Entry determination device

Abstract

To provide an entry determination device capable of determining entry of a moving object into an entry prohibited area shown on a video with high accuracy.SOLUTION: An entry determination device 1 includes: an acquisition unit 2 that acquires a video Y captured by image capturing means X installed to capture a predetermined range; a storage unit 3 that stores an entry prohibited area R1 for a moving object Z1 within the predetermined range and detection criteria for detecting at least a portion of the moving object Z1 shown on the video Y; a first detection unit 4 that can detect the moving object Z1 within the video Y based on the detection criteria; a second detection unit 5 that can detect a vehicle Z2 traveling within the video Y; and a determination unit 6 that determines entry of the moving object Z1 into the entry prohibited area R1 when the moving object Z1 is detected within the entry prohibited area R1. However, the determination unit 6 does not determine the entry if both the moving object Z1 and the vehicle Z2 are detected within the entry prohibited area R1.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an intrusion determination device that can determine with high accuracy whether a moving object has entered a no-entry area captured on an image. [Background technology]

[0002] A technique has been known in the past for identifying a group of joints belonging to an object based on multiple joints captured in time-series images, and estimating the behavior of the object based on the displacement of the group of joints (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6525179 Summary of the Invention [Problem to be solved by the invention]

[0004] By using the above technology, it is also possible to determine whether a person is entering a no-entry area in the video (for example, near a parking gate or train tracks).

[0005] However, with the above configuration, when a car or train passes through a no-entry area, the driver and passengers are also detected, which creates the problem of the car or train mistakenly determining that a human has entered the no-entry area.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an intrusion determination device that can determine with high accuracy whether a moving object has entered a no-entry area captured on an image. [Means for solving the problem]

[0007] The present invention provides an entry determination device comprising: an acquisition unit that acquires video captured by a camera means installed to capture a predetermined range; a memory unit that stores a no-entry area for a moving object within the predetermined range and detection criteria for detecting at least a portion of the moving object captured in the video; a first detection unit that can detect a moving object in the video based on the detection criteria; a second detection unit that can detect a vehicle traveling in the video; and a determination unit that determines that a moving object has entered the no-entry area when a moving object is detected within the no-entry area, wherein the determination unit does not determine that the moving object has entered when both a moving object and a vehicle are detected within the no-entry area.

[0008] According to another aspect of the present invention, there are provided an entry determination program and an entry determination method corresponding to the above-mentioned entry determination device. [Effects of the Invention]

[0009] According to the intrusion determination device of the present invention, it is possible to determine with high accuracy whether a moving object has entered a no-entry area captured on an image. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is an explanatory diagram of determining whether a moving object has entered a no-entry area according to an embodiment of the present invention; [Figure 2] 1 is a block diagram of an intrusion determination device according to an embodiment of the present invention; [Figure 3] FIG. 1 is an explanatory diagram of a no-entry area according to an embodiment of the present invention; [Figure 4] FIG. 1 is an explanatory diagram of an overlapping area and a running area according to an embodiment of the present invention; [Figure 5] FIG. 1 is an explanatory diagram of divided regions according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0011] An entry determination device 1 according to an embodiment of the present invention will be described below with reference to FIGS.

[0012] 1, the entry determination device 1 determines the entry of a moving object Z1 into a no-entry area R1 captured in an image Y (in FIG. 1, frames constituting the image) captured by a photographing means X. In this embodiment, a human being is used as the moving object Z1, and for ease of understanding, the moving object Z1 is simply displayed using only a skeleton.

[0013] As shown in FIG. 2, the entry determination device 1 includes an acquisition unit 2, a storage unit 3, a first detection unit 4, a second detection unit 5, a determination unit 6, and a notification unit .

[0014] The acquisition unit 2 acquires an image Y captured by an image capturing means X that is installed to capture a predetermined range. In this embodiment, it is assumed that the entire range captured by the image capturing means X is set as the predetermined range.

[0015] The storage unit 3 stores a no-entry area R1 for the moving object Z1 within the predetermined range and a detection criterion for detecting at least a part of the moving object Z1 captured in the image Y.

[0016] In this embodiment, the no-entry area R1 is stored by the user. Fig. 3(a) shows an example in which the vicinity of a parking lot gate is stored as the no-entry area R1 (view of vehicle Z2 from diagonally ahead), and Fig. 3(b) shows an example in which train tracks are stored as the no-entry area R1 (view of vehicle Z2 from the side).

[0017] In this embodiment, a "joint identification standard", a "moving object identification standard", and a "behavior identification standard" are stored as detection standards.

[0018] The "joint identification standard" is used to identify the multiple joints of the active body Z1 (neck, right elbow, left elbow, waist, right knee, left knee, etc.), and indicates the shape, direction, size, etc. for identifying each joint.

[0019] The "actor identification criteria" indicate the "basic posture" of various variations of the acting entity Z1 ("walking", "standing upright", etc.), the "range of motion of each joint", and the "distance between each joint" in a single acting entity Z1.

