JP6299630B2 - Warning device, warning method and warning program - Google Patents

Description

  The present invention relates to a warning device, a warning method, and a warning program.

  An imaging device such as a digital camera generally images an area to be imaged using a filter that allows light of a specific wavelength to pass through. The image capturing apparatus can improve the image quality of the captured image by using a filter suitable for the amount of light in the region to be imaged. Therefore, during the daytime when the amount of visible light is large, a camera to which a daytime filter that passes more visible light region is applied is used. On the other hand, at night when the amount of visible light is small, an infrared camera to which a night filter that allows more infrared region to pass is applied.

  Patent Document 1 discloses a technique related to a monitoring device including an infrared sensor and an infrared camera. The monitoring apparatus according to Patent Document 1 captures an area monitored by an infrared sensor using an infrared camera, and detects a change in the monitored area based on a captured image captured by the monitoring camera. Then, the abnormal state is determined based on the detected change and the output of the infrared sensor.

  In recent years, warning devices have been developed that take pictures of the surroundings of a vehicle using an in-vehicle camera, recognize the photographed image, detect a person or car as an object in the image, and warn the driver. Yes. Patent Document 2 discloses a technique related to a person detection device for detecting a person from a captured image. The person detection device according to Patent Document 2 detects the appearance of an object based on an image acquired from an image sensor, and determines whether or not a parameter relating to the appearance of the detected object matches a comparison parameter relating to a person. A person probability representing the probability that the object is a person is calculated according to the degree of coincidence. If the person probability is equal to or higher than a preset person threshold, the object is determined to be a person.

JP 2007-160957 A JP 2011-146049 A

  Here, in the case of the warning device described above, there may be a situation where it is difficult to determine the external environment of the vehicle. For example, it may be a weather change or a situation where the vehicle travels in a place where the brightness changes abruptly, such as inside or outside a tunnel. Therefore, in a situation where it is difficult to determine the external environment of the vehicle, there is a problem that a warning based on detection of an object may be difficult.

  In the monitoring apparatus according to Patent Document 1, it is not assumed that the monitoring area is a specific area in the facility and it is difficult to determine the external environment. Moreover, the person detection apparatus according to Patent Document 2 has a single analysis target. Therefore, for example, when it is difficult to discriminate the external environment, if an appropriate filter cannot be used, the image quality deteriorates. And when the image quality of the image to be analyzed is low, the detection accuracy of an object that may hinder the traveling of the vehicle may be lowered. Therefore, an appropriate warning cannot be performed. Furthermore, such a problem occurs not only in the vehicle but also in a warning device mounted on the entire mobile body.

  The present invention has been made in view of the above-described problems, and provides a warning device, a warning method, and a warning method for appropriately performing warning based on detection of an object even in a situation where it is difficult to determine the external environment of a moving object. The purpose is to provide a warning program.

  According to a first aspect of the present invention, there is provided an image acquisition unit that acquires a plurality of images based on a plurality of filter characteristics, and a detection unit that detects a predetermined object for each of the acquired plurality of images. And warning means for performing a predetermined warning when the object is detected from at least one of the plurality of acquired images, wherein the warning means includes the plurality of images. Provided is a warning device that increases the degree of warning when the object is detected from all of the plurality of images than when the object is detected from a part of the plurality of images.

  According to a second aspect of the present invention, there is provided an image acquisition step for acquiring a plurality of images based on a plurality of filter characteristics, and a detection step for detecting a predetermined object for each of the acquired plurality of images. And a warning step for performing a predetermined warning when the object is detected from at least one of the plurality of acquired images, wherein the warning step includes: Provided is a warning method characterized in that when the object is detected from all of the objects, the degree of warning is made higher than when the object is detected from a part of the plurality of images.

  According to a third aspect of the present invention, there is provided an image acquisition step of acquiring a plurality of images based on a plurality of filter characteristics, and a detection step of detecting a predetermined object for each of the acquired plurality of images. And a warning step of performing a predetermined warning when the object is detected from at least one of the plurality of acquired images, and the warning step includes the plurality of warning steps. A warning program is provided in which, when the object is detected from all of the images, the degree of warning is higher than when the object is detected from a part of the plurality of images. .

