CN113723226A - Mobile stall detection method and device, electronic equipment and storage medium - Google Patents
Mobile stall detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113723226A CN113723226A CN202110932893.3A CN202110932893A CN113723226A CN 113723226 A CN113723226 A CN 113723226A CN 202110932893 A CN202110932893 A CN 202110932893A CN 113723226 A CN113723226 A CN 113723226A
- Authority
- CN
- China
- Prior art keywords
- booth
- detected
- type
- carrier
- evaluation value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims description 89
- 235000013399 edible fruits Nutrition 0.000 claims description 19
- 235000013311 vegetables Nutrition 0.000 claims description 14
- 238000007667 floating Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims description 2
- 239000000969 carrier Substances 0.000 description 15
- 239000013598 vector Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001061260 Emmelichthys struhsakeri Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The application discloses a mobile stall detection method, a mobile stall detection device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an image to be detected; detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected, and determining the detection results of the at least two objects; the carrier type is the type of a carrier for carrying articles in the to-be-detected booth, and the accessory type is the type of an accessory associated with the to-be-detected booth; and determining whether the booth to be detected is a mobile booth based on the detection results of the at least two objects. Therefore, the method improves the accuracy of the mobile booth detection by combining at least two objects of the booth type, the carrier type and the accessory type in the booth detection process.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for detecting a mobile booth, an electronic device, and a storage medium.
Background
The management of the operating stall is an important part of city management, and the modernized city construction is directly influenced by the quality of the management of the operating stall. Mobile vendors such as retail establishments or individuals typically use mobile booths such as mobile vendors to sell products at a non-fixed location. The mobile booths formed by mobile booters in the vending process not only occupy public places such as urban roads and squares, but also bring problems in various aspects such as environmental sanitation, food safety and the like. The management of the mobile stalls is a key and difficult point of the management of the urban operating stall, and the construction and the management of modern cities are directly influenced.
In order to reduce the number of mobile booths, a great amount of manpower is usually required to be driven by city pipelines to go to the street to investigate and dissuade, and if a walking mobile booter is encountered, the management difficulty is higher. With the popularization of intelligent city management, image recognition and detection play a great role in the fields of transportation and public safety. However, at present, the mobile booths cannot be accurately identified from a plurality of booths, which is not beneficial to the management of the mobile booths.
Disclosure of Invention
The application provides a mobile booth detection method, a mobile booth detection device, electronic equipment and a storage medium, so as to improve the detection accuracy of a mobile booth.
The application provides a method for detecting a mobile booth, which comprises the steps of obtaining an image to be detected; detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected, and determining the detection results of the at least two objects; the carrier type is the type of a carrier for carrying articles in the to-be-detected booth, and the accessory type is the type of an accessory associated with the to-be-detected booth; and determining whether the booth to be detected is a mobile booth based on the detection results of the at least two objects.
The second aspect of the present application provides a mobile booth detection apparatus, comprising: the video frame acquisition module is used for acquiring an image to be detected; the target detection module is connected with the video frame acquisition module and is used for detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected and determining the detection results of the at least two objects, wherein the carrier type is the type of a carrier for carrying articles in the booth to be detected, and the accessory type is the type of an accessory associated with the booth to be detected; and the processing module is connected with the target detection module and determines whether the booth to be detected is a mobile booth or not based on the detection results of at least two objects.
A third aspect of the present application provides an electronic device, which includes a processor and a memory coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the method for detecting a moving booth provided in the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon program instructions that, when executed by a processor, implement the method for detecting a flow booth as provided by the first aspect.
The application at least has the beneficial effects that: compared with the prior art, the mobile booth detection method has the advantages that in the booth detection process, the accuracy of mobile booth detection is improved by combining at least two objects in a booth type, a carrier type and an accessory type.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of an embodiment of a method for mobile booth inspection according to the present application;
fig. 2 is a schematic flow chart of another embodiment of the booth detection method of the present application;
fig. 3 is a schematic flow chart of a mobile booth testing method according to another embodiment of the present application;
fig. 4 is a schematic flow chart of a booth detection method according to another embodiment of the present application;
fig. 5 is a schematic flow chart of a mobile booth detection method according to another embodiment of the present application;
fig. 6 is a schematic view of a fruit booth of the present application;
fig. 7 is another schematic view of a fruit booth of the present application;
fig. 8 is a schematic view of a vegetable booth of the present application;
fig. 9 is another schematic view of a vegetable booth of the present application;
fig. 10 is a schematic view of a dining booth of the present application;
fig. 11 is a schematic diagram of a frame structure of the mobile booth testing apparatus of the present application;
FIG. 12 is a schematic diagram of a frame structure of the electronic device of the present application;
fig. 13 is a schematic diagram of a frame structure of the computer-readable storage medium of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first", "second" and "third" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any indication of the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of the feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. All directional indications (such as up, down, left, right, front, and rear … …) in the embodiments of the present application are only used to explain the relative positional relationship between the components, the movement, and the like in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indication is changed accordingly. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The first aspect of the application provides a method for detecting a mobile booth, which improves the accuracy of mobile booth detection by combining at least two objects of a booth type, a carrier type and an accessory type in the detection process. Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a method for detecting a mobile booth in the present application, the method including the following steps:
s11: and acquiring an image to be detected.
