CN110866505A - Method and device for detecting luggage consignment intrusion - Google Patents
Method and device for detecting luggage consignment intrusion Download PDFInfo
- Publication number
- CN110866505A CN110866505A CN201911140460.3A CN201911140460A CN110866505A CN 110866505 A CN110866505 A CN 110866505A CN 201911140460 A CN201911140460 A CN 201911140460A CN 110866505 A CN110866505 A CN 110866505A
- Authority
- CN
- China
- Prior art keywords
- image
- baggage
- determining whether
- view
- luggage
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/32—Normalisation of the pattern dimensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
The application discloses a method and a device for detecting luggage consignment intrusion, comprising the following steps: acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting a depth camera; determining a baggage identification look-down image based on the look-down depth image; determining a baggage identification side view image based on the side view depth image; and determining whether the luggage has an invader or not by adopting an image contour recognition algorithm based on the luggage recognition top view image and the luggage recognition side view image. According to the method and the device for detecting the baggage consignment intrusion, the depth image of the baggage is obtained through the depth camera, whether the intruder exists in the baggage area is determined through the identification of the baggage in the depth image and the identification of the outline, and then corresponding prompt control is performed, so that the accurate baggage consignment data can be obtained, and the use experience of passengers is improved.
Description
Technical Field
The invention relates to a data processing technology, in particular to a method and a device for detecting luggage consignment intrusion.
Background
With the increasing popularity of intelligent service concepts, airlines have also been trying to provide various intelligent services in recent years, and one of them is self-service baggage consignment.
During self-service baggage consignment, a passenger places baggage on a conveyor and a detection system detects the size and weight of the baggage to complete the acquisition of consignment data. In practice, however, it is often the case that the passenger does not consciously affect the height and weight measurements of the baggage, for example, the passenger may be holding their hand on the handle of the baggage and thereby weighing or losing the weight of the baggage. Therefore, it is desirable to provide a baggage consignment intrusion detection method so as to timely identify the situation of external factor interference detection, thereby obtaining accurate baggage consignment data and improving the efficiency and experience of self-service baggage consignment service.
Disclosure of Invention
Accordingly, the present invention is directed to a method for overcoming the problems in the art.
In order to achieve the purpose, the invention provides the following technical scheme:
a baggage consignment intrusion detection method, comprising:
acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting a depth camera;
determining a baggage identification look-down image based on the look-down depth image;
determining a baggage identification side view image based on the side view depth image;
and determining whether the luggage has an invader or not by adopting an image contour recognition algorithm based on the luggage recognition top view image and the luggage recognition side view image.
Optionally, the determining whether the baggage has an intruder by using an image contour recognition algorithm based on the baggage recognition top view image and the baggage recognition side view image includes:
selecting one of the baggage identification top view image and the baggage identification side view image as a first image and the other as a second image;
determining whether a boundary of the first image has something identified as part of baggage;
if so, determining whether an external object invades a preset area in the first image by adopting an image contour recognition algorithm;
if yes, determining whether the external object is in contact with the luggage or not by adopting an image contour recognition algorithm based on the second image;
and if so, determining that the invader exists.
Optionally, the determining, by using an image contour recognition algorithm, whether an external object invades a preset area in the first image includes:
determining whether the number of contours in the first image is equal to 1 by adopting an image contour identification algorithm;
the determining whether the external object is in contact with the baggage by using an image contour recognition algorithm based on the second image comprises:
determining whether the number of contours in the second image is equal to 1 using an image contour recognition algorithm.
Optionally, before the determining whether the object identified as the baggage part exists at the boundary of the first image, the method further includes:
preprocessing the first image to obtain a first preprocessed image;
said determining whether the boundary of the first image has something identified as part of baggage includes:
determining whether a boundary of the first pre-processed image has something identified as part of baggage.