  According to the present invention, it is possible to provide a warning device, a warning method, and a warning program for appropriately performing a warning based on detection of an object even in a situation where it is difficult to determine the external environment of a moving object.

It is a block diagram which shows the whole structure of the moving body carrying the warning device concerning this Embodiment 1. FIG. 1 is a block diagram showing a hardware configuration of a warning device according to a first embodiment. It is a flowchart for demonstrating the flow of the detection and warning process of the target concerning this Embodiment 1. FIG. It is a figure which shows the example of the picked-up image by the 1st filter concerning this Embodiment 1. FIG. It is a figure which shows the example of the picked-up image by the 2nd filter concerning this Embodiment 1. FIG. It is a flowchart for demonstrating the flow of an example of the warning process concerning this Embodiment 1. FIG. It is a figure which shows the example which emphasizes the position of the target object concerning this Embodiment 1, and displays it on a screen. It is a block diagram which shows the structure of the warning device concerning this Embodiment 2. It is a flowchart for demonstrating the flow of the mode setting process concerning this Embodiment 2. FIG. It is a block diagram which shows the structure of the image acquisition means concerning this Embodiment 3.

  Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. In the drawings, the same elements are denoted by the same reference numerals, and redundant description will be omitted as necessary for the sake of clarity.

<Embodiment 1 of the Invention>
FIG. 1 is a block diagram showing an overall configuration of a moving body 1 equipped with a warning device 10 according to the first embodiment. The moving body 1 is equipped with a warning device 10, a display device 21, a speaker 22, and the like, and travels by a driver's operation. The moving body 1 is, for example, a vehicle such as an automobile. The warning device 10 detects an object around the mobile body 1 that may collide with the mobile body 1 by analyzing an image taken while the mobile body 1 is traveling, and the driver through the display device 21 or the speaker 22 or the like. This is a device that gives a warning. The display device is, for example, an organic EL (electro-luminescence) display or a plasma display.

  The warning device 10 includes an image acquisition unit 11, a detection unit 12, and a warning unit 13. The image acquisition means 11 captures a peripheral area of the moving body 1 with a plurality of different filter characteristics while the moving body 1 is traveling, and acquires it as a plurality of images. That is, the image acquisition unit 11 acquires a plurality of images based on each of the plurality of filter characteristics. The image acquisition unit 11 includes photographing devices 111 and 112. The imaging devices 111 and 112 correspond to each of a plurality of filter characteristics. Then, each of the photographing devices 111 and 112 performs photographing with a corresponding filter characteristic. In addition, the imaging device with which the image acquisition means 11 is provided is not limited to two. For example, the image acquisition unit 11 may include three or more imaging devices corresponding to three or more filter characteristics. Note that the photographing apparatus is, for example, a camera.

  The detection means 12 detects a predetermined target object for each of the acquired plurality of images. The warning unit 13 issues a predetermined warning when an object is detected from at least one of the acquired images. In particular, the warning unit 13 according to the embodiment of the present invention has a higher degree of warning when an object is detected from all of a plurality of images than when an object is detected from a part of the plurality of images. To increase. Here, increasing the degree of warning means changing the operation of the warning means so that the object can be recognized more as described later.

  FIG. 2 is a block diagram of a hardware configuration of the warning device 10 according to the first embodiment. The warning device 10 includes a processor 110, an IF (InterFace) unit 120, imaging devices 131 and 132, and a storage unit 140.

  The processor 110 is a control device such as a CPU (Central Processing Unit). The IF unit 120 is an interface that performs input / output with the outside of the warning device 10. In particular, the IF unit 120 outputs information indicating a warning to the display device 21 or the speaker 22 under the control of the processor 110.

