Automatic transferring system of unmanned garbage truck

Abstract

The invention relates to the technical field of unmanned driving, in particular to an automatic transferring system of an unmanned garbage truck, which comprises an image acquisition module for acquiring a video image of a monitoring camera; the target determination module is connected with the image acquisition module and is used for determining whether a to-be-detected target appears or not; the feature extraction module is connected with the image acquisition module and the target determination module and is used for determining whether the hand extract is garbage or not; the behavior prediction module is connected with the feature extraction module and used for determining the advancing direction of the to-be-detected target; the automatic transfer module is connected with the behavior prediction module and used for determining whether to transfer the unmanned garbage collection vehicle or not; the route planning module is connected with the automatic transfer module and used for determining the driving route of the unmanned garbage truck; and the planning and adjusting module is connected with the route planning module and is used for determining a planning route adjusting scheme of the unmanned garbage truck. According to the invention, the accuracy and efficiency of automatic transfer of the unmanned garbage truck are improved.

Description

Technical Field

[0001] The invention relates to the field of unmanned driving technology, and in particular to an automatic mobilization system for an unmanned driving garbage collection and transportation vehicle. Background Art

[0002] As the urban population continues to increase, the amount of garbage generated has also increased. The traditional manual garbage collection method can no longer meet the needs of efficient and timely treatment. At the same time, the continuous advancement of technologies such as autonomous driving, the Internet of Things, big data and artificial intelligence has made it possible for the intelligent transformation of the garbage disposal field. Against this background, the automatic mobilization system of unmanned garbage trucks came into being, aiming to achieve automation and intelligence of garbage collection in large communities through technical means, improve processing efficiency and reduce labor costs.

[0003] Chinese patent application publication number: CN109213133A discloses an automatic mobilization system for unmanned garbage trucks, including several unmanned garbage trucks, each of which includes: a time monitoring module, a carriage state detection module, a garbage point monitoring module, a wireless transmission module and a processing module; the processing module sends the idle signal to other unmanned garbage trucks and receives the help signal sent by other unmanned garbage trucks through the wireless transmission module, and when the unmanned garbage truck is fully loaded, the unmanned garbage truck closest to the remaining garbage point is selected from the idle signals sent by other unmanned garbage trucks as an assisting vehicle, and the remaining garbage points are sent to the unmanned garbage truck as an assisting vehicle. However, the prior art has the following problems: the prior art is to improve the timeliness and efficiency of garbage collection, which leads to the problem of poor accuracy and low efficiency of unmanned garbage trucks. Summary of the invention

[0004] To this end, the present invention provides an automatic mobilization system for an unmanned garbage collection vehicle, so as to overcome the problems of poor accuracy and low efficiency of automatic mobilization of unmanned garbage collection vehicles in the prior art.

[0005] To achieve the above object, the present invention provides an automatic mobilization system for an unmanned garbage collection vehicle, comprising:

[0006] An image acquisition module, which is used to obtain video images from a surveillance camera;

[0007] A target determination module, which is connected to the image acquisition module, is used to determine whether a target to be detected appears on the video image based on the human feature values ​​on the video image, and determine the eligibility of the selected video image quality according to the clarity of the video image in which the target to be detected appears;

[0008] A feature extraction module, which is connected to the image acquisition module and the target determination module, and is used to extract a comprehensive feature value of a hand extract of a target to be detected in a video image of qualified quality, so as to determine whether the hand extract is garbage based on the comprehensive feature value;

[0009] a behavior prediction module, which is connected to the feature extraction module, and is used to extract the leg feature value of the target to be detected in the video image in which the hand extract is garbage, determine the moving direction of the target to be detected based on the leg feature value, and determine whether the target to be detected is heading for the garbage bin area in combination with the relative difference between the leg feature value of the target to be detected and the leg feature value in the target video images of multiple different areas where the target to be detected appears;

[0010] an automatic mobilization module, which is connected to the behavior prediction module and is used to determine whether to call an unmanned garbage collection vehicle based on the time when the garbage bin is full;

[0011] A route planning module, which is connected to the automatic mobilization module, and is used to determine the driving route of the unmanned garbage collection vehicle based on the ratio of the garbage bin full time to the preset time under the condition that the unmanned garbage collection vehicle is determined to be called;

[0012] A planning adjustment module is connected to the route planning module, which determines the timeliness of the deployment of the unmanned garbage collection vehicle based on a response time threshold within a monitoring cycle, and determines the urgency or number of vehicles to increase the automatic deployment of the unmanned garbage collection vehicle based on the difference between a preset response time threshold and a response time threshold.