Optionally, before determining whether the external object is in contact with the baggage by using an image contour recognition algorithm based on the second image, the method further includes:
preprocessing the second image to obtain a second preprocessed image;
determining whether the foreign object is in contact with the baggage by using an image contour recognition algorithm based on the second image, including:
and determining whether the number of contours in the second preprocessed image is equal to 1 by adopting an image contour identification algorithm.
Optionally, the preprocessing the first image includes:
and performing cutting processing on the first image, and extracting a part containing the luggage in the first image.
Optionally, the preprocessing the first image or the preprocessing the second image includes:
and carrying out color mixing processing and noise reduction processing on the first image or the second image.
Optionally, the performing color matching and noise reduction on the first image or the second image includes:
turning white the thing identified as a part of the baggage in the first image or the second image, and turning black the other part;
and carrying out noise reduction treatment on the first image or the second image after color mixing by adopting expansion, corrosion and/or median blurring technology.
Optionally, the determining a baggage identification overhead image based on the overhead depth image includes:
determining a baggage identification top view image based on the top view depth map and a distance between a camera taking the top view depth map and the conveyor belt;
the determining a baggage identification side view image based on the side view depth image comprises:
determining a baggage identification side view image based on the side view depth map and a distance of a camera capturing the side view depth map from the conveyor belt edge.
A baggage check-in intrusion detection device comprising:
the image acquisition module is used for acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting the depth camera;
an overhead baggage identification module to determine an overhead image based on the overhead depth image;
a side view baggage identification module to determine a baggage identification side view image based on the side view depth image;
and the intrusion determination module is used for determining whether the baggage has an intruder or not by adopting an image contour recognition algorithm based on the baggage recognition top view image and the baggage recognition side view image.
Compared with the prior art, the embodiment of the invention discloses a method and a device for detecting the intrusion of consignment of luggage, which comprises the following steps: acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting a depth camera; determining a baggage identification look-down image based on the look-down depth image; determining a baggage identification side view image based on the side view depth image; and determining whether the luggage has an invader or not by adopting an image contour recognition algorithm based on the luggage recognition top view image and the luggage recognition side view image. According to the method and the device for detecting the baggage consignment intrusion, the depth image of the baggage is obtained through the depth camera, whether the intruder exists in the baggage area is determined through the identification of the baggage in the depth image and the identification of the outline, and then corresponding prompt control is performed, so that the accurate baggage consignment data can be obtained, and the use experience of passengers is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a baggage consignment intrusion detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for determining whether an intruding object exists in the baggage according to an embodiment of the present invention;
FIG. 3a is a schematic view of an image of an intrusion situation according to an embodiment of the present invention;
FIG. 3b is a schematic view of a top view outline recognition disclosed in the embodiments of the present invention;
FIG. 3c is a schematic side view outline recognition according to an embodiment of the present disclosure;
FIG. 4a is a schematic diagram of a picture before denoising processing according to an embodiment of the present invention;
FIG. 4b is a schematic diagram of a noise-reduced picture according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a baggage consignment intrusion detection apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an intrusion determination module according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
Fig. 1 is a flowchart of a baggage consignment intrusion detection method according to an embodiment of the present invention, and referring to fig. 1, the baggage consignment intrusion detection method may include:
step 101: a depth camera is used to acquire a top view depth image and a side view depth image of a baggage positioned on a conveyor belt.
In this embodiment, since the region where the baggage is placed needs to be identified, that is, the distance between the camera and the object needs to be acquired, the depth camera needs to be used to acquire the baggage image. Specifically, a 3D depth camera may be arranged right above a conveyor belt of the self-service baggage handling device for collecting a top-view depth map of baggage; in addition, a 3D depth camera is arranged on the front side of the conveyor belt and used for collecting a side-view depth map of the luggage.
Step 102: determining a baggage identification look-down image based on the look-down depth image.