Specifically, the video frame sequence of the location to be detected may be obtained by the image obtaining device, the image obtaining device may be fixed at a certain position to obtain the video frame sequence of the specific location, and the image obtaining device may also adjust its position to obtain the video frame sequences of different locations to be detected.
The video frame sequence is obtained from the same place to be detected, and may be a continuous or discontinuous video frame sequence, and the frame number of the video frame sequence is greater than a preset frame number, and the preset frame number may be 1000 frames, 1500 frames, and so on.
In some embodiments, the image to be detected may be one or more frames of images in a sequence of video frames, and is not particularly limited.
S12: detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected, and determining the detection results of the at least two objects; the carrier type is the type of the carrier for carrying the articles in the to-be-detected booth, and the accessory type is the type of the accessory associated with the to-be-detected booth.
Specifically, at least two objects of the booth type, the carrier type, and the accessory type of the image to be detected may be image-detected using a preset detection model. The preset detection model is a deep learning network model, is obtained by training a large number of training samples in advance, and can be an image detection model so as to perform image detection on video frames and obtain a detection result.
More specifically, the preset detection model may be an object detection model for performing object detection on at least two objects among a booth type, a carrier type, and an attachment type of the booth to be detected. The detection results of at least two objects are determined, i.e. it is determined whether an object is detected in the detection results. For example, the booth type and the carrier type of the booth to be detected are detected, and it is determined whether the booth type and the carrier type are detected.
In combination with the foregoing, when the video frame sequence includes consecutive multi-frame video frames, the preset detection model continuously performs image detection on the current video frame in the video frame sequence according to the acquisition time sequence of the video frames, so as to acquire an image detection result of the current video frame. At this time, the current video frame is the image to be detected.
Specifically, the booth type may be divided according to the type of goods sold by the booth. For example, booth types may include fruit booths, vegetable booths, dining booths, dress booths, grocery booths, and so forth.
The carrier type is a type of carrier for carrying articles in the booth to be detected, and for example, the carrier type may include types of automobiles, non-automobiles, and general containers, and the like.
The accessory type is the type of accessory associated with the booth to be inspected, which may be the type of other items in the booth besides goods and carriers. For example, the accessory types may be service supplies, shelter supplies, mobile gas supply supplies, and the like. The service supplies can comprise tables, seats and the like, the shielding supplies can comprise sunshades, baffles and the like, and the gas supply and power supply supplies can comprise gas tanks, generators and the like.
Of course, the division of the booth type, the carrier type, and the attachment type is not limited thereto.
In combination with the above, the article types in the booths can be obtained through the object detection model, so as to judge the booth types, the carrier types and the accessory types according to the article types. For the booth to be detected, the number of booth types is 1, and the number of carrier types and accessory types may be 1 or more than 1. Since the booth type includes only one, when the article type is large, the base for judging the booth type can be made based on the article type corresponding to the article with the largest number of articles.
For example, when a booth is detected to include a large amount of fruit, the booth type may be obtained as a fruit booth. When a cart is detected in the booth, the carrier type can be obtained including a non-motor vehicle type. When the detected type of the accessory comprises a gas tank, the type of the accessory can be acquired to comprise a mobile gas supply power type.
S13: and determining whether the booth to be detected is a mobile booth based on the detection results of the at least two objects.
Whether an object is detected can be known based on the detection results of at least two objects, and whether a mobile booth is determined according to whether an object is detected. That is, it is possible to know whether the booth type, the carrier type, and the attachment type are detected based on the detection results of at least two kinds of detection objects, and thus to make a judgment of the moving booth.
For example, if it is known based on the detection result that the booth type, the carrier type, and the attachment type are detected in the image to be detected, the booth is more likely to be a mobile booth. If the detected booth type and carrier type are detected, then the booth is less likely to be a mobile booth. If only the booth type is detected, the booth is less likely to be a mobile booth.
In some embodiments, the possibility that the booth to be detected is the mobile booth can be obtained according to the detection result, and when the possibility is greater than the threshold value, the booth to be detected is taken as the mobile booth.
Therefore, in the booth detection process, the detection results of at least two objects in the booth type, the carrier type and the accessory type are combined to judge whether the booth to be detected is the mobile booth, and the detection accuracy of the mobile booth is improved.
Referring to fig. 2, fig. 2 is a schematic flow chart of another embodiment of a mobile booth detection method according to the present application.
Specifically, the step S13 may specifically be:
s21: on the basis of the detection results of the at least two objects, a booth evaluation value of the booth to be detected is determined.
The booth evaluation value is a value for evaluating the degree of possibility that a booth is a mobile booth, and the greater the booth evaluation value, the greater the possibility that a booth to be detected is a mobile booth.