[0013] Furthermore, under the condition of determining to acquire the video image of the surveillance camera, the image acquisition module determines that a target to be detected appears on the video image based on a comparison result that a human feature value on the video image is greater than a preset human feature value, and determines that the quality of the target video image is qualified based on a comparison result that a clarity of the target video image showing the target to be detected is greater than a preset clarity.

[0014] Furthermore, the feature extraction module extracts a comprehensive feature value of a hand extract of the target to be detected in the target video image of qualified quality, under the condition that the quality of the target video image is determined to be qualified, and determines that the hand extract is garbage based on a comparison result that the comprehensive feature value is greater than a preset comprehensive feature value.

[0015] Furthermore, under the condition that the hand extract is determined to be garbage, the behavior prediction module extracts leg features of the target to be detected in the target video image in which the hand extract is garbage, and determines that the moving direction of the target to be detected is the direction of the garbage can based on the comparison result that the leg feature value of the target to be detected is greater than a preset leg feature value.

[0016] Furthermore, under the condition of determining the moving direction of the target to be detected, the behavior prediction module determines that the target to be detected is heading towards the trash can area based on the comparison result that the relative difference between the leg feature value of the target to be detected and the preset leg feature value in the target video images of multiple different areas where the target to be detected appears is less than or equal to the preset relative difference.

[0017] Furthermore, the automatic mobilization module determines to call the unmanned garbage collection vehicle based on a comparison result that the time when the garbage bin is full is less than or equal to a preset time, under the condition that the target to be detected goes to the garbage bin area.

[0018] Furthermore, under the condition of determining to call the unmanned garbage collection truck, the route planning module determines to plan the driving route of the unmanned garbage collection truck in the order of the time when the garbage bins are full based on the comparison result that the ratio of the time when the garbage bins are full to the preset time is less than or equal to the preset ratio.

[0019] Furthermore, under the condition of determining to call the unmanned garbage collection truck, the route planning module determines to plan the driving route of the unmanned garbage collection truck based on the distance between the unmanned garbage collection truck and the full garbage bin from near to far, based on the comparison result that the ratio of the time when the garbage bin is full to the preset time is greater than the preset ratio.

[0020] Furthermore, under the condition of determining the driving route of the unmanned garbage collection truck, the planning adjustment module determines that the automatic deployment of the unmanned garbage collection truck is not timely based on the comparison result that the difference between a preset response time threshold and the response time threshold within a monitoring cycle is less than or equal to the preset difference, and determines the planned route adjustment plan to increase the urgency of the automatic deployment of the unmanned garbage collection truck.

[0021] Furthermore, under the condition of determining the driving route of the unmanned garbage collection truck, the planning adjustment module determines that the unmanned garbage collection truck is not automatically mobilized in time based on the comparison result that the difference between a preset response time threshold and a response time threshold within a monitoring cycle is greater than the preset difference, and determines the planned route adjustment plan to increase the number of vehicles automatically mobilized by the unmanned garbage collection truck.

[0022] Compared with the prior art, the beneficial effect of the present invention is that the present invention obtains community surveillance video recognition and screens target video images to determine whether the hand extract is garbage, predict the direction of the discarder, mobilize the unmanned garbage truck according to the time when the garbage bin is full, and plan the driving route. According to the data within the monitoring period, the timeliness of the garbage truck mobilization is evaluated and the planned route is adjusted. The monitoring of garbage discarding behavior in the community and the automatic dispatch of garbage trucks are realized, and the efficiency and accuracy of garbage disposal are improved. At the same time, the driving route is adjusted according to the real-time monitoring data to ensure the timeliness and efficiency of garbage collection and transportation, which helps to maintain the cleanliness and hygiene of the community environment.