In one illustrative example, the determining a baggage identification overhead image based on the overhead depth image may include: determining a baggage identification top view image based on the top view depth map and a distance between a camera taking the top view depth map and the conveyor belt. E.g., the depth camera is a distance d1 from the conveyor belt, then the image in the depth range between the conveyor belt and the camera is determined to be a baggage identification clothing image.
Step 103: determining a baggage identification side view image based on the side view depth image.
In one illustrative example, the determining a baggage identification side view image based on the side view depth image may include: determining a baggage identification side view image based on the side view depth map and a distance of a camera capturing the side view depth map from the conveyor belt edge. The identification process is similar to the process of determining the baggage identification overhead image.
Step 104: and determining whether the luggage has an invader or not by adopting an image contour recognition algorithm based on the luggage recognition top view image and the luggage recognition side view image.
Whether an external object invades a designated area (such as an area above a conveyor belt) of the self-service luggage consignment device or not can be determined through an image contour recognition algorithm, and whether the external invaded object is in contact with luggage or not can be further recognized. And (4) integrating the recognition result of the image contour recognition algorithm to determine whether the invader exists in the luggage area. In the following embodiments, a detailed description will be given of a specific process for determining whether an intruding object exists, and will not be described herein too much.
In this embodiment, the baggage consignment intrusion detection method obtains the depth image of the baggage through the depth camera, determines whether the baggage area has an intruding object or not through the identification of the baggage in the depth image and the identification of the outline, and then makes corresponding prompt control, so as to be beneficial to obtaining accurate baggage consignment data and improve the use experience of passengers.
Fig. 2 is a flowchart illustrating a method for determining whether an intruding object exists in the baggage according to an embodiment of the present invention, as shown in fig. 2, the method may include:
step 201: one of the baggage identification top view image and the baggage identification side view image is selected as a first image and the other is selected as a second image.
Since the two acquired images are depth images and only the orientations of the acquired images are different, any one of the two acquired images can be selected first to make a preliminary judgment image and the other one can be selected as a determination judgment image.
Step 202: it is determined whether the boundary of the first image has something identified as part of the baggage and, if so, step 203 is entered.
Since the depth camera is configured to only include the collection view angle of the corresponding area of the conveyor belt when installed, if an external invader exists in the corresponding area above the conveyor belt, then there is also certainly an object in the first image boundary that is recognized by the system as a baggage portion. If the boundary of the first image has an object identified as part of the baggage, it indicates that the baggage may be invaded by an external object. Fig. 3a is a schematic image of an intrusion situation, fig. 3b is a schematic top view perspective contour recognition, and fig. 3c is a schematic side view perspective contour recognition, which can be understood in conjunction with the three figures, in which the arms of a person can be recognized at the image boundaries.
Step 203: and determining whether an external object invades a preset area in the first image by adopting an image contour recognition algorithm, and if so, entering step 204.
In some cases, even if there is an object identified as a part of the baggage in the boundary of the first image, the object may not contact the baggage, and this is not an intrusion situation, so it is necessary to determine whether there is an intrusion of an external object into a preset area in the first image. The preset area may be, for example, an area directly above or an area directly beside the baggage.
Step 204: and determining whether the external object is in contact with the luggage or not by adopting an image contour recognition algorithm based on the second image, and if so, entering step 205.
When it is determined that the external object intrudes into the preset area in the first image, it is necessary to further determine whether the external object contacts the baggage, for example, if the human hand is above the baggage in a top view, but it is not possible to determine whether the human hand contacts the baggage, in which case it is necessary to see whether the human hand contacts the baggage from a side.
Step 205: the presence of an intruder is determined.
If an external object invades a preset area in the first image and the external object is in contact with the luggage, the condition that the luggage is invaded can be determined.
This embodiment details the process of determining whether an intruding object exists in the baggage, which is helpful for those skilled in the art to better understand the present application. In this embodiment, the case where the judgment or determination result is that there is no contact or no contact is not described, and the case where there is no intrusion of the baggage is described.