  The photographing devices 131 and 132 correspond to the photographing devices 111 and 112 described above. The imaging device 131 includes a first filter 1311 and a first image sensor 1312. The first filter 1311 performs a process of selecting the wavelength of light incident on the first image sensor 1312. That is, the first filter 1311 is a filter that is applied when the photographing apparatus 131 is photographing. The first filter 1311 has, for example, a filter characteristic that blocks the near-infrared region and passes the visible light region. It is assumed that the first filter 1311 is a filter suitable when the peripheral area of the moving body 1 is bright, such as at least during the daytime. The first imaging element 1312 is an element that converts the intensity of light that has passed through the first filter 1311 into an electrical signal.

  The imaging device 132 includes a second filter 1321 and a second imaging element 1322. The second filter 1321 performs processing for selecting the wavelength of light incident on the second image sensor 1322. That is, the second filter 1321 is a filter that is applied when the image capturing apparatus 132 captures an image. The second filter 1321 has, for example, a filter characteristic that blocks the near infrared region and passes the visible light region. The second filter 1321 is a filter suitable for a case where the peripheral area of the moving body 1 is dark, such as at night. The second imaging element 1322 is an element that converts the intensity of light that has passed through the second filter 1321 into an electrical signal.

  The storage unit 140 is a storage device such as a memory or a hard disk, for example. The storage unit 140 stores a warning program 141, captured images 1421 and 1422, and index values 1431 and 1432. The warning program 141 is a computer program in which an object detection and warning process of the warning device 10 according to the present embodiment, that is, a warning method is implemented.

  The captured image 1421 is image data captured by the imaging device 131 using the first filter 1311 and the first imaging element 1312. The captured image 1422 is image data captured by the imaging device 132 using the second filter 1321 and the second imaging element 1322. The index value 1431 is a value indicating the degree of detection of the target object from the captured image 1421 by the detection unit 12. The index value 1432 is a value indicating the degree of detection of an object from the captured image 1422 by the detection unit 12. The index values 1431 and 1432 can be said to be index values of the detection accuracy of the object when the captured image is recognized.

  The processor 110 reads the warning program 141 from the storage unit 140 and executes it. Accordingly, the warning device 10 operates as the image acquisition unit 11, the detection unit 12, the warning unit 13, and the like according to the present embodiment using the IF unit 120 and the imaging devices 131 and 132 as appropriate.

  FIG. 3 is a flowchart for explaining the flow of object detection and warning processing according to the first embodiment. As a premise, it is evening and the like, and it is assumed that the amount of light between daytime and nighttime is incident on the moving body 1.

  First, the imaging device 111 captures an area around the moving body 1 with the first filter characteristic while the moving body 1 is traveling, and acquires the first image as a first image (S111). At this time, the warning device 10 stores the acquired first image in the storage unit 140. And the detection means 12 detects a predetermined target object with respect to a 1st image (S112). Here, FIG. 4 is a diagram illustrating an example of the captured image 31 by the first filter according to the first embodiment. The captured image 31 indicates that the object 41 is detected to some extent in the traveling direction of the moving body 1. However, it is assumed that the detection means 12 cannot be sufficiently identified only by the object 41.

  In parallel with step S111, the imaging device 112 captures the peripheral area of the moving body 1 with the second filter characteristic while the moving body 1 is traveling, and obtains it as a second image (S121). At this time, the warning device 10 stores the acquired second image in the storage unit 140. And the detection means 12 detects a predetermined target object with respect to a 2nd image (S122). Here, FIG. 5 is a diagram illustrating an example of the captured image 32 by the second filter according to the first embodiment. The captured image 32 indicates that the object 42 is slightly detected in the traveling direction of the moving body 1. However, since the captured image 32 itself is unclear, it is assumed that the detection unit 12 cannot sufficiently distinguish the object 42 from the road.

  After steps S112 and S122, the warning unit 13 determines whether an object is detected from one of the first image and the second image (S131). Here, when detected from one side, the warning means 13 performs a first warning process (S132). For example, the warning unit 13 outputs an image in which the object is detected to the display device 21 and displays it on the screen. For example, when the amount of light in the external environment is sufficient, the object is clearly shown in the first image, but the object cannot be identified and detected in the second image. In such a case, the warning unit 13 outputs the first image to the display device 21. Then, the driver can recognize the danger by displaying the first image on the screen.