Each object may correspond to a preset evaluation value, and if an object is detected, the evaluation value corresponding to the object is calculated as the booth evaluation value. For example, if the booth type and the carrier type are detected, the preset evaluation values corresponding to the booth type and the carrier type are respectively calculated as the booth evaluation values.
Different preset evaluation values can be set according to different correspondences, and the importance degree of the judgment of the flowing booth can be set according to the object. One object may be set with different preset evaluation values corresponding to objects under different refinements in one object.
S22: and if the estimated value of the booth is determined to be larger than or equal to the estimated value of the preset booth, determining the booth to be detected in the image to be detected as the mobile booth.
The preset booth evaluation value can be set according to the accuracy requirement of the mobile booth detection, and if the mobile booth detection is required to be realized with higher accuracy, a higher preset booth evaluation value can be set.
When the booth evaluation value is greater than or equal to the preset booth evaluation value, it is indicated that more objects are detected in the image to be detected, or that the detected objects, although less objects, are of higher importance to the flow booth judgment.
Therefore, the mobile booth is judged by acquiring the booth evaluation value, so that the quantitative judgment of the mobile booth is realized, and the accuracy of the mobile booth judgment is improved.
Further, the step S21 may specifically be: and determining the booth evaluation value of the booth to be detected based on the detection results of the at least two objects and the weights corresponding to the at least two objects.
That is, the booth evaluation value is set to a bit weight, different objects may correspond to different weights, and the same object may also be set to different weights. At this time, the booth evaluation value of the booth to be detected is the weight corresponding to the detected object.
Specifically, each booth type corresponds to a weight, and the weights corresponding to different booth types may be the same or different. Each bearer type corresponds to a weight, and the weights corresponding to different bearer types are different. Each appendage type corresponds to a weight, and the weights for different appendage types are different.
Specifically, when the detection result includes the booth type, the carrier type, and the accessory type, the weights of the booth type, the carrier type, and the accessory type are respectively calculated based on the weights respectively corresponding to the booth type, the carrier type, and the accessory type, and the sum of the weights of the booth type, the carrier type, and the accessory type is used as the weight of the image to be detected.
For example, the booth type is denoted as 1, the weight of the booth type is 1, and the weights of the carrier type and the accessory type are calculated similarly. For another example, the booth type is a fruit booth, and the weight of the fruit booth is 0.4, so that the weight of the fruit booth is 1 × 0.4 — 0.4.
And for the same booth, when the carrier types are more than two, the weight corresponding to the carrier type is the sum of the weights of different carrier types. Correspondingly, when the types of the attachments are multiple, the same is true for the weight calculation.
For example, when there are two carrier types, the weight of a carrier type is 1 +1 corresponding to one carrier type and +1 corresponding to another carrier type.
Referring to fig. 3, fig. 3 is a schematic flow chart of a mobile booth detection method according to another embodiment of the present application.
In combination with the above, the image to be detected may include a multi-frame image in the target video, where the target video may be the above-mentioned video frame sequence, and the multi-frame image may be a continuous multi-frame image in the video frame sequence.
Referring to fig. 3, fig. 3 is a schematic flow chart of a mobile booth detection method according to another embodiment of the present application.
Specifically, the step S13 may include:
s31: and determining the booth evaluation value of the booth to be detected in each frame image based on the detection results of at least two objects of each frame image in the plurality of frame images.
Specifically, the currently detected image in the multi-frame images is an image to be detected, and the detection of at least two objects in the image to be detected can be performed according to the acquisition sequence of the multi-frame images, so as to respectively acquire the booth evaluation values corresponding to the respective frame images.
S32: and determining whether the booth to be detected is a mobile booth based on the booth evaluation value of the booth to be detected in each frame image and a preset booth evaluation value.
Specifically, the booth evaluation value of each frame image in the multi-frame image is compared with a preset booth evaluation value, and whether the booth to be detected in each frame image is a floating booth is determined.
For example, if 1000 frames of images are obtained in total, the booth evaluation value of each frame of image is compared with the preset booth evaluation value, and then whether the booth to be detected in each frame of image in the 1000 frames of images is a floating booth is obtained.
Referring to fig. 4, fig. 4 is a schematic flow chart of a mobile booth detection method according to another embodiment of the present application.
In some embodiments, the step S32 specifically includes:
s41: the cumulative number of frames of frame images whose booth evaluation value is greater than or equal to the preset booth evaluation value is determined.
Specifically, after the booth evaluation value of a frame is obtained, it is determined whether the booth evaluation value of the frame is greater than or equal to a preset booth evaluation value, and if the booth evaluation value of the frame is greater than the preset booth evaluation value, it indicates that the booth to be detected in the frame is a mobile booth more likely.