In the above embodiment, the determining, by using an image contour recognition algorithm, whether an external object invades a preset area in the first image may include: an image contour recognition algorithm is used to determine whether the number of contours in the first image is equal to 1. If the number is equal to 1, it indicates that, from the shooting perspective of the first image, an external object coincides with the baggage, that is, the external object invades the preset area.
The determining whether the external object is in contact with the baggage by using an image contour recognition algorithm based on the second image may include: determining whether the number of contours in the second image is equal to 1 using an image contour recognition algorithm. If the value is equal to 1, the external object is in contact with the luggage. This can be understood in connection with fig. 3.
In the above embodiment, before the determining whether the object identified as the baggage part exists at the boundary of the first image, the method may further include: preprocessing the first image to obtain a first preprocessed image; the determining whether the boundary of the first image has something identified as part of baggage may include: determining whether a boundary of the first pre-processed image has something identified as part of baggage.
Correspondingly, before the determining whether the external object is in contact with the baggage by using an image contour recognition algorithm based on the second image, the method may further include: preprocessing the second image to obtain a second preprocessed image; the determining whether the foreign object is in contact with the baggage using an image contour recognition algorithm based on the second image may include: and determining whether the number of contours in the second preprocessed image is equal to 1 by adopting an image contour identification algorithm.
The preprocessing of the first image and the second image can enable the subsequent correlation processing and identification for the images to be more accurately carried out. For example, the preprocessing of the first image may include performing a cropping process on the first image to extract a portion of the first image that includes baggage. In practical applications, since the wide angle of the camera may be too large, the generated picture needs to be subjected to boundary clipping, for example, 80% of the original picture is retained.
In other implementations, the preprocessing the first image or the preprocessing the second image may include: and carrying out color mixing processing and noise reduction processing on the first image or the second image. The method specifically comprises the following steps: turning white the thing identified as a part of the baggage in the first image or the second image, and turning black the other part; and carrying out noise reduction treatment on the first image or the second image after color mixing by adopting expansion, corrosion and/or median blurring technology.
Fig. 4a is a schematic diagram of a picture before noise reduction processing disclosed in the embodiment of the present invention, and fig. 4b is a schematic diagram of a picture after noise reduction processing disclosed in the embodiment of the present invention, so that it can be seen that noise reduction processing can remove many small noise points in an image, so that a subsequent contour recognition effect is better.
In one particular implementation, a baggage consignment intrusion detection method may include the following:
deploying two 3D cameras on a self-service baggage machine:
1.1 deploy a first 3D camera (camera 1) directly above the baggage detection zone.
1.2 deploy a second 3D camera (camera 2) directly to the side of the baggage detection zone (camera towards the passenger).
Judging whether an external object invades the designated area:
2.1 the distance d1(cm) to the conveyor belt was measured by the camera 1 without placing an object on the conveyor belt.
2.2 put the baggage on the conveyer belt, use the camera 1 to grab the picture of the baggage detection area and generate the distance matrix (each element in the distance matrix corresponds to each pixel of the depth image one-to-one, representing the distance between this pixel and the camera), in order to prevent other foreign objects attached on the conveyer belt from interfering the intrusion detection result, in this embodiment, the object above 5cm of the conveyer belt is regarded as the baggage to be detected, otherwise, it will not be recognized as a part of the baggage.
2.3 according to the conclusion provided by 2.2, the baggage to be detected is reflected in the generated distance matrix at a distance which should be less than (d1-5) cm (the higher the height of the object, the closer the distance to the camera, in this embodiment the object with a height greater than 5cm is identified as baggage, the camera 1 has a distance d1 to the conveyer belt, the object is placed on the baggage conveyer belt, and therefore the distance of the part with a height greater than 5cm in the distance matrix should be less than (d1-5) cm).
2.4 in order to make the result more accurate, the generated black and white picture needs to be preprocessed, and the original black and white picture can be denoised by using methods of expansion, corrosion and median blurring. In addition, due to the large wide angle of the camera, the generated picture can be subjected to boundary clipping, for example, 80% of the original picture is reserved.
