arm will perform corresponding operations based on these data.
[0032] Furthermore, when using it, the user uploads the information of the location of each trash can to the platform, and through the depth camera 3 and the laser radar 5, the intelligent cleaning car based on the Opencv object recognition technology realizes the unmanned driving function to reach the designated area. The trash can is scanned by the camera component 11 to identify the color and shape of the garbage, and distinguish between recyclable garbage and non-recyclable garbage. The recyclable trash can is grabbed by the six-degree-of-freedom mechanical arm 9, and the garbage in the bucket is poured into the recyclable garbage area in the garbage collection box 4, and put back to its original place. The same applies to non-recyclable garbage. After collecting the garbage in the area, return to the garbage station, and arrive at the unloading area of recyclable garbage. The electric push rod 6 lifts the garbage collection box 4 and opens the corresponding collection box door 8 to realize garbage dumping, achieve the optimal solution for the working path of the cleaning car, and make garbage removal efficient. After arriving at the designated target, the vehicle uses Opencv to realize the object recognition function and feeds back the signal to the host computer. The host computer signal is then input to the six-degree-of-freedom robotic arm 9 module, allowing the six-degree-of-freedom robotic arm 9 to make different responses according to the signal and pour the garbage cans of different colors into the designated garbage collection box 4 behind the cleaning vehicle. After collecting the urban garbage, the cleaning vehicle drives to the designated garbage dump area and unloads the garbage.
[0033] It should be noted that the six-degree-of-freedom robotic arm 9 and the robotic arm gimbal 10 in the above embodiment are conventional equipment of the link vehicle, and the detailed structure is common knowledge to those skilled in the art and will not be described in detail.
[0034] The above only describes some exemplary embodiments of the present invention by way of illustration. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.
Claims
1. An intelligent cleaning vehicle based on Opencv object recognition technology, characterized in that: It comprises a six-degree-of-freedom mechanical arm (9) mounted on a body (1) and a depth camera (3) with a collection end facing the forward direction of the body (1), the six-degree-of-freedom mechanical arm (9) comprising a grasping mechanism and a camera assembly (11) arranged with the collection end facing the clamping direction of the grasping mechanism; It also includes a garbage collection box (4) mounted on the body (1), and laser radars (5) arranged according to a predetermined rule are respectively arranged on both sides of the body (1) and the garbage collection box (4); It also includes an Arduino single-chip microcomputer and an ant algorithm module connected to the input end of the Arduino single-chip microcomputer, and the output ends of the depth camera (3) and the plurality of laser radars (5) are connected to the input end of the ant algorithm module; The Arduino single chip microcomputer collects image data based on the camera assembly (11) to control the six-degree-of-freedom mechanical arm (9).
2. According to claim 1, the intelligent cleaning vehicle based on Opencv object recognition technology is characterized in that: It also includes a semi-trailer body (2) mounted on the body (1), wherein: One end of the garbage collection box (4) is rotated on the semi-trailer body (2), and the other end is movably connected via an electric push rod (6) rotatably arranged on the semi-trailer body (2).
3. According to claim 1, the intelligent cleaning vehicle based on Opencv object recognition technology is characterized in that: The interior of the garbage collection box (4) forms two independent chambers through a classification baffle (7); A hatch for the six-degree-of-freedom mechanical arm (9) to be placed into the two cavities is provided on one side of the garbage collection box (4), and a collection box door (8) is provided on one side of the hatch.
4. The intelligent cleaning vehicle based on Opencv object recognition technology according to claim 1 is characterized in that: The six-degree-of-freedom mechanical arm (9) is connected to a mechanical arm platform (10) movably arranged on the body (1).
5. The intelligent cleaning vehicle based on Opencv object recognition technology according to claim 1 is characterized in that: An Opencv recognition module is arranged in the camera assembly (11).
Citation Information
Patent Citations
Environmental -sanitation cleaning trolley
CN208701570U