  When it is determined NO in step S131, the warning unit 13 determines whether an object is detected from both the first image and the second image (S133). For example, in the case of the captured images 31 and 32 in FIGS. 4 and 5 described above, the object is detected from both. At this time, the warning means 13 performs a second warning process (S134). Here, it is assumed that the second warning process has a higher degree of warning than the first warning in step S132. Here, what has a high degree of warning is demonstrated. For example, the warning unit 13 outputs the first image in which the object is detected with higher accuracy among the first image and the second image to the display device 21 and displays the first image on the screen. At this time, the warning means 13 may process the first image so that the vicinity of the object in the first image is emphasized and displayed on the display device 21. Note that highlighting and displaying will be described later, for example, surrounding the object with a square line, adding a mark above the object or the object, or changing the color of the object. and so on. Alternatively, the warning unit 13 may output a warning sound through the speaker 22 together with the display based on the first image. That is, the warning unit 13 performs a predetermined warning using an image in which the object is detected with higher accuracy among the first image and the second image.

  On the other hand, as an example, a case where the degree of warning is not as high as described above (for example, a case where an object is detected from one of the first image and the second image) will be described. In this case, as described above, of the first image and the second image, an image showing the object is output to the display device 21 and displayed on the screen. At this time, when the warning means 13 displays the first image on the display device 21 without processing or displays the processed image on the display device 21, the warning means 13 is the target compared with the case where the warning degree is high. Processing such as thinning the line surrounding the object, changing the mark attached above the object, or changing the color of the object to be changed is performed. Further, when the warning means 13 outputs a warning sound through the speaker 22, processing such as changing the volume and changing the warning sound is performed as compared with the case where the warning degree is high.

  If NO is determined in step S133, the process in FIG. 3 is terminated.

  Here, in steps S <b> 112 and S <b> 122 of FIG. 3, the detection unit 12 may calculate an index value indicating the degree of detection of the object for each of the plurality of acquired images. For example, as shown in Patent Document 2, the detection unit 12 may detect a parameter related to the appearance of the object, and calculate the degree of matching between the comparison parameter and the detected parameter as an index value. In addition, as a parameter regarding an external appearance, a brightness | luminance, saturation, an edge, or these combination is mentioned, for example. In addition, the process which calculates an index value when detecting a target object from each image is not limited to this.

  The detecting unit 12 stores the calculated index value in the storage unit 140. An example of the warning process in steps S131 to S134 in FIG. 3 in this case will be described with reference to FIG.

  First, the warning means 13 determines whether or not there is one image whose index value exceeds a predetermined value (S131a). For example, the warning unit 13 determines whether or not the index value 1431 read from the storage unit 140 exceeds a predetermined value. Similarly, the warning unit 13 determines whether or not the index value 1432 read from the storage unit 140 exceeds a predetermined value. When one of the index values 1431 and 1432 exceeds a predetermined value and the other is equal to or less than the predetermined value, the warning unit 13 displays a corresponding image, that is, an image exceeding the predetermined value on the screen (S132a). Step S132a is an example of a first warning process.

  When it is determined NO in step S131a, the warning unit 13 determines whether or not both images have an index value exceeding a predetermined value (S133a). If both are present, the warning means 13 selects the image with the highest index value (S134a). For example, in the case of the captured images 31 and 32, the captured image 31 is selected. And the warning means 13 emphasizes and displays a target object on a screen using the selected image (S134b). For example, the warning unit 13 generates an image surrounding the region of the target object 41 in the captured image 31, outputs the image to the display device 21, and displays it on the screen. Here, FIG. 7 is a diagram illustrating an example in which the position of the object according to the first embodiment is emphasized and displayed on the screen. The highlighted display area 43 in the captured image 31 is an example of highlighted display. However, cooperative display is not limited to this. In addition, when it determines with NO in step S133a, the process of FIG. 6 is complete | finished.