2.5, scanning the image boundary generated in the step 2.4, if any boundary has a white part, indicating that an object invades the detection area from the outside, otherwise, no object invades the detection area. And if the external invasion is detected, carrying out outline recognition on the white part (the luggage part) of the processed picture in the step 2.4. If the number of the outlines in the picture is equal to 1, it is indicated that the external invaded object and the luggage are overlapped in the overlooking angle, and in this case, whether the two are in contact or not cannot be judged, and the step 3 needs to be performed. On the contrary, if the number of the outlines in the picture is more than or equal to 2, the number of the outlines in the picture can indicate that a plurality of outlines exist besides the luggage, but the outlines do not contact the luggage, it can be judged that the external invaded object does not contact the luggage, and the self-service luggage consignment system operates normally.
3. Judging whether the external object is in contact with the luggage
3.1 with 2.5 conclusions (overlooking that the intruding object and the baggage are already overlapping), with camera 2, keep the pixels within 100cm and convert them into a depth matrix (the width of the conveyor belt is usually 80cm, avoiding that objects too far away will affect the result).
3.2 Using the method of 2.5, if the outline of the generated side view black and white picture is equal to 1, which indicates that the object invaded from the outside contacts with the luggage, the self-service luggage consignment system will prompt the outside invasion and require the passengers to place the luggage again according to the regulations. Otherwise, the external invading object is not contacted with the luggage, and the self-service luggage consignment system operates normally.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present invention is not limited by the illustrated ordering of acts, as some steps may occur in other orders or concurrently with other steps in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
The method is described in detail in the embodiments disclosed above, and the method of the present invention can be implemented by various types of apparatuses, so that the present invention also discloses an apparatus, and the following detailed description will be given of specific embodiments.
Fig. 5 is a schematic structural diagram of a baggage check-in device according to an embodiment of the present invention, and as shown in fig. 5, the baggage check-in device 50 may include:
an image obtaining module 501, configured to obtain a top view depth image and a side view depth image of the baggage on the conveyer belt by using the depth camera.
In this embodiment, since the region where the baggage is placed needs to be identified, that is, the distance between the camera and the object needs to be acquired, the depth camera needs to be used to acquire the baggage image. Specifically, a 3D depth camera may be arranged right above a conveyor belt of the self-service baggage handling device for collecting a top-view depth map of baggage; in addition, a 3D depth camera is arranged on the front side of the conveyor belt and used for collecting a side-view depth map of the luggage.
An overhead baggage identification module 502 for determining a baggage identification overhead image based on the overhead depth image.
In one illustrative example, the overhead baggage identification module 502 may be specifically configured to: determining a baggage identification top view image based on the top view depth map and a distance between a camera taking the top view depth map and the conveyor belt. E.g., the depth camera is a distance d1 from the conveyor belt, then the image in the depth range between the conveyor belt and the camera is determined to be a baggage identification clothing image.
A side view baggage identification module 503 for determining a baggage identification side view image based on the side view depth image.
In one illustrative example, the side-looking baggage identification module 503 may be specifically configured to: determining a baggage identification side view image based on the side view depth map and a distance of a camera capturing the side view depth map from the conveyor belt edge. The identification process is similar to the process of determining the baggage identification overhead image.
An intrusion determination module 504, configured to determine whether an intruder is present in the baggage by using an image contour recognition algorithm based on the baggage recognition top view image and the baggage recognition side view image.
Whether an external object invades a designated area (such as an area above a conveyor belt) of the self-service luggage consignment device or not can be determined through an image contour recognition algorithm, and whether the external invaded object is in contact with luggage or not can be further recognized. And (4) integrating the recognition result of the image contour recognition algorithm to determine whether the invader exists in the luggage area.