Further, the total number of image frames in which the booth evaluation value is greater than or equal to the preset booth evaluation value among the plurality of frame images is acquired. For example, the total image frame number is 1000 frames, and it is judged that the booth evaluation value of 800 frame images is greater than or equal to the preset booth evaluation value, then the integrated frame number of frame images having booth evaluation values greater than or equal to the preset booth evaluation value is 800 frames.
In some embodiments, step S41 is preceded by: judging whether the at least two objects comprise booth types or not; if not, updating the preset booth evaluation value and the first frame number threshold.
It should be understood that if at least two objects do not include a booth type, this indicates that no booth type is detected, and the detected object may not be associated with a booth. At this time, if it is determined whether the booth is a mobile booth, the preset booth evaluation value and the first frame number threshold value need to be further updated, so as to improve the accuracy of detection.
In some embodiments, the preset booth evaluation value and the first frame number threshold may be increased.
S42: and if the accumulated frame number is larger than the first frame number threshold value, determining that the booth to be detected is a mobile booth.
Wherein the first frame number threshold may be a larger frame number threshold. It should be understood that when the accumulated frame number is greater than the first frame number threshold, it indicates that the detected booth in the image frames is likely to be a floating booth, and indicates that there is a high possibility of a floating booth in the scene of acquiring the multi-frame image. At this time, the to-be-detected booth in each frame image is determined to be a mobile booth, that is, the to-be-detected booth in the image acquired in the detection scene is determined to be a mobile booth.
In other embodiments, when the ratio of the accumulated frame number to the obtained total frame number is greater than a preset ratio, the booth to be detected is determined to be a mobile booth.
It should be understood that the booth to be detected is determined as the floating booth by determining that the accumulated frame number is greater than the threshold value of the first frame number, and such a determination manner greatly improves the accuracy of detecting the floating booth, especially the stable floating booth in a specific scene.
For example, when a mobile booth passes through an image frame acquisition scene, a preset booth evaluation value in a few image frames acquired is greater than or equal to a preset booth evaluation value, but the booth to be detected is not taken as a mobile booth because the number of frames accumulated at this time is too small. At the moment, the mobile detection of the mobile booth is avoided, the accuracy of detecting whether the mobile booth is stable or not in a specific scene is guaranteed, and the effectiveness of law enforcement is guaranteed.
S43: if the accumulated frame number is larger than the second frame number threshold value, alarm information is sent out, and the second frame number threshold value is larger than the first frame number threshold value.
Because the second frame number threshold is greater than the first frame number threshold, when the accumulated frame number is greater than the second frame number threshold, it indicates that the booth evaluation value of a large number of image frames is greater than the preset booth evaluation value, and the probability that the booth to be detected is a mobile booth is high.
At the moment, the possibility that monitoring personnel detect the mobile booth is high through warning, the monitoring personnel can be noticed, and then the specific image acquisition scene is further checked, so that the effectiveness of law enforcement is improved.
Referring to fig. 5, fig. 5 is a schematic flow chart of a mobile booth detection method according to another embodiment of the present application.
In some embodiments, the step S41 includes:
s51: and judging whether the booth evaluation value of the booth to be detected of the image to be detected is greater than or equal to the preset booth evaluation value.
Specifically, the booth evaluation value of the booth to be detected is compared with the preset booth evaluation value, and whether the booth evaluation value of the booth to be detected is greater than the preset booth evaluation value is further determined.
If so, go to step S52, otherwise go to step S53.
S52: the accumulated frame number is increased by one frame.
And increasing the previous accumulated frame number by one frame, wherein the previous accumulated frame number is 800 frames, for example, and if the booth evaluation value in the image to be detected is detected to be greater than or equal to the preset booth evaluation value, adding one frame to the previous accumulated frame number to obtain an accumulated frame number of 801 frames.
S53: and judging whether the booth evaluation value of the booth to be detected of the image to be detected is less than one half of the preset booth evaluation value.
And when the booth evaluation value of the to-be-detected booth of the to-be-detected image is smaller than the preset booth evaluation value, further judging whether the booth evaluation value of the to-be-detected booth of the to-be-detected image is smaller than one half of the preset booth evaluation value. If so, go to step S54, otherwise, go to step S55.
S54: the accumulated frame number is decreased by one frame.
If the estimated value of the booth to be detected of the image to be detected is less than one half of the estimated value of the preset booth, it indicates that the probability of flowing the booth is very low when the booth to be detected in the image to be detected is detected.
It should be understood that if the booth evaluation value of the booth to be detected, which continuously detects multiple frame images, is less than one-half of the preset booth evaluation value, it means that there is very little possibility that there is a floating booth in the image acquisition scene. By reducing the accumulated frame number, the influence of the previous accumulated frame number on the current detection result can be eliminated, and the accuracy of the detection result is improved.
S55: the accumulated frame number remains unchanged.
If the booth evaluation value of the booth to be detected of the image to be detected is not less than one half of the preset booth evaluation value, it is indicated that the booth to be detected of the image to be detected cannot be evaluated as a mobile booth, but the number of accumulated frames of the suspected mobile booth of the booth to be detected remains unchanged, that is, the previous detection result is retained, and the evaluation of the booth to be detected is further performed by combining the subsequent detection result.