Thus, at least the following can be said from the first embodiment.
First, as in the past, when shooting using one of the two filter characteristics, it is possible to detect an object with high accuracy by using an appropriate filter characteristic for the external environment. However, when an inappropriate filter characteristic is used, the detection accuracy of the object is lowered. When the moving body is traveling, a situation in which it is difficult to determine the external environment may occur. For this reason, in the first embodiment, the probability that an object can be detected from at least one of the images is increased by photographing the periphery in advance using each of the plurality of filter characteristics. Therefore, it is possible to warn the driver of more cases about dangerous situations and improve safety.

  As a situation where it is difficult to discriminate the external environment, for example, there is an evening when it is difficult to discriminate between daytime and nighttime from the amount of light. In such a situation, using either the daytime filter or the nighttime filter, each image does not have sufficient image quality, and it may not be detected with sufficient accuracy simply by analyzing a single image. There is. Therefore, in the first embodiment, when an object is detected with a certain degree of accuracy from each of a plurality of images taken with a plurality of different filter characteristics for the same object, it is determined that the situation is dangerous. In particular, in such a situation, it may be difficult for the driver to recognize the object as compared with the case where it is clear whether it is day or night. Therefore, in such a situation, it is possible to appropriately warn the driver by increasing the degree of warning compared to normal.

  In the case of the second warning process having a higher degree of warning than the first warning process, an image in which the object is detected with higher accuracy is used from the two images. The reason is that when an object is detected from two or more captured images, warning is made using an image with higher detection accuracy, so that it becomes easier for the driver to identify the object. is there.

<Embodiment 2 of the Invention>
The second embodiment is an improved example of the first embodiment described above. FIG. 8 is a block diagram illustrating a configuration of the warning device 10a according to the second embodiment. The warning device 10a is obtained by adding position information acquisition means 14 and setting means 15 to the warning device 10 of FIG. Therefore, in the following description, description of the same configuration as that in FIG. 1 is omitted. For convenience of explanation, a storage unit 16 corresponding to the storage unit 140 of FIG. 2 is shown in FIG. It is assumed that the warning program 141 also has a function corresponding to the second embodiment.

  The storage unit 16 further stores map information 161, a specific area 162, position information 163, a first mode 164, and a first mode 165 in addition to the configuration in the storage unit 140 of FIG. . The map information 161 is information in which the road on which the vehicle travels and the position of each facility are defined by coordinates. As the map information 161, information used in a general car navigation system can be used. The specific area 162 is information in which some areas in the map information 161 are defined in advance. The specific area 162 indicates, for example, an area such as an expressway, a general road, a tunnel, and a railway station. The position information 163 is current position information of the moving body 1 acquired by the position information acquisition unit 14.

  The first mode 164 is setting information that defines that the image acquisition unit 11 captures images with one filter characteristic. The second mode 165 is setting information that defines that the image acquisition unit 11 captures images with a plurality of filter characteristics.

  The position information acquisition unit 14 periodically acquires the current position information of the moving body 1. Then, the position information acquisition unit 14 stores the acquired position information in the storage unit 16. The position information acquisition unit 14 is, for example, a device that is mounted on a vehicle and acquires GPS (Global Positioning System) information.

  The setting unit 15 selects the first mode 164 or the second mode 165 according to a predetermined condition, and sets the selected mode in the image acquisition unit 11. Further, the setting means 15 selects the second mode 165 and sets it in the image acquisition means 11 when the acquired position information 163 is within the range of the specific area 162 on the map information 161.

  Here, the predetermined condition is, for example, a condition using a part or all of position information, time information, weather, road information, travel information, and the like. The conditions using the position information include, for example, whether the distance between the current position and the specific position is within a predetermined value, whether the distance is within a specific area, or the like. The conditions using the time information include, for example, a season discrimination condition based on the current month and day, a time zone discrimination condition such as day / night or evening according to the hour and minute, and the like. In addition, in order to use time information, the structure etc. which acquire the information of present time separately are required.