In this embodiment, luggage check-in detection device acquires the depth image of luggage through the depth camera, confirms whether there is the invading thing in the luggage region through the discernment and the discernment of profile to luggage in the depth image, and then makes corresponding prompt control, is favorable to acquireing accurate luggage check-in data, promotes passenger's use and experiences.
Fig. 6 is a schematic structural diagram of an intrusion determination module according to an embodiment of the present invention, and as shown in fig. 6, the intrusion determination module 504 may include:
an image selection module 601, configured to select one of the baggage identification top view image and the baggage identification side view image as a first image and the other as a second image.
A boundary determination module 602, configured to determine whether there is a thing identified as a baggage portion at the boundary of the first image.
The outline recognition module 603 is configured to, when the boundary determination module determines that the object identified as the baggage part exists in the boundary of the first image, determine whether an external object invades a preset area in the first image by using an image outline recognition algorithm; and under the condition that the first image is determined to have the external object invaded into the preset area, determining whether the external object is in contact with the luggage or not by adopting an image contour recognition algorithm based on the second image.
And an intrusion judgment module 604, configured to determine that an intruder exists when the contour recognition module determines that the external object is in contact with the baggage.
This embodiment details the process of determining whether an intruding object exists in the baggage, which is helpful for those skilled in the art to better understand the present application. In this embodiment, the case where the judgment or determination result is that there is no contact or no contact is not described, and the case where there is no intrusion of the baggage is described.
Specific and different implementations of a certain module in the baggage consignment intrusion detection apparatus are described in the method embodiment, and specific contents may refer to corresponding parts of the method embodiment, and are not repeated herein.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A baggage consignment intrusion detection method, comprising:
acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting a depth camera;
determining a baggage identification look-down image based on the look-down depth image;
determining a baggage identification side view image based on the side view depth image;
and determining whether the luggage has an invader or not by adopting an image contour recognition algorithm based on the luggage recognition top view image and the luggage recognition side view image.
2. The baggage consignment intrusion detection method according to claim 1, wherein said determining whether an intruder is present in the baggage using an image contour recognition algorithm based on the baggage recognition top view image and the baggage recognition side view image comprises:
selecting one of the baggage identification top view image and the baggage identification side view image as a first image and the other as a second image;
determining whether a boundary of the first image has something identified as part of baggage;
if so, determining whether an external object invades a preset area in the first image by adopting an image contour recognition algorithm;
if yes, determining whether the external object is in contact with the luggage or not by adopting an image contour recognition algorithm based on the second image;
and if so, determining that the invader exists.
3. The method of claim 2, wherein the determining whether the external object intrudes into the predetermined area in the first image by using an image contour recognition algorithm comprises:
determining whether the number of contours in the first image is equal to 1 by adopting an image contour identification algorithm;
the determining whether the external object is in contact with the baggage by using an image contour recognition algorithm based on the second image comprises:
determining whether the number of contours in the second image is equal to 1 using an image contour recognition algorithm.
4. The baggage consignment intrusion detection method according to claim 3, further comprising, before said determining whether the boundary of said first image has something identified as part of baggage:
preprocessing the first image to obtain a first preprocessed image;
said determining whether the boundary of the first image has something identified as part of baggage includes:
determining whether a boundary of the first pre-processed image has something identified as part of baggage.
5. The baggage consignment intrusion detection method according to claim 3, further comprising, before said determining whether the foreign object is in contact with the baggage using an image contour recognition algorithm based on the second image:
preprocessing the second image to obtain a second preprocessed image;
determining whether the foreign object is in contact with the baggage by using an image contour recognition algorithm based on the second image, including:
and determining whether the number of contours in the second preprocessed image is equal to 1 by adopting an image contour identification algorithm.
6. The baggage consignment intrusion detection method according to claim 4, wherein the preprocessing the first image comprises:
and performing cutting processing on the first image, and extracting a part containing the luggage in the first image.