[0023] Furthermore, the present invention determines whether the target to be detected appears by comparing the human feature values ​​on the video image with the preset human feature values, and further determines whether the quality of the target video image is qualified based on the comparison result of the clarity of the target video image with the preset clarity, accurately identifies the target to be detected in the monitoring video, and effectively screens out target video images with qualified quality, providing an accurate and reliable data basis for feature extraction and behavior prediction, thereby improving the accuracy and efficiency of the automatic mobilization of unmanned garbage trucks.

[0024] Furthermore, the present invention determines whether it is garbage by extracting the features of the hand extracts in the video image of the qualified target, judges whether the target to be detected is moving towards the garbage can according to the leg feature values, and further confirms whether it is heading towards the garbage can area by the relative difference between the leg feature values ​​and the leg feature values. Accurate feature extraction and comparison, as well as behavior prediction, realize the intelligent recognition and tracking of garbage discarding behavior, and provide data support for the subsequent automatic mobilization of unmanned garbage collection vehicles, thereby improving the accuracy and efficiency of the automatic mobilization of unmanned garbage collection vehicles.

[0025] Furthermore, the present invention determines whether to call an unmanned garbage collection vehicle by comparing the time when the garbage bin is full with the preset time, and determines the driving route according to the ratio of the time when the garbage bin is full to the preset time. The overflowing state of the garbage bin is judged and the collection route is reasonably planned, thereby realizing the automation and efficiency of garbage collection, effectively improving the timeliness and efficiency of garbage disposal, and reducing the impact of garbage accumulation on the community environment.

[0026] Furthermore, the present invention evaluates the timeliness of the mobilization of unmanned garbage collection trucks by comparing the difference between a preset response time threshold and a response time threshold within a monitoring period with a preset difference, and formulates an urgency or quantity adjustment plan according to the size of the difference, so as to promptly discover problems with the mobilization of unmanned garbage collection trucks, and optimize the collection efficiency by adjusting the urgency or the number of vehicles to ensure that the garbage is processed in a timely manner, thereby improving the intelligence and response speed of garbage management, thereby improving the accuracy and efficiency of the automatic mobilization of unmanned garbage collection trucks. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a module connection diagram of the automatic mobilization system of the unmanned garbage collection vehicle according to an embodiment of the present invention;

[0028] Figure 2 A flow chart of determining whether a target to be detected appears on a video image according to an embodiment of the present invention;

[0029] Figure 3 A flow chart for determining the quality eligibility of a target video image according to an embodiment of the present invention;

[0030] Figure 4 The present invention is a flowchart for determining the timeliness of the deployment of an unmanned garbage collection vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0033] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical test data and the corresponding historical test results of the present invention in the three months before this test. It can be understood by those skilled in the art that the present invention can determine the above parameters for a single item by selecting the highest proportion of values ​​as the preset standard parameters according to the data distribution, using weighted summation to use the obtained values ​​as the preset standard parameters, substituting each historical data into a specific formula and using the values ​​obtained by the formula as the preset standard parameters or other selection methods, as long as the present invention can clearly define different specific situations in the single determination process through the obtained values.

[0034] See also Figure 1 - Figure 4 As shown, Figure 1This is a module connection diagram of the automatic mobilization system of the unmanned garbage collection vehicle according to an embodiment of the present invention; Figure 2 A flow chart of determining whether a target to be detected appears on a video image according to an embodiment of the present invention; Figure 3 A flow chart for determining the quality eligibility of a target video image according to an embodiment of the present invention; Figure 4 The present invention is a flowchart for determining the timeliness of the deployment of an unmanned garbage collection vehicle according to an embodiment of the present invention.

[0035] The embodiment of the present invention is used for an automatic mobilization system of an unmanned garbage collection vehicle, comprising:

[0036] Image acquisition module: used to obtain video images from surveillance cameras;

[0037] Target determination module: connected to the image acquisition module, used to determine whether the target to be detected appears on the video image based on the human feature value on the video image, and determine the eligibility of the target video image quality;

[0038] Feature extraction module: connected to the image acquisition module and the target determination module, used to determine whether the hand extract is garbage based on the comprehensive feature value of the hand extract of the target to be detected in the target video image with qualified quality;

[0039] Behavior prediction module: connected to the feature extraction module, used to determine the moving direction of the target to be detected based on the leg feature value of the target to be detected in the target video image whose hand extract is garbage;

[0040] Automatic mobilization module: It is connected to the behavior prediction module and is used to determine whether to call an unmanned garbage truck based on the time when the garbage bin is full;

[0041] Route planning module: connected to the automatic mobilization module, used to determine the driving route of the unmanned garbage collection vehicle based on the difference between the full time of the garbage bin and the preset time;

[0042] Planning adjustment module: It is connected to the route planning module and is used to determine the timeliness of the garbage truck mobilization based on the response time threshold within a monitoring cycle, and to determine the planned route adjustment plan of the unmanned garbage collection truck based on the difference between the preset response time threshold and the response time threshold.