  The conditions using the weather include, for example, the state of clouds, whether the weather is clear, cloudy, rainy, or the like. In order to use the weather, a configuration for acquiring weather information is required separately. The conditions using the road information are, for example, determination conditions such as whether the road type is an expressway or a general road, road width, road sign, road shape, road surface condition, and the like. In addition, in order to use road information, the structure etc. which acquire the information regarding the road on driving separately are required. The conditions using the travel information include determination conditions such as whether or not the vehicle speed, brake control information, and the like exceed a predetermined value. In order to use the travel information, a configuration for acquiring speed and brake control information from the vehicle is required.

  FIG. 9 is a flowchart for explaining the flow of the mode setting process according to the second embodiment. First, the position information acquisition unit 14 periodically acquires current position information (S21). Next, the setting unit 15 determines whether or not the acquired position information is within the range of the specific area (S22). When it determines with it being in the range of a specific area, the setting means 15 selects a 2nd mode (S23). On the other hand, when it determines with it being outside the range of a specific area, the setting means 15 selects a 1st mode (S24). Thereafter, the setting unit 15 sets the selected mode in the image acquisition unit 11 (S25).

  Thus, in the second embodiment, the type of filter used at the time of shooting can be switched according to the situation. Thereby, when it is easy to determine the external environment, the power consumption of the moving body 1 can be suppressed using the first mode. In addition, when it is difficult to determine the external environment, it is possible to immediately switch to the second mode using a plurality of filter characteristics.

<Third Embodiment of the Invention>
The third embodiment is a modification of the first embodiment described above. In the first embodiment described above, the image acquisition unit 11 has two imaging devices. However, the image acquisition unit 11 according to the third embodiment has one imaging device.

  FIG. 10 is a block diagram illustrating a configuration of the image acquisition unit 11a according to the third embodiment. The image acquisition unit 11a includes one photographing device 113. The imaging device 113 performs imaging by periodically switching a plurality of filter characteristics. The photographing apparatus 113 includes a filter 1131, an image sensor 1132, and a switching unit 1133. The filter 1131 performs a process of selecting the wavelength of light incident on the image sensor 1132. For example, the filter 1131 selects a visible light region or a near-infrared region, passes light, and enters the image sensor 1132. The filter 1131 can include an infrared region cut filter (IR filter), a high pass filter, a band pass filter, and the like. That is, the filter 1131 can realize one selected from a plurality of types of filter characteristics. The imaging element 1132 is an element that converts the intensity of light that has passed through the filter 1131 into an electrical signal. The switching unit 1133 sets the selected filter characteristic for the filter 1131. Then, the switching unit 1133 periodically switches the selection of the filter characteristics. Note that the switching unit 1133 switches the filter characteristics at a speed that is substantially the same as when a plurality of imaging devices simultaneously capture the same object using a plurality of filter characteristics. Note that switching photography is performed periodically by whether the switching means has a clock or receives a signal based on the clock.

  As described above, according to the third embodiment, the same effect as that of the first embodiment can be obtained.

<Other embodiments of the invention>
It should be noted that the above-described embodiments can be appropriately combined. That is, the second embodiment and the third embodiment may be combined.

  Although the present invention has been described with reference to the above embodiment, the present invention is not limited only to the configuration of the above embodiment, and within the scope of the invention of the claims of the present application. It goes without saying that various modifications, corrections, and combinations that can be made by those skilled in the art are included.

  Further, the arbitrary processing of the above-described in-vehicle device can be realized by causing a CPU (Central Processing Unit) to execute a computer program. In this case, the computer program can be stored using various types of non-transitory computer readable media and supplied to the computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (for example, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (for example, magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / W and semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)) are included. The program may also be supplied to the computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

  In addition to the case where the function of the above-described embodiment is realized by the computer executing the program that realizes the function of the above-described embodiment, this program is not limited to the OS ( A case where the functions of the above-described embodiment are realized in cooperation with an operating system or application software is also included in the embodiment of the present invention. Furthermore, the present invention is also applicable to the case where the functions of the above-described embodiment are realized by performing all or part of the processing of the program by a function expansion board inserted into the computer or a function expansion unit connected to the computer. It is included in the embodiment.