7. The baggage consignment intrusion detection method according to claim 4 or 5, wherein the preprocessing the first image or the preprocessing the second image comprises:
and carrying out color mixing processing and noise reduction processing on the first image or the second image.
8. The baggage consignment intrusion detection method according to claim 7, wherein the performing of the toning process and the denoising process on the first image or the second image includes:
turning white the thing identified as a part of the baggage in the first image or the second image, and turning black the other part;
and carrying out noise reduction treatment on the first image or the second image after color mixing by adopting expansion, corrosion and/or median blurring technology.
9. The baggage consignment intrusion detection method according to claim 1, wherein said determining a baggage identification top view image based on said top view depth image comprises:
determining a baggage identification top view image based on the top view depth map and a distance between a camera taking the top view depth map and the conveyor belt;
the determining a baggage identification side view image based on the side view depth image comprises:
determining a baggage identification side view image based on the side view depth map and a distance of a camera capturing the side view depth map from the conveyor belt edge.
10. A baggage check-in intrusion detection device, comprising:
the image acquisition module is used for acquiring a top view depth image and a side view depth image of the luggage on the conveyor belt by adopting the depth camera;
an overhead baggage identification module to determine an overhead image based on the overhead depth image;
a side view baggage identification module to determine a baggage identification side view image based on the side view depth image;
and the intrusion determination module is used for determining whether the baggage has an intruder or not by adopting an image contour recognition algorithm based on the baggage recognition top view image and the baggage recognition side view image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911140460.3A CN110866505A (en) | 2019-11-20 | 2019-11-20 | Method and device for detecting luggage consignment intrusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911140460.3A CN110866505A (en) | 2019-11-20 | 2019-11-20 | Method and device for detecting luggage consignment intrusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866505A true CN110866505A (en) | 2020-03-06 |
Family
ID=69655728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911140460.3A Pending CN110866505A (en) | 2019-11-20 | 2019-11-20 | Method and device for detecting luggage consignment intrusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866505A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308071A (en) * | 2020-11-02 | 2021-02-02 | 沈阳民航东北凯亚有限公司 | Intrusion detection method and device for consigning luggage and electronic equipment |
| CN113780199A (en) * | 2021-09-15 | 2021-12-10 | 江苏迪赛司自动化工程有限公司 | Double-vision imaging device and intelligent identification method for belt-transported foreign object target |
| CN115661668A (en) * | 2022-12-13 | 2023-01-31 | 山东大学 | Method, device, medium and equipment for identifying flowers to be pollinated of pepper flowers |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714610A (en) * | 2014-01-17 | 2014-04-09 | 北京纳兰德科技有限公司 | Self-help luggage equipment and self-help luggage system as well as installation method |
| CN104867221A (en) * | 2015-06-04 | 2015-08-26 | 北京纳兰德科技有限公司 | Self-service baggage checking system |
| CN204856678U (en) * | 2015-08-19 | 2015-12-09 | 上海民航华东凯亚系统集成有限公司 | Self -service luggage delivery system |
| CN106056056A (en) * | 2016-05-23 | 2016-10-26 | 浙江大学 | Long-distance non-contact luggage volume detection system and method thereof |
| CN106132831A (en) * | 2014-02-28 | 2016-11-16 | Icm空港科技澳大利亚有限公司 | Luggage treating stations and system |
| CN108922071A (en) * | 2018-07-06 | 2018-11-30 | 青岛永悦光迅技术有限责任公司 | A kind of self-service check-in and luggage delivery equipment and its system |
-
2019