[0043] In the embodiment of the present invention, the target to be detected is a person appearing in the surveillance video.

[0044] In the embodiment of the present invention, the monitoring cycle is the time taken by the unmanned garbage collection vehicle to depart and return within one week.

[0045] Specifically, the present invention obtains community surveillance video recognition and filters the target video image to determine whether the hand extract is garbage, predict the direction of the discarder, mobilize the unmanned garbage truck according to the time when the garbage bin is full, and plan the driving route. The timeliness of the garbage truck mobilization is evaluated based on the data within the monitoring period, and the planned route is adjusted. The monitoring of garbage discarding behavior in the community and the automatic dispatch of garbage trucks are realized, which improves the efficiency and accuracy of garbage disposal. At the same time, the driving route is adjusted according to the real-time monitoring data to ensure the timeliness and efficiency of garbage removal, which helps to maintain the cleanliness and hygiene of the community environment.

[0046] Specifically, the target determination module determines whether the target to be detected appears on the video image according to the comparison result of the human feature value on the video image and the preset human feature value under the condition of determining to obtain the video image of the surveillance camera;

[0047] If the human body feature value is less than or equal to the preset human body feature value, it is determined that the target to be detected does not appear on the video image;

[0048] If the human body feature value is greater than the preset human body feature value, it is determined that a target to be detected appears on the video image.

[0049] In the embodiment of the present invention, the preset human characteristic value is 0.87, but the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0050] Specifically, the human feature value is the ratio of the sum of the ratios of the RGB values ​​of the colors of several single pixel points on the video image to the average RGB value to the number of pixels.

[0051] In the embodiment of the present invention, the RGB value is the intensity value of the three basic colors of red, green and blue in the RGB color mode.

[0052] Specifically, the target determination module determines the quality of the target video image based on a comparison result of the definition of the target video image showing the target to be detected and a preset definition of 0.92 under the condition that the target to be detected appears on the video image;

[0053] If the definition is less than or equal to the preset definition, determining that the quality of the target video image is unqualified;

[0054] If the definition is greater than the preset definition, it is determined that the quality of the target video image is qualified.

[0055] In the embodiment of the present invention, the preset clarity value is 0.92, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0056] Specifically, the definition is the ratio of the sum of the ratios of the grayscale values ​​of a number of single pixels in the target video image to the average grayscale value to the number of pixels.

[0057] Specifically, the present invention determines whether a target to be detected appears by comparing human feature values ​​on a video image with preset human feature values, and further determines whether the target video image quality is qualified based on the comparison result of the clarity of the target video image with the preset clarity, accurately identifies the target to be detected in the surveillance video, and effectively screens out target video images of qualified quality, providing an accurate and reliable data basis for feature extraction and behavior prediction, thereby improving the accuracy and efficiency of the automatic mobilization of unmanned garbage trucks.

[0058] Specifically, the feature extraction module extracts the comprehensive feature value of the hand extract of the target to be detected in the target video image with qualified quality, and determines whether the hand extract is garbage according to the comparison result between the comprehensive feature value and the preset comprehensive feature value.

[0059] If the comprehensive characteristic value is less than or equal to the preset comprehensive characteristic value, it is determined that the hand extract is not garbage;

[0060] If the comprehensive characteristic value is greater than the preset comprehensive characteristic value, it is determined that the hand extract is garbage.

[0061] In the embodiment of the present invention, the preset comprehensive characteristic value is 0.85, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0062] Specifically, the comprehensive characteristic value is the ratio of the circumference of the hand extract to the preset circumference multiplied by the ratio of the area to the preset area multiplied by the ratio of the roundness to the preset roundness.