[0020] The "behavior identification standard" indicates the movement of each joint when the behavioral body Z1 performs a predetermined behavior, and in this embodiment, "behavior identification standard" for various types of behavior is stored.

[0021] Furthermore, in this embodiment, the storage unit 3 further stores a travel area R2 in which the vehicle Z2 can travel (see FIGS. 4 and 5). In this embodiment, the travel area R2 is also stored by the user.

[0022] The first detector 4 is capable of detecting the moving object Z1 in the image Y based on the above detection criteria.

[0023] When detecting the moving object Z1, first, the moving object Z1 captured in the image Y is identified.

[0024] In this embodiment, after detecting multiple joints that match the "joint identification standard" stored in the memory unit 3, the multiple joints included in one moving object Z1 are identified by referring to the "moving object identification standard." In the example of Figure 1, all joints are identified as joints included in one moving object Z1, and it is identified that one moving object Z1 exists.

[0025] The second detection unit 5 can detect a vehicle Z2 traveling in the image Y. FIG. 3(a) shows an example in which a car is used as the vehicle Z2, and FIG. 3(b) shows an example in which a train is used as the vehicle Z2. In this embodiment, the vehicle Z2 is detected using background subtraction, and it is considered that a known background subtraction method is used for the detection using background subtraction.

[0026] When the moving object Z1 is detected within the entry-prohibited area R1, the determination unit 6 determines that the moving object Z1 has entered the entry-prohibited area R1.

[0027] The notification unit 7 issues a notification when the determination unit 6 determines that an "entry" has occurred. For example, an alert may be issued to the moving object Z1 by a voice output means installed near the no-entry area R1, or the "entry" may be notified to an information terminal of a facility manager or the like.

[0028] This configuration makes it possible to determine whether a moving object Z1 has entered a no-entry area R1. However, as shown in Figures 3(a) and 3(b), when a vehicle Z2 travels through the no-entry area R1, the driver and passengers of the vehicle are also detected, resulting in a problem where the vehicle Z2 is mistakenly determined to have "entered" the no-entry area R1 when it travels through the no-entry area R1.

[0029] Therefore, in this embodiment, when both moving body Z1 and vehicle Z2 are detected within the no-entry area R1, the judgment unit 6 will assume that the driver or passengers of vehicle Z2 have been mistakenly detected as moving body Z1, and will not judge it as "entry."

[0030] This prevents the vehicle Z2 from being mistakenly judged as having "entered" when it travels through the no-entry area R1 of the moving object Z1.

[0031] However, as shown in Figure 4(a), if a moving object Z1 is present within the no-entry area R1 outside the driving area R2 of vehicle Z2, it must be judged as "entry." However, if the system is simply configured such that "if both moving object Z1 and vehicle Z2 are detected within the no-entry area R1, it will not be judged as "entry," and in such cases, it will fail to judge as "entry."

[0032] Therefore, in this embodiment, the judgment unit 6 will not judge that there is an "entry" when both the moving object Z1 and the vehicle Z2 are detected within the overlapping area R3 between the no-entry area R1 and the traveling area R2.

[0033] This prevents a failure to determine whether a moving object Z1 has "entered" when the moving object Z1 is present in a no-entry area R1 other than the driving area R2 of the vehicle Z2, as shown in FIG. 4(a).

[0034] Furthermore, as shown in Figure 4, it is also possible that there are multiple (separate) driving areas R2 (in Figure 4, an entrance gate and an exit gate for automobiles), and in this case, there will also be multiple overlapping areas R3. In this case, as shown in Figure 4(b), with the above configuration, if a moving object Z1 is in one overlapping area R31 and a vehicle Z2 is in the other overlapping area R32, it will fail to determine that there is an "entry."

[0035] Therefore, in this embodiment, the memory unit 3 stores multiple driving areas R2, and the judgment unit 6 does not judge that there is an "entry" when both the moving object Z1 and the vehicle Z2 are detected within the overlapping area R3 between the no-entry area R1 and one driving area R2.

[0036] This prevents a failure to determine "entry" when the moving object Z1 is in an overlapping area R3 different from the vehicle Z2, as shown in FIG. 4(b).

[0037] Furthermore, for example, as shown in Figure 5, it is possible to imagine a situation in which one overlapping area R3 is large and the moving body Z1 and the vehicle Z2 are located at different positions within the one overlapping area R3, but with the above configuration, even in such a situation, it will not be judged as "entry."

[0038] Therefore, in this embodiment, if both the moving object Z1 and the vehicle Z2 are detected in one of the divided regions R4 obtained by dividing the overlapping region R3, it is not determined that the moving object Z1 and the vehicle Z2 are entering the area. The division method may be to divide the area into a predetermined size, or the size may be changed depending on the location.

[0039] This prevents a mistaken determination of "entry" when, for example, a moving object Z1 and a vehicle Z2 are located at separate positions within one overlapping area R3, as shown in FIG.

[0040] As explained above, the entry determination device 1 according to this embodiment does not determine "entry" when both the moving object Z1 and the vehicle Z2 are detected within the no-entry area R1.