- 2019-11-20 CN CN201911140460.3A patent/CN110866505A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714610A (en) * | 2014-01-17 | 2014-04-09 | 北京纳兰德科技有限公司 | Self-help luggage equipment and self-help luggage system as well as installation method |
| CN106132831A (en) * | 2014-02-28 | 2016-11-16 | Icm空港科技澳大利亚有限公司 | Luggage treating stations and system |
| CN107651211A (en) * | 2014-02-28 | 2018-02-02 | Icm空港科技澳大利亚有限公司 | Luggage treating stations and system |
| CN104867221A (en) * | 2015-06-04 | 2015-08-26 | 北京纳兰德科技有限公司 | Self-service baggage checking system |
| CN204856678U (en) * | 2015-08-19 | 2015-12-09 | 上海民航华东凯亚系统集成有限公司 | Self -service luggage delivery system |
| CN106056056A (en) * | 2016-05-23 | 2016-10-26 | 浙江大学 | Long-distance non-contact luggage volume detection system and method thereof |
| CN108922071A (en) * | 2018-07-06 | 2018-11-30 | 青岛永悦光迅技术有限责任公司 | A kind of self-service check-in and luggage delivery equipment and its system |
Non-Patent Citations (2)
| Title |
|---|
| 刘经纬等: "《"互联网+"人工智能技术实现》", 30 June 2019, 首都经贸大学出版社 * |
| 柴加宁等: "机场自助行李托运系统应用探讨", 《江苏航空》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308071A (en) * | 2020-11-02 | 2021-02-02 | 沈阳民航东北凯亚有限公司 | Intrusion detection method and device for consigning luggage and electronic equipment |
| CN112308071B (en) * | 2020-11-02 | 2024-03-05 | 沈阳民航东北凯亚有限公司 | Intrusion detection method and device for luggage consignment and electronic equipment |
| CN113780199A (en) * | 2021-09-15 | 2021-12-10 | 江苏迪赛司自动化工程有限公司 | Double-vision imaging device and intelligent identification method for belt-transported foreign object target |
| CN115661668A (en) * | 2022-12-13 | 2023-01-31 | 山东大学 | Method, device, medium and equipment for identifying flowers to be pollinated of pepper flowers |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3115772B1 (en) | Vehicle inspection method and system | |
| CN110866505A (en) | Method and device for detecting luggage consignment intrusion | |
| US10452922B2 (en) | IR or thermal image enhancement method based on background information for video analysis | |
| US6614928B1 (en) | Automatic parcel volume capture system and volume capture method using parcel image recognition | |
| CN107330433B (en) | Image processing method and device | |
| US20140037159A1 (en) | Apparatus and method for analyzing lesions in medical image | |
| US11490854B2 (en) | Method and device for analyzing water content of skin by means of skin image | |
| US7508994B2 (en) | Method for detecting streaks in digital images | |
| JP2008286725A (en) | Person detector and detection method | |
| US8107725B2 (en) | Image processor and image processing method | |
| CN111611863B (en) | License plate image quality evaluation method and device and computer equipment | |
| Wang et al. | Extracting oil slick features from VIIRS nighttime imagery using a Gaussian filter and morphological constraints | |
| CN111242888A (en) | Image processing method and system based on machine vision | |
| WO2013102797A1 (en) | System and method for detecting targets in maritime surveillance applications | |
| CN109870730B (en) | Method and system for regular inspection of X-ray machine image resolution test body | |
| CN106920266B (en) | The Background Generation Method and device of identifying code | |
| US10268922B2 (en) | Image processing by means of cross-correlation | |
| CN112183454B (en) | Image detection method and device, storage medium and terminal | |
| US11062440B2 (en) | Detection of irregularities using registration | |
| Cattaneo et al. | A PNU-based technique to detect forged regions in digital images | |
| CN112037243B (en) | Passive terahertz security inspection method, system and medium | |
| US10789688B2 (en) | Method, device, and system for enhancing changes in an image captured by a thermal camera | |
| JP3198258B2 (en) | Parked vehicle detection method and device | |
| KR20100018734A (en) | Method and apparatus for discriminating dangerous object in dead zone by using image processing | |
| KR101705876B1 (en) | Method for detecting pedestrian candidate and method for recognizing pedestrian using the same |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |
|
| RJ01 | Rejection of invention patent application after publication |