DESCRIPTION OF SYMBOLS 1 Mobile body 10 Warning device 10a Warning device 11 Image acquisition means 11a Image acquisition means 111 Imaging device 112 Imaging device 113 Imaging device 1131 Filter 1132 Imaging element 1133 Switching means 12 Detection means 13 Warning means 14 Position information acquisition means 15 Setting means 16 Storage Unit 161 Map information 162 Specific area 163 Position information 164 First mode 165 Second mode 21 Display device 22 Speaker 110 Processor 120 IF unit 131 Imaging device 1311 First filter 1312 First imaging device 132 Imaging device 1321 Second Filter 1322 Second imaging device 140 Storage unit 141 Warning program 1421 Captured image 1422 Captured image 1431 Index value 1432 Index value 31 Captured image 32 Captured image 41 Object 42 Object 43 Grayscale display area

Claims (10)

Image acquisition means for acquiring a plurality of images based on each of a plurality of filter characteristics;
Detecting means for detecting a predetermined object for each of the plurality of acquired images;
Warning means for performing a predetermined warning when the object is detected from at least one of the plurality of acquired images;
With
The warning means is
A warning device that increases the degree of warning when the object is detected from all of the plurality of images than when the object is detected from a part of the plurality of images. The warning means is
The warning device according to claim 1, wherein when the target object is detected from two or more of the plurality of images, the predetermined warning is performed using an image in which the target object is detected with higher accuracy. The detection means includes
Calculating an index value indicating the degree of detection of the object for each of the plurality of acquired images;
The warning means is
An image in which the index value exceeds a predetermined value, the object is detected,
The warning device according to claim 2, wherein when the object is detected from two or more of the plurality of images, the predetermined warning is performed using an image having the highest index value. The first mode in which the image acquisition means captures with one filter characteristic, or the second mode in which the image acquisition means captures with the plurality of filter characteristics is selected according to a predetermined condition, and the selected mode is selected. The warning device according to claim 1, further comprising a setting unit that sets the image acquisition unit. Further comprising position information acquisition means for acquiring the current position information of the moving body equipped with the warning device ;
The setting means includes
The warning device according to claim 4, wherein the second mode is selected and set in the image acquisition unit when the acquired position information is within a specific region on map information. The warning means is
The said warning is performed by highlighting the position of the said object on the detected image, and displaying it on a screen, when the said detection means is detected by the said detection means. Warning device according to item. The image acquisition means includes
A plurality of imaging devices corresponding to each of the plurality of filter characteristics;
Each of the plurality of photographing devices is
The warning device according to any one of claims 1 to 6, wherein shooting is performed with a corresponding filter characteristic. The image acquisition means has one photographing device,
The warning device according to any one of claims 1 to 6, wherein the photographing device performs photographing by periodically switching the plurality of filter characteristics. An image acquisition step of acquiring a plurality of images based on each of the plurality of filter characteristics;
A detection step of detecting a predetermined object for each of the plurality of acquired images;
A warning step for giving a predetermined warning when the object is detected from at least one of the plurality of acquired images;
With
The warning step includes
A warning method characterized in that, when the object is detected from all of the plurality of images, the degree of warning is higher than when the object is detected from a part of the plurality of images. An image acquisition step of acquiring a plurality of images based on each of the plurality of filter characteristics;
A detection step of detecting a predetermined object for each of the plurality of acquired images;
A warning step for giving a predetermined warning when the object is detected from at least one of the plurality of acquired images;
To the computer,
The warning step includes
A warning program characterized by having a higher degree of warning when the object is detected from all of the plurality of images than when the object is detected from a part of the plurality of images.

Images