Referring to fig. 6-10, fig. 6 is a schematic view of a fruit booth of the present application, fig. 7 is another schematic view of a fruit booth of the present application, fig. 8 is a schematic view of a vegetable booth of the present application, fig. 9 is another schematic view of a vegetable booth of the present application, and fig. 10 is a schematic view of a dining booth of the present application.
In some embodiments, the booth types include fruit, vegetable, dining, and clothing booth types. Fig. 6 and 7 are schematic views of a fruit booth; fig. 8 and 9 are schematic views of vegetable booths; fig. 10 is a schematic view of a dining booth.
Specifically, the carrier type may include a first carrier and a second carrier, different carrier types correspond to different weights, and each carrier type may include a plurality of carriers. When one or more vectors belonging to the same vector type are detected, i.e. only one vector type is detected.
Wherein the loading capacity of the first carrier is greater than or equal to a preset loading capacity, and the loading capacity of the second carrier is less than the preset loading capacity. Thus, the first vector is a larger vector and the second vector is a smaller vector. For example, the first carrier may comprise a motor vehicle, tricycle, cart, etc., and the second carrier may comprise a storage basket, bag, box, etc.
With reference to fig. 6 and 10, if the booth has a motor vehicle, the booth has a first carrier. As shown in fig. 7 and 9, the booth has the cart and the tricycle, respectively, and the booth has the first carrier. As shown in fig. 8, the booth does not have the motor vehicle, tricycle and cart, and the booth does not have a large carrier. Wherein, a storage basket is also arranged in the figure 6, and a small carrier is arranged in the booth at the same time. Fig. 7, 8 and 9 show storage bags with small carriers in the booth.
Wherein the first carrier and the second carrier can be further refined in carrier type, the first carrier can comprise at least two first sub-carriers, and the weights of different first sub-carriers are different. The second carrier may comprise at least two second sub-carriers, different ones of the second sub-carriers having different weights. For example, the first carrier comprises two first sub-carriers, one first sub-carrier comprising a tricycle and the other first sub-carrier comprising a motor vehicle.
In some embodiments, if no booth type is detected, the weight of the first carrier is set greater than the weight of the accessory type, which is greater than the weight of the second carrier.
For example, the first carrier comprises two first sub-carriers, the first sub-carrier comprises a tricycle, the other first sub-carrier comprises a motor vehicle, the tricycle has a weight of 0.4, and the motor vehicle has a weight of 0.2. The weight of the accessory type is 0.2, where there is only one accessory type, including umbrellas, tables, chairs, etc. The second carrier comprises a storage basket, a storage bag and a storage box, and the weight is 0.1.
In some embodiments, the booth type is a fruit booth having a weight greater than a weight of the first carrier, the weight of the first carrier being greater than a weight of the second carrier, the weight of the second carrier being greater than or equal to a weight of the appendage type.
Specifically, the weight of the fruit booth was 0.4. The first carrier comprises three first sub-carriers, one first sub-carrier comprising a tricycle and a cart, respectively, the other first sub-carrier comprising a motor vehicle, the further first sub-carrier comprising a table, the tricycle and the cart having a weight of 0.3, the motor vehicle having a weight of 0.2, the table having a weight of 0.05. The second carrier comprises two second sub-carriers, wherein one second sub-carrier comprises a storage basket and a storage basket, the other second sub-carrier comprises a storage barrel, the weights of the storage basket and the storage basket are 0.2, and the weight of the storage barrel is 0.1. The appendage type is an occluding umbrella with a weight of 0.2.
It will be appreciated that since fruit is easily damaged, it is usually placed on a carrier. When the mobile stall is placed on a tricycle or a cart, the mobile stall is more likely to be placed on the tricycle or the cart; when the mobile booth is placed on a motor vehicle, the mobile booth is less likely to be used; when the mobile booth is placed on a table, the mobile booth is likely to be out of store, and the mobile booth is less likely to be operated. Therefore, when the booth type is a fruit booth, the first carrier is used as a main judgment condition, and the second carrier and the accessory type are used as a secondary condition.
In some embodiments, the booth type is a vegetable booth having a weight greater than a weight of the second carrier, the weight of the second carrier being greater than a weight of the first carrier, the weight of the first carrier being greater than or equal to a weight of the appendage type.
Specifically, the weight of the vegetable booth was 0.4. The second carrier comprises two second sub-carriers, wherein one second sub-carrier is a storage basket, a storage basket and a storage bag, the other second sub-carrier comprises a storage barrel, the weights of the storage basket, the storage basket and the storage bag are 0.3, and the weight of the storage barrel is 0.2. The first carrier is a tricycle, and the weight is 0.1; the appendage type is an occluding umbrella with a weight of 0.1.