[0063] Specifically, the behavior prediction module, under the condition that the hand extract is determined to be garbage, extracts the leg features of the target to be detected in the target video image in which the hand extract is garbage, and determines whether the forward direction of the target to be detected is the direction of the garbage can according to the comparison result of the leg feature value of the target to be detected and the preset leg feature value;

[0064] If the leg feature value is less than or equal to the preset leg feature value, it is determined that the moving direction of the target to be detected is not the direction of the trash can;

[0065] If the leg feature value is greater than the preset leg feature value, it is determined that the moving direction of the target to be detected is the direction of the trash can.

[0066] In the embodiment of the present invention, the preset leg characteristic value is 0.88, but the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0067] Specifically, the preset leg characteristic value is the ratio of the hip joint angle between the thigh and the trunk to the preset hip joint angle multiplied by the ratio of the knee joint angle between the thigh and the calf to the preset knee joint angle multiplied by the ratio of the ankle joint angle between the calf and the sole of the foot to the preset ankle joint angle.

[0068] Specifically, the behavior prediction module determines whether the target to be detected is heading towards the trash can area based on a comparison result of a relative difference between a leg feature value of the target to be detected and a preset leg feature value in target video images of multiple different areas where the target to be detected appears and a preset relative difference of 0.25, under the condition that the forward direction of the target to be detected is the direction of the trash can;

[0069] If the relative difference is less than or equal to the preset relative difference, it is determined that the target to be detected is heading to the trash can area;

[0070] If the relative difference is greater than the preset relative difference, it is determined that the target to be detected has not gone to the trash can area;

[0071] The relative difference is the relative difference between the leg feature value and the preset leg feature value.

[0072] In the embodiment of the present invention, the preset relative difference value is 0.25, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0073] Specifically, the present invention determines whether it is garbage by extracting the features of the hand extracts in the video image of the qualified target, judges whether the target to be detected is moving towards the garbage can according to the leg feature values, and further confirms whether it is heading towards the garbage can area by the relative difference between the leg feature values ​​and the leg feature values. Accurate feature extraction and comparison, as well as behavior prediction, realize the intelligent recognition and tracking of garbage discarding behavior, and provide data support for the subsequent automatic mobilization of unmanned garbage collection trucks, thereby improving the accuracy and efficiency of the automatic mobilization of unmanned garbage collection trucks.

[0074] Specifically, under the condition that the target to be detected goes to the trash can area to discard trash,

[0075] Specifically, the automatic mobilization module determines whether to call an unmanned garbage collection vehicle based on the comparison result of the time when the garbage bin is full and the preset time of 3h, under the condition that the target to be detected is heading to the garbage bin area;

[0076] If the time is less than or equal to the preset time, it is determined to call an unmanned garbage collection vehicle;

[0077] If the time is greater than the preset time, it is determined that there is no need to call an unmanned garbage collection truck.

[0078] In the embodiment of the present invention, the preset time value is 3 hours, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0079] In the embodiment of the present invention, the time when the trash can is full is obtained by taking the average of the time when several trash cans are full in a week, which represents the time between two adjacent targets to be detected going to the trash can area.

[0080] Specifically, the route planning module determines the driving route of the unmanned garbage collection vehicle according to the comparison result of the ratio of the time when the garbage bin is full to the preset time and the preset ratio of 0.75 under the condition of determining to call the unmanned garbage collection vehicle;

[0081] If the ratio is less than or equal to the preset ratio, it is determined to plan the driving route of the unmanned garbage collection vehicle in the order of the time when the garbage bins are full;

[0082] If the ratio is greater than the preset ratio, it is determined to plan the driving route of the unmanned garbage collection vehicle based on the distance between the unmanned garbage collection vehicle and the full garbage bin from near to far;

[0083] The ratio is the ratio of the time when the trash can is full to the preset time.

[0084] In the embodiment of the present invention, the preset ratio is 0.75, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0085] Specifically, the present invention determines whether to call an unmanned garbage collection vehicle by comparing the time when the garbage bin is full with the preset time, and determines the driving route according to the ratio of the time when the garbage bin is full to the preset time. The overflowing state of the garbage bin is judged and the collection route is reasonably planned, thereby realizing the automation and efficiency of garbage collection, effectively improving the timeliness and efficiency of garbage disposal, and reducing the impact of garbage accumulation on the community environment.

[0086] Specifically, the planning adjustment module determines the timeliness of the automatic mobilization of the unmanned garbage collection vehicle based on the comparison result of the response time threshold within a monitoring cycle and the preset response time threshold 1h under the condition of determining the driving route of the unmanned garbage collection vehicle;

[0087] If the response time threshold is less than or equal to the preset response time threshold, it is determined that the unmanned garbage collection vehicle is not automatically mobilized in time;

[0088] If the response time threshold is greater than the preset response time threshold, it is determined that the unmanned garbage collection vehicle is automatically mobilized in time.

[0089] In the embodiment of the present invention, the preset response time threshold value is 1 hour, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0090] Specifically, the response time threshold is the time it takes for the unmanned garbage collection vehicle to depart and return.

[0091] Specifically, the planning adjustment module determines the planned route adjustment scheme for the untimely automatic mobilization of the unmanned garbage collection vehicle based on the comparison result of the preset response time threshold and the difference between the response time threshold and the preset difference 0.3, under the condition that the unmanned garbage collection vehicle is determined to be untimely in automatic mobilization;

[0092] If the difference is less than or equal to the preset difference, it is determined that the urgency of the automatic deployment of the unmanned garbage collection vehicle is increased to a corresponding value by using a preset urgency adjustment coefficient of 0.8;

[0093] If the difference is greater than the preset difference, it is determined that the number of vehicles automatically mobilized by the unmanned garbage collection vehicle is increased to a corresponding value by a preset number adjustment coefficient of 2;

[0094] The difference is the difference between the preset response time threshold and the response time threshold.

[0095] In the embodiment of the present invention, the preset difference value is 0.3, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0096] Specifically, the planning adjustment module calculates the urgency according to the following formula and sets:

[0097]

[0098] Among them, P represents the urgency, V represents the total volume threshold of the full trash can, N represents the number of trash cans, and V0 represents the volume of each trash can.

[0099] In the embodiment of the present invention, the threshold value of the total volume of the full trash cans is the product of the number of full trash cans in the video image and the volume of each trash can. The value range of the threshold value of the total volume of the full trash cans is 80-100m 3 , preferably 90m 3,Increasing the urgency actually reduces the total volume threshold of the full trash can.

[0100] In an embodiment of the present invention, the increased urgency is the product of the urgency of the automatic mobilization of the unmanned garbage collection truck and the preset urgency adjustment coefficient of 0.8, and the increased number of vehicles is the product of the number of vehicles automatically mobilized by the unmanned garbage collection truck and the preset number adjustment coefficient of 2.

[0101] Specifically, the present invention evaluates the timeliness of the mobilization of unmanned garbage collection trucks by comparing the difference between a preset response time threshold and a response time threshold within a monitoring period with a preset difference, and formulates an urgency or quantity adjustment plan according to the size of the difference, so as to promptly discover problems with the mobilization of unmanned garbage collection trucks, and optimize the collection efficiency by adjusting the urgency or the number of vehicles, ensuring that garbage is handled in a timely manner, thereby improving the intelligence and response speed of garbage management, and thus improving the accuracy and efficiency of the automatic mobilization of unmanned garbage collection trucks.

[0102] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic mobilization system for unmanned garbage trucks, characterized in that: include: An image acquisition module, which is used to obtain video images from a surveillance camera; A target determination module, which is connected to the image acquisition module, is used to determine whether a target to be detected appears on the video image based on the human feature values ​​on the video image, and determine the eligibility of the selected video image quality according to the clarity of the video image in which the target to be detected appears; A feature extraction module, which is connected to the image acquisition module and the target determination module, and is used to extract a comprehensive feature value of a hand extract of a target to be detected in a video image of qualified quality, so as to determine whether the hand extract is garbage based on the comprehensive feature value; a behavior prediction module, which is connected to the feature extraction module, and is used to extract the leg feature value of the target to be detected in the video image in which the hand extract is garbage, determine the moving direction of the target to be detected based on the leg feature value, and determine whether the target to be detected is heading for the garbage bin area in combination with the relative difference between the leg feature value of the target to be detected and the leg feature value in the target video images of multiple different areas where the target to be detected appears; an automatic mobilization module, which is connected to the behavior prediction module and is used to determine whether to call an unmanned garbage collection vehicle based on the time when the garbage bin is full; A route planning module, which is connected to the automatic mobilization module, and is used to determine the driving route of the unmanned garbage collection vehicle based on the ratio of the garbage bin full time to the preset time under the condition that the unmanned garbage collection vehicle is determined to be called; A planning adjustment module is connected to the route planning module, which determines the timeliness of the automatic deployment of the unmanned garbage collection vehicle based on a response time threshold within a monitoring cycle, and determines the urgency or number of vehicles to increase the automatic deployment of the unmanned garbage collection vehicle based on the difference between a preset response time threshold and a response time threshold.

2. The automatic mobilization system for unmanned garbage trucks according to claim 1 is characterized in that: The image acquisition module determines, under the condition of determining that the video image of the surveillance camera is acquired, that the target to be detected appears on the video image based on a comparison result that a human feature value on the video image is greater than a preset human feature value, and determines that the quality of the target video image is qualified based on a comparison result that a clarity of the target video image showing the target to be detected is greater than a preset clarity.

3. The automatic mobilization system for unmanned garbage trucks according to claim 2 is characterized in that: The feature extraction module extracts the comprehensive feature value of the hand extract of the target to be detected in the target video image with qualified quality, under the condition that the quality of the target video image is determined to be qualified, and determines that the hand extract is garbage based on the comparison result that the comprehensive feature value is greater than the preset comprehensive feature value.

4. The automatic mobilization system for unmanned garbage trucks according to claim 3 is characterized in that: Under the condition that the hand extract is determined to be garbage, the behavior prediction module extracts the leg features of the target to be detected in the target video image in which the hand extract is garbage, and determines that the moving direction of the target to be detected is the direction of the garbage can based on the comparison result that the leg feature value of the target to be detected is greater than the preset leg feature value.

5. The automatic mobilization system for unmanned garbage trucks according to claim 4 is characterized in that: Under the condition of determining the forward direction of the target to be detected, the behavior prediction module determines that the target to be detected is heading towards the trash can area based on the comparison result that the relative difference between the leg feature value of the target to be detected and the preset leg feature value in the target video images of multiple different areas where the target to be detected appears is less than or equal to the preset relative difference.

6. The automatic mobilization system for unmanned garbage trucks according to claim 5, characterized in that: The automatic mobilization module determines to call an unmanned garbage collection vehicle based on a comparison result that the time when the garbage bin is full is less than or equal to a preset time, under the condition that the target to be detected is heading to the garbage bin area.

7. The automatic mobilization system for unmanned garbage trucks according to claim 6, characterized in that: The route planning module, under the condition of determining to call the unmanned garbage collection truck, plans the driving route of the unmanned garbage collection truck in the order of the time when the garbage bins are full based on the comparison result that the ratio of the time when the garbage bins are full to the preset time is less than or equal to the preset ratio.

8. The automatic mobilization system for unmanned garbage trucks according to claim 6, characterized in that: Under the condition of determining to call the unmanned garbage collection truck, the route planning module determines to plan the driving route of the unmanned garbage collection truck based on the distance between the unmanned garbage collection truck and the full garbage bin from near to far based on the comparison result that the ratio of the time when the garbage bin is full to the preset time is greater than the preset ratio.

9. The automatic mobilization system for unmanned garbage trucks according to claim 8, characterized in that: The planning adjustment module determines, under the condition of determining the driving route of the unmanned garbage collection truck, that the automatic deployment of the unmanned garbage collection truck is not timely based on the comparison result that the difference between a preset response time threshold and a response time threshold within a monitoring cycle is less than or equal to the preset difference, and determines the planned route adjustment plan to increase the urgency of the automatic deployment of the unmanned garbage collection truck.

10. The automatic mobilization system for unmanned garbage trucks according to claim 8, characterized in that: The planning adjustment module determines, under the condition of determining the driving route of the unmanned garbage collection truck, that the unmanned garbage collection truck is not automatically mobilized in time based on a comparison result that the difference between a preset response time threshold and a response time threshold within a monitoring cycle is greater than the preset difference, and determines that the planned route adjustment plan is to increase the number of vehicles automatically mobilized by the unmanned garbage collection truck.

Images