[0041] This configuration prevents the vehicle Z2 from erroneously determining that it has "entered" when it travels through the no-entry area R1 of the moving object Z1.

[0042] Furthermore, the entry determination device 1 according to this embodiment does not determine "entry" when both the moving object Z1 and the vehicle Z2 are detected within the overlapping area R3 of the no-entry area R1 and the traveling area R2.

[0043] This configuration prevents a mistaken determination of "entry of the moving object Z1" when the moving object Z1 is present in a region of the no-entry area R1 other than the travel region R2 of the vehicle Z2.

[0044] In addition, the entry determination device 1 according to this embodiment stores multiple driving areas R2, and does not determine "entry" when both the moving body Z1 and the vehicle Z2 are detected within the overlap area R3 between the no-entry area R1 and one driving area R2.

[0045] This configuration prevents a failure to determine that the moving object Z1 is entering an overlapping area R3 that is different from the vehicle Z2.

[0046] Furthermore, in the entry determination device 1 according to this embodiment, if both the moving body Z1 and the vehicle Z2 are detected within one of the multiple divided areas R4 into which the overlapping area R3 is divided, the entry determination is not made.

[0047] This configuration prevents a failure to determine "entry" when, for example, the moving object Z1 and the vehicle Z2 are located at separate positions within one overlapping area R3.

[0048] The entry determination device of the present invention is not limited to the above-described embodiment, and various modifications and improvements are possible within the scope of the claims.

[0049] For example, in the above embodiment, the second detection unit 5 detects the vehicle Z2 using background subtraction, but the background subtraction may also use optical flow. Furthermore, the vehicle Z2 may be detected by other methods such as object detection, other than background subtraction.

[0050] Furthermore, in the above embodiment, a human being is used as an example of the moving body Z1, but it is also possible to use an animal or a robot.

[0051] Furthermore, in the above embodiment, the behavior of a moving object is detected based on the movements of a plurality of joints, but the behavior of a moving object may be detected by other methods without detecting the joints.

[0052] The present invention can also be applied to a program and method corresponding to the processing performed by each component as a controller, and to a recording medium storing the program. In the case of a recording medium, the program is installed in a computer or the like. Here, the recording medium storing the program may be a non-transitory recording medium. A CD-ROM or the like is conceivable as a non-transitory recording medium, but is not limited to this. [Explanation of symbols]

[0053] 1 Entry judgment device 2 Acquisition part 3 Storage section 4. First detector 5 Second detection unit 6 Judgment section 7. Information Department R1 No entry area R2 driving area R3 overlap area R31 Overlapping area R32 Overlapping area R4 divided area X Shooting Method Y Video Z1 action body Z2 vehicle

Claims

1. an acquisition unit that acquires an image captured by an image capturing means installed to capture a predetermined range; a storage unit that stores a no-entry area for a moving object within the predetermined range and a detection standard for detecting at least a part of the moving object captured in the video; a first detection unit capable of detecting a moving object in the video based on the detection criterion; a second detection unit capable of detecting a vehicle traveling within the image; a determination unit that determines that a moving object has entered the no-entry area when the moving object is detected within the no-entry area; Equipped with The entry determination device is characterized in that the determination unit does not determine that an entry has occurred when both a moving object and a vehicle are detected within the no-entry area.

2. The storage unit further stores a travel area in which the vehicle can travel, 2. The entry determination device according to claim 1, wherein the determination unit does not determine that an entry has occurred when both a moving object and a vehicle are detected within an overlapping area between the no-entry area and the traveling area.

3. The storage unit stores a plurality of the travel areas, The entry determination device according to claim 2, characterized in that the determination unit does not determine that an entry has occurred when both a moving object and a vehicle are detected within an overlapping area between the no-entry area and one of the driving areas.

4. The entry determination device according to claim 2, characterized in that the determination unit does not determine that an entry has occurred when both a moving object and a vehicle are detected within one of the multiple divided areas obtained by dividing the overlapping area.

5. A program executed by a computer that stores a no-entry area for a moving object within a predetermined range captured by a photographing means and a detection criterion for detecting at least a part of the moving object captured in the image, acquiring an image captured by the imaging means; detecting an active object in the video based on the detection criteria; detecting a vehicle traveling within the image; a step of determining that a moving object has entered the no-entry area when the moving object is detected within the no-entry area; Equipped with An entry determination program, wherein in the determining step, the entry is not determined to have occurred when both a moving object and a vehicle are detected within the no-entry area.

6. A method executed by a computer that stores a no-entry area for a moving object within a predetermined range captured by a capturing means and a detection criterion for detecting at least a part of the moving object captured in the image, the method comprising: acquiring an image captured by the imaging means; detecting an active object in the video based on the detection criteria; detecting a vehicle traveling within the image; a step of determining that a moving object has entered the no-entry area when the moving object is detected within the no-entry area; Equipped with The method for determining entry, wherein the determining step does not determine that an entry has occurred when both a moving object and a vehicle are detected within the no-entry area.

Images