It will be appreciated that due to the short shelf life of vegetables, commercial vendors typically sell small quantities, typically without the first carrier, and typically sell the vegetables directly on the ground or in baskets, bags and tubs. In this case, the second carrier is the primary determination condition, the first carrier and the sunshade are the secondary determination conditions, and the more the types of the second carriers are, the greater the possibility that the booth is a mobile booth is.
In some embodiments, the booth type is a dining booth, the weight of the first carrier is greater than the weight of the dining booth, the weight of the dining booth is greater than the weight of the accessory type, and the weight of the accessory type is greater than or equal to the weight of the second carrier.
Specifically, the weight of the dining booth is 0.3. The first carrier is a tricycle with a weight of 0.4. The accessory types are a gas tank and a sunshade umbrella, and the weight is 0.2; the second carrier comprises two second sub-carriers, wherein one second sub-carrier comprises a table and a chair, the other second sub-carrier comprises a storage barrel and a storage bag, the weights of the table and the chair are 0.2, and the weights of the storage barrel and the storage bag are 0.1.
It should be understood that when the booth type is a dining booth, the first carrier is more likely to be needed, and thus the first carrier is the main determination condition. At this time, the second carrier and the type of the accessories are secondary judgment conditions, and when the type of the accessories is a shading umbrella and a gas tank, the possibility that the booth is a mobile booth is high.
In some embodiments, the booth type is a dress booth, the weight of the booth type is greater than the weight of the booth type for the second carrier, the weight of the second carrier is greater than the weight of the first carrier, and the type of the first carrier is greater than or equal to the type of the appendage type.
Specifically, the weight of the clothing booth was 0.4. The second carrier comprises a storage basket, a storage bag and a storage box, and the weight of the storage basket, the storage bag and the storage box is 0.3. The first carrier comprises two first sub-carriers, wherein one first sub-carrier comprises a motor vehicle, the other second sub-carrier comprises a tricycle, the weight of the motor vehicle is 0.2, and the weight of the tricycle is 0.1. The accessory types include umbrella, table and chair, which are weighted 0.1.
It should be understood that when the booth type is a dress booth, the second carrier is the primary criterion, and the first carrier and the accessory type are the secondary criteria.
Referring to fig. 11, fig. 11 is a schematic diagram of a frame structure of the mobile booth detecting apparatus 20 of the present application.
The second aspect of the present application provides a mobile booth detecting apparatus 20, where the mobile booth detecting apparatus 20 includes a video frame acquiring module 201, an object detecting module 202, and a processing module 203, the object detecting module 202 is connected to the video frame acquiring module 201, and the processing module 203 is connected to the object detecting module 202.
The video frame acquiring module 201 is configured to acquire an image to be detected.
The target detection module 202 is configured to detect at least two objects of a booth type, a carrier type, and an attachment type of a booth to be detected in the image to be detected, and determine detection results of the at least two objects, where the carrier type is a type of a carrier carrying an article in the booth to be detected, and the attachment type is a type of an attachment associated with the booth to be detected.
The processing module 203 is configured to determine whether the booth to be detected is a mobile booth based on the detection results of the at least two objects.
It should be understood that, for a specific description of the corresponding steps performed by the modules, reference may be made to the flow booth detection method provided in the first aspect.
Referring to fig. 12, fig. 12 is a schematic diagram of a frame structure of an electronic device 30 according to the present application.
The third aspect of the present application provides an electronic device 30, which includes a processor 301 and a memory 302 coupled to each other, wherein the processor 301 is configured to execute program instructions stored in the memory 302 to implement the method for detecting a moving booth provided in the first aspect.
In one particular implementation scenario, the electronic device 30 may include, but is not limited to: a microcomputer, a server, and the electronic device 30 may also include a mobile device such as a notebook computer, a tablet computer, and the like, which is not limited herein.
Specifically, the processor 301 is configured to control itself and the memory 302 to implement the steps of the above-described embodiments of the method for detecting a rover. Processor 301 may also be referred to as a CPU (Central Processing Unit). The processor 301 may be an integrated circuit chip having signal processing capabilities. The Processor 301 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 301 may be commonly implemented by integrated circuit chips.
Referring to fig. 13, fig. 13 is a schematic diagram of a frame structure of a computer-readable storage medium 40 according to the present application.
A fourth aspect of the present application provides a computer readable storage medium 40 having stored thereon program instructions 401, the program instructions 401 when executed by a processor implementing the method for detecting a flow booth as provided by the first aspect described above.
The computer-readable storage medium 40 may include: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (14)
1. A method for mobile booth inspection, the method comprising:
acquiring an image to be detected;
detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected, and determining the detection results of the at least two objects; the carrier type is the type of the carrier for carrying articles in the to-be-detected booth, and the accessory type is the type of the accessory associated with the to-be-detected booth;
and determining whether the booth to be detected is a mobile booth or not based on the detection results of the at least two objects.
2. The method of claim 1, wherein said determining whether the booth to be tested is a mobile booth based on the results of the testing of the at least two objects comprises:
determining a booth evaluation value of the booth to be detected based on the detection results of the at least two objects;
and if the estimated value of the booth is determined to be larger than or equal to the estimated value of the preset booth, determining that the booth to be detected in the image to be detected is the mobile booth.
3. The method as claimed in claim 2, wherein determining booth evaluation values of the booth to be inspected based on the detection results of the at least two objects comprises:
and determining the booth evaluation value of the booth to be detected based on the detection results of the at least two objects and the weights corresponding to the at least two objects.
4. The method according to claim 2 or 3, wherein the image to be detected comprises a plurality of frames of images in the target video;
the determining the booth evaluation value of the booth to be detected in the image to be detected based on the detection results of the at least two objects includes:
determining a booth evaluation value of the booth to be detected in each frame image based on detection results of at least two objects in each frame image in the multiple frame images;
and determining whether the to-be-detected booth is the mobile booth or not based on the booth evaluation value of the to-be-detected booth and a preset booth evaluation value in each frame image.
5. The method as claimed in claim 4, wherein said determining whether said booth to be detected is said floating booth based on said booth evaluation value of said booth to be detected and a preset booth evaluation value in said each frame image comprises:
determining the accumulated frame number of the frame images of which the booth evaluation values are greater than or equal to the preset booth evaluation value;
and if the accumulated frame number is larger than a first frame number threshold value, determining that the to-be-detected booth is the mobile booth.
6. The method as claimed in claim 5, wherein after determining that the booth to be tested is the mobile booth, further comprising:
and if the accumulated frame number is determined to be greater than a second frame number threshold, sending alarm information, wherein the second frame number threshold is greater than the first frame number threshold.
7. The method of claim 5,
the determining the accumulated frame number of the frame image with the booth evaluation value being greater than or equal to the preset booth evaluation value includes:
judging whether the booth evaluation value of the booth to be detected of the image to be detected is greater than or equal to the preset booth evaluation value;
if yes, increasing one frame by the accumulated frame number;
if not, judging whether the booth evaluation value of the to-be-detected booth of the to-be-detected image is less than one half of the preset booth evaluation value or not;
if the booth evaluation value of the booth to be detected of the image to be detected is less than one half of the preset booth evaluation value, reducing the accumulated frame number by one frame;
and if the booth evaluation value of the booth to be detected of the image to be detected is not less than one half of the preset booth evaluation value, keeping the accumulated frame number unchanged.
8. The method of claim 5, wherein prior to determining the cumulative number of frames of frame images for which the booth evaluation value is greater than or equal to the preset booth evaluation value, further comprising:
determining whether the at least two objects include the booth type;
and if not, updating the preset booth evaluation value and the first frame number threshold.
9. The method of claim 3, wherein said at least two objects include a booth type and a carrier type of said booth to be tested;
the booth type comprises at least one of a fruit booth, a vegetable booth, a catering booth and a clothing booth; the carrier types comprise a first carrier and a second carrier; the loading capacity of the first carrier is greater than or equal to a preset loading capacity, and the loading capacity of the second carrier is less than the preset loading capacity.
10. The method of claim 9,
the booth type is a fruit booth, the weight of the fruit booth is greater than the weight of the first carrier, the weight of the first carrier is greater than the weight of the second carrier, and the weight of the second carrier is greater than or equal to the weight of the accessory type; or
The booth type is a vegetable booth, the weight of the vegetable booth is greater than the weight of the second carrier, the weight of the second carrier is greater than the weight of the first carrier, and the weight of the first carrier is greater than or equal to the weight of the accessory type; or
The booth type is a catering booth, the weight of the first carrier is greater than that of the catering booth, the weight of the catering booth is greater than that of the accessory type, and the weight of the accessory is greater than or equal to that of the second carrier; or
The booth type is a clothing booth, the weight of the booth type is greater than that of the second carrier, the weight of the second carrier is greater than that of the first carrier, and the type of the first carrier is greater than or equal to that of the accessory type.
11. The method of claim 3, wherein the at least two objects comprise the carrier type and the adjunct type, the carrier type comprising a first carrier having a loading capacity greater than or equal to a preset loading capacity and a second carrier having a loading capacity less than the preset loading capacity; the weight of the first carrier is greater than the weight of the adjunct type, which is greater than the weight of the second carrier.
12. A mobile booth testing apparatus, the apparatus comprising:
the video frame acquisition module is used for acquiring an image to be detected;
the target detection module is connected with the video frame acquisition module and is used for detecting at least two objects in the booth type, the carrier type and the accessory type of the booth to be detected in the image to be detected and determining the detection results of the at least two objects, wherein the carrier type is the type of a carrier for carrying articles in the booth to be detected, and the accessory type is the type of an accessory associated with the booth to be detected;
and the processing module is connected with the target detection module and determines whether the to-be-detected booth is a mobile booth or not based on the detection results of the at least two objects.
13. An electronic device comprising a processor and a memory coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the method for mobile booth detection of any of claims 1-11.
14. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, carry out the method of mobile booth detection of any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110932893.3A CN113723226A (en) | 2021-08-13 | 2021-08-13 | Mobile stall detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110932893.3A CN113723226A (en) | 2021-08-13 | 2021-08-13 | Mobile stall detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113723226A true CN113723226A (en) | 2021-11-30 |
Family
ID=78675853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110932893.3A Pending CN113723226A (en) | 2021-08-13 | 2021-08-13 | Mobile stall detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723226A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130258107A1 (en) * | 2012-03-29 | 2013-10-03 | Xerox Corporation | Method of determining parking lot occupancy from digital camera images |
| US20140376769A1 (en) * | 2013-06-20 | 2014-12-25 | Xerox Corporation | Method for detecting large size and passenger vehicles from fixed cameras |
| CN110363220A (en) * | 2019-06-11 | 2019-10-22 | 北京奇艺世纪科技有限公司 | Behavior category detection method, device, electronic equipment and computer-readable medium |
| CN111126252A (en) * | 2019-12-20 | 2020-05-08 | 浙江大华技术股份有限公司 | Stall behavior detection method and related device |
| CN111739009A (en) * | 2020-06-23 | 2020-10-02 | 北京金山云网络技术有限公司 | Image detection method and device, electronic equipment and storage medium |
| CN112749978A (en) * | 2020-12-31 | 2021-05-04 | 百度在线网络技术（北京）有限公司 | Detection method, apparatus, device, storage medium, and program product |
-
2021
- 2021-08-13 CN CN202110932893.3A patent/CN113723226A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130258107A1 (en) * | 2012-03-29 | 2013-10-03 | Xerox Corporation | Method of determining parking lot occupancy from digital camera images |
| US20140376769A1 (en) * | 2013-06-20 | 2014-12-25 | Xerox Corporation | Method for detecting large size and passenger vehicles from fixed cameras |
| CN110363220A (en) * | 2019-06-11 | 2019-10-22 | 北京奇艺世纪科技有限公司 | Behavior category detection method, device, electronic equipment and computer-readable medium |
| CN111126252A (en) * | 2019-12-20 | 2020-05-08 | 浙江大华技术股份有限公司 | Stall behavior detection method and related device |
| CN111739009A (en) * | 2020-06-23 | 2020-10-02 | 北京金山云网络技术有限公司 | Image detection method and device, electronic equipment and storage medium |
| CN112749978A (en) * | 2020-12-31 | 2021-05-04 | 百度在线网络技术（北京）有限公司 | Detection method, apparatus, device, storage medium, and program product |
Non-Patent Citations (2)
| Title |
|---|
| ZAJAM, A 等: "Detecting Efficient Parking Space Using Smart Parking", 2018 9TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT), 18 October 2018 (2018-10-18), pages 1 - 7 * |
| 宋乐陶 等: "基于深度卷积神经网络的非法摊位检测", 现代计算机, vol. 2018, no. 24, 25 August 2018 (2018-08-25), pages 65 - 71 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126252B (en) | Swing behavior detection method and related device | |
| US20220292358A1 (en) | Method and system for tracking an object | |
| Brutzer et al. | Evaluation of background subtraction techniques for video surveillance | |
| CN105913040B (en) | The real-time pedestrian detecting system of dual camera under the conditions of noctovision | |
| US9547866B2 (en) | Methods and apparatus to estimate demography based on aerial images | |
| CN104376741B (en) | Parking lot state detection method and system | |
| Lwowski et al. | Pedestrian detection system for smart communities using deep convolutional neural networks | |
| CN107071736B (en) | Shared bicycle data acquisition platform | |
| CN107085229B (en) | Collecting method | |
| CN104766079B (en) | A kind of remote method for detecting infrared puniness target | |
| CN106611510A (en) | Parking stall detecting device and method and electronic equipment | |
| CN106570015A (en) | Image searching method and device | |
| CN113723226A (en) | Mobile stall detection method and device, electronic equipment and storage medium | |
| US11919160B2 (en) | Fall detection and assistance | |
| CN107784507A (en) | Doubtful infringement commodity method for early warning and device, computer-readable storage medium and equipment | |
| JPWO2020044510A1 (en) | Computer systems, object detection methods and programs | |
| CN112347818B (en) | Method and device for screening difficult sample images of video target detection model | |
| CN107977764A (en) | Index file generation method, index file distributor information query method, index file generation device, distributor information query device and server | |
| CN110096946A (en) | A kind of self-service system merged based on pressure sensitivity and vision | |
| CN105184245B (en) | A kind of crowd density estimation method of multiple features fusion | |
| Vildjiounaite et al. | Predicting consumers' locations in dynamic environments via 3D sensor-based tracking | |
| Yeh et al. | Fast salient object detection through efficient subwindow search | |
| Rout et al. | A novel five-frame difference scheme for local change detection in underwater video | |
| Vasu et al. | Vehicle tracking using a human-vision-based model of visual similarity | |
| Hachicha et al. | Multi-temporal SAR classification according to change detection operators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |