Image recording apparatus

Abstract

To provide an image recording device capable of appropriately suppressing the capacity of an image file while improving the image quality of a required area.SOLUTION: An image recording device 1 according to the present invention includes an image acquisition unit 11 that acquires an image around a self vehicle, an object recognition unit 12 that recognizes a predetermined object from the image acquired by the image acquisition unit 11, a determination reference speed calculation unit 13 that calculates a determination reference speed using the speed at which the object recognized by the object recognition unit 12 moves relative to the self vehicle and the speed of the self vehicle, a region-of-interest extraction unit 14 that extracts a region including the object, in which the determination reference speed satisfies a predetermined condition, as a region-of-interest and an image quality setting unit 15 that sets the image quality so that the image of the region-of-interest extracted by the region-of-interest extraction unit 14 among the images acquired by the image acquisition unit 11 has higher image quality than the images of other regions.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an image recording apparatus.

Background Art

[0002] In recent years, development of an image recording apparatus for accurately recording the situation at the time of an accident has been underway.

[0003] Patent Document 1 discloses a technique related to an image processing apparatus that sets an area of interest for an image frame of a moving image captured by an imaging unit, detects an area of a moving object in this image frame, determines whether at least a part of the detected area of the moving object is included in the area of interest, and controls encoding for inside and outside the area of interest of the moving image according to the result of this determination.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In an image recording apparatus such as a drive recorder, the surroundings of a vehicle are constantly photographed, and an image and a video which is an aggregate of images (hereinafter simply referred to as an image) are recorded. In recent years, the images of image recording apparatuses have become higher definition, and accordingly the capacity of image files has also increased.

[0006] In the technology disclosed in Patent Document 1, when a moving object is included in a region of interest (ROI), encoding is performed so that the region of interest has high image quality. In this way, by selectively making the region of interest have high image quality and relatively reducing the image quality of regions other than the region of interest, it is possible to improve the image quality of the necessary region while reducing the capacity of the image file. However, in an image recording device such as a drive recorder, if all regions with movement are made to have high image quality as in the technology disclosed in Patent Document 1, when the vehicle is running, the entire image will have high image quality. Therefore, it is necessary to selectively make regions important to the user, for example, an object approaching the host vehicle equipped with the image recording device, have high image quality.

[0007] The present invention has been made in view of the above points, and an object thereof is to provide an image recording device capable of appropriately suppressing the capacity of an image file while improving the image quality of a necessary region.

Means for Solving the Problems

[0008] The present invention provides an image recording device including an image acquisition unit that acquires an image around the host vehicle, an object recognition unit that recognizes a predetermined object from the image acquired by the image acquisition unit, a determination reference speed calculation unit that calculates a determination reference speed using the speed at which the object recognized by the object recognition unit moves relative to the host vehicle and the speed of the host vehicle, an interest region extraction unit that extracts, as an interest region, a region including an object that satisfies a predetermined condition with respect to the determination reference speed, and an image quality setting unit that sets the image quality of the interest region extracted by the interest region extraction unit among the images acquired by the image acquisition unit to be higher than the image quality of the images of other regions.

[0009] The present invention provides an image recording apparatus including: an image acquisition unit that acquires an image around a host vehicle; an object recognition unit that recognizes a predetermined object from the image acquired by the image acquisition unit and calculates a displacement amount of a position on the image where the object is recognized; a region of interest extraction unit that extracts, as a region of interest, a region including the object when the displacement amount is greater than a predetermined value; and an image quality setting unit that sets the image quality of the image of the region of interest extracted by the region of interest extraction unit among the images acquired by the image acquisition unit to be higher in image quality than the images of other regions.

[0010] The present invention provides an image recording apparatus including: an image acquisition unit that acquires an image around a host vehicle; a motion vector detection unit that detects a motion vector using the image acquired by the image acquisition unit; a region of interest extraction unit that extracts, as a region of interest, a region including a motion vector that satisfies a predetermined condition among the motion vectors detected by the motion vector detection unit; and an image quality setting unit that sets the image quality of the image of the region of interest extracted by the region of interest extraction unit among the images acquired by the image acquisition unit to be higher in image quality than the images of other regions.

Advantages of the Invention

[0011] According to the present disclosure, it is possible to provide an image recording apparatus capable of appropriately suppressing the capacity of an image file while improving the image quality of a necessary region.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0013] <Embodiment 1> Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration example of the image recording apparatus according to Embodiment 1. As shown in FIG. 1, the image recording apparatus 1 according to the present embodiment includes an image acquisition unit 11, an object recognition unit 12, a determination reference speed calculation unit 13, a region of interest extraction unit 14, and an image quality setting unit 15.

[0014] The image recording apparatus 1 records the image acquired by the image acquisition unit 11 in the recording unit 18. At this time, the image quality of the image to be recorded is set in the image quality setting unit 15. In the present embodiment, the recording unit 18 is, for example, a recording medium such as an SD card, an SSD (Solid State Drive), an HDD (hard disk drive), or a memory. The recording unit 18 may be built in the image recording apparatus 1, may be configured to be removable from the image recording apparatus 1, or may be provided outside the image recording apparatus 1.

[0015] The image acquisition unit 11 acquires an image of the surroundings of the host vehicle. The surroundings of the host vehicle may include not only the front of the host vehicle but also the rear, sides, top, and bottom. Further, the image acquisition unit 11 may acquire an image including the interior of the vehicle. The image acquisition unit 11 may be configured to include a camera, or may be configured to receive an image signal output from a separately provided camera.

[0016] The object recognition unit 12 recognizes a predetermined object from the image acquired by the image acquisition unit 11. Specifically, the object recognition unit 12 recognizes an object such as another vehicle or a person from the image acquired by the image acquisition unit 11 using image recognition technology. For example, the object recognition unit 12 includes an object recognition dictionary that has been trained with supervised machine learning using data such as other vehicles and people, and determines whether these objects are included in the image acquired by the image acquisition unit 11. The object recognition unit 12 may recognize a predetermined object from the image acquired by the image acquisition unit 11 using other known image recognition technologies. Note that the objects to be recognized may be objects other than objects such as other vehicles and people, such as guardrails, buildings, street trees, and scenery, and are not limited to these as long as they are generally recognized as obstacles to the travel of the host vehicle. Further, as will be described later, the object recognition unit 12 may calculate the amount of displacement of the recognized object on the image. The amount of displacement of an object is a value obtained by acquiring the horizontal and vertical positions (for example, the center position of the recognized object) of the object on the image over a plurality of frames and calculating the maximum change amount over a predetermined period. The amount of displacement is calculated in pixel units or as a ratio of the amount of displacement occupied in the entire screen of the image, and is the amount by which the recognized object has moved on the image within a predetermined period.

[0017] The determination reference speed calculation unit 13 calculates a determination reference speed using the speed at which the object recognized by the object recognition unit 12 moves relative to the host vehicle and the speed of the host vehicle. For example, the determination reference speed calculation unit 13 calculates the distance between the object and the host vehicle in each frame of the image (it does not have to be every frame), and calculates the speed at which the object moves relative to the host vehicle using the elapsed time and the displacement amount of the distance. Also, sensors such as LiDAR (Light Detection and Ranging) and millimeter-wave radar may be used to measure the distance between the object and the host vehicle, and the speed at which the object moves relative to the host vehicle may be calculated. These sensors may also be used assistively. Furthermore, a stereo camera may be used to measure the distance between the object and the host vehicle, the distance between the object and the host vehicle may be estimated from the size of the photographed license plate, and the position (distance) of the object as seen from the host vehicle may be estimated from the contact position where an object such as another vehicle or a pedestrian touches the ground. Then, the speed at which the object moves relative to the host vehicle may be calculated using the estimated distance of the object and the elapsed time.

[0018] Also, the speed of the host vehicle may be calculated using the position information of the host vehicle obtained using a GNSS (global navigation satellite system) receiver and this position information of the host vehicle and time information. The speed of the host vehicle may be obtained via a CAN (Controller Area Network) to obtain the running speed of the vehicle, or the speed at which stationary objects such as buildings and street trees recognized by the object recognition unit 12 move relative to the host vehicle may be calculated. The determination reference speed calculation unit 13 calculates a determination reference speed using the speed at which the object moves relative to the host vehicle and the speed of the host vehicle obtained in this way. Also, in the present embodiment, vector recognition is performed with the direction in which the host vehicle is moving as positive for the speed of the host vehicle, and a function is provided to recognize the vector in the direction approaching the host vehicle as negative for the speed at which the object moves relative to the host vehicle. In this case, the determination reference speed calculation unit 13 calculates a determination reference speed using the speed of the host vehicle and vector information, and the speed of the object and vector information. An example of calculating the determination reference speed will be described later.

[0019] The region of interest extraction unit 14 extracts, as the region of interest, a region on the image that includes an object whose reference speed calculated by the reference speed calculation unit 13 satisfies a predetermined condition. The predetermined condition is a condition for appropriately extracting an object that needs attention for the running of the host vehicle, excluding an object moving away from the host vehicle, an object approaching the host vehicle at the same speed as the host vehicle speed, that is, a stationary object, etc. For example, the region of interest extraction unit 14 may extract, as the region of interest, a region that includes an object whose reference speed is faster than a predetermined speed.

[0020] As the predetermined condition (speed), the same speed as the host vehicle speed may be set, any speed slower than the host vehicle speed may be set, or any speed faster than the host vehicle speed may be set. Also, the predetermined condition may be changed according to the environment in which the image recording device 1 is used. For example, at night, a slower speed may be set as the predetermined condition than in the daytime. By doing so, at night, a wider region of interest can be extracted than in the daytime, and an object that needs more attention for the running of the host vehicle can be efficiently extracted. The predetermined condition may be set according to the type of object such as another vehicle or a person recognized by the object recognition unit 12. For example, when a person is recognized, a slower speed may be set as the predetermined condition compared to when another vehicle is recognized. By doing so, when a person is recognized, a wider region of interest can be extracted than when another vehicle is recognized, and an object that needs attention for the running of the host vehicle, such as a pedestrian, can be efficiently extracted.

[0021] The region of interest extraction unit 14, for example, divides the image acquired by the image acquisition unit 11 into a predetermined rectangular region such as 9 divisions (3×3) or 16 divisions (4×4) in advance. Then, the region of interest extraction unit 14 extracts, as the region of interest, one or more of the divided regions that include an object whose reference speed satisfies a predetermined condition. At this time, the region of interest extraction unit 14 extracts, as the region of interest, the divided region that includes an object whose reference speed satisfies a predetermined condition for each frame of the image.

[0022] Further, instead of pre-dividing the image, the region of interest extraction unit 14 may extract a rectangular region of any size that includes all objects whose judgment reference speed satisfies a predetermined condition. In this case, in addition to a rectangle, a circular, elliptical, or region of the shape of the object itself may be extracted as the region of interest. Further, the region of interest extraction unit 14 may extract a region that includes a part of an object whose judgment reference speed satisfies a predetermined condition. For example, the region of interest extraction unit 14 may extract a region where the object recognition unit 12 has recognized a predetermined object.

[0023] Further, the region of interest extraction unit 14 may use, as a condition for extracting a region of interest, that the object has a judgment reference speed slower than a predetermined speed and a moving direction the same as that of the host vehicle. By doing so, it is possible to extract other vehicles or two-wheeled vehicles traveling parallel to the host vehicle and not to extract other stopped vehicles or two-wheeled vehicles, and it is possible to efficiently extract objects that require more attention for the running of the host vehicle. Further, the region of interest extraction unit 14 may further extract, as the region of interest, a region that includes an object whose displacement amount recognized by the object recognition unit 12 is larger than a predetermined value. Specific examples of cases where the region of interest extraction unit 14 extracts a region of interest will be described later.

[0024] The image quality setting unit 15 sets the image quality of the image of the region of interest extracted by the region of interest extraction unit 14 among the images acquired by the image acquisition unit 11 to be higher than that of the images of other regions. For example, the image quality setting unit 15 may make the image of the region of interest have a higher image quality than the images of other regions by making the image of the region of interest have a higher image quality than the default image quality. Further, the image quality setting unit 15 may make the image of the region of interest have a higher image quality than the images of other regions by making the images of other regions have a lower image quality than the default image quality. For example, the default image quality is the image quality that is standardly applied to the image acquired by the image acquisition unit 11, and when no region of interest is extracted, the entire image is recorded with the default image quality.

[0025] For example, when using a compression format such as JPEG2000 or M-JPEG, by using the ROI encoding technology that controls the bit rate of the region of interest (ROI) using the Max-Shift method, the image of the region of interest can be set to a higher image quality than the images of other regions. Also, the image can be divided into multiple regions, and the image quality can be made different between the region of interest and other regions by means such as setting encoding parameters for each region. Note that the compression format to be used is not limited to JPEG2000, M-JPEG, etc., and any compression format may be used as long as it is a compression method capable of setting the image quality for each region of the image. For example, a compression format such as H.264 or H.265 may be used.

[0026] Also, the image quality of each region may be controlled over a plurality of frames before and after each frame in which the region of interest is extracted. For example, in the case of a B-frame (Bi-directional Predicted Frame) in moving image compression, the image quality of the front and rear frames including the frame before the frame in which the region of interest is extracted may be controlled.

[0027] Next, the operation (image recording method) of the image recording apparatus 1 according to the present embodiment will be described using the flowchart shown in FIG. 2. First, the image acquisition unit 11 acquires an image around the host vehicle (step S1). Next, the object recognition unit 12 recognizes a predetermined object from the image acquired by the image acquisition unit 11 (step S2). Specifically, the object recognition unit 12 recognizes objects such as other vehicles and persons from the image acquired by the image acquisition unit 11 using image recognition technology.

[0028] Next, the determination reference speed calculation unit 13 calculates a determination reference speed using the speed at which the object recognized by the object recognition unit 12 moves relative to the host vehicle and the speed of the host vehicle (step S3). Then, when there is an object whose determination reference speed calculated by the determination reference speed calculation unit 13 satisfies a predetermined condition (step S4: Yes), the region of interest extraction unit 14 extracts, as a region of interest, the region on the image including the object whose determination reference speed satisfies the predetermined condition (step S5). On the other hand, when there is no object whose determination reference speed calculated by the determination reference speed calculation unit 13 satisfies the predetermined condition (step S4: No), the process returns to the process of step S1.

[0029] Next, the image quality setting unit 15 sets the image quality of the image of the region of interest extracted by the region of interest extraction unit 14 among the images acquired by the image acquisition unit 11 to be higher than the images of other regions (step S6). Then, the image recording device 1 records the image acquired by the image acquisition unit 11 in the recording unit 18 (step S7). At this time, the image is recorded in the recording unit 18 with the image quality set by the image quality setting unit 15. Thereafter, the operations of steps S1 to S7 are repeated.

[0030] Next, an operation example of the image recording device 1 according to the present embodiment will be specifically described with reference to FIGS. 3 to 8.

[0031] First, as shown in FIG. 3, a case where another vehicle 22 is traveling in the oncoming lane with respect to the host vehicle 21 and the host vehicle 21 and the other vehicle 22 pass by each other will be described. In the case shown in FIG. 3, the host vehicle 21 is moving at a speed of 60 km / h in the upward direction on the paper surface. The vector of the host vehicle 21 at this time is positive (+). Further, the other vehicle 22 is moving at a speed of 60 km / h in the downward direction on the paper surface. Since the other vehicle 22 located in front of the host vehicle 21 is moving in a direction approaching the host vehicle 21, the vector of the other vehicle 22 is negative (-). At this time, the speed at which the other vehicle 22 moves with respect to the host vehicle 21 calculated by the determination reference speed calculation unit 13 is 120 km / h. Also, combined with the speed of the host vehicle 21 of 60 km / h, the speed of the other vehicle 22 is calculated to be 60 km / h.

[0032] Since the moving speed of the host vehicle 21 is 60 km / h and the vector is positive, and the moving speed of the other vehicle 22 is 60 km / h and the vector is negative, the determination reference speed calculation unit 13 calculates the determination reference speed as "+60 - (-60) = 120 km / h". The region of interest extraction unit 14 extracts, as the region of interest, a region including an object for which the determination reference speed calculated in this way satisfies a predetermined condition. For example, when the region of interest extraction unit 14 sets the speed of the host vehicle 21 as 60 km / h as a predetermined condition, since the determination reference speed 120 km / h is higher than the speed of the host vehicle 21, which is 60 km / h, the region of interest extraction unit 14 extracts the region including the other vehicle 22 as the region of interest. In other words, when the host vehicle 21 is traveling, the region of interest extraction unit 14 extracts, as the region of interest, a region including an object that exists in the traveling direction of the host vehicle 21 and shows a movement having a negative vector in the direction approaching the host vehicle 21. Then, the image quality setting unit 15 sets the image quality of the region of interest including the other vehicle 22 to be higher than the image quality of the images of other regions.

[0033] Next, as shown in FIG. 4, a case where the host vehicle 21 and the other vehicle 22 are traveling in the same lane and the other vehicle 22 is traveling in front of the host vehicle 21 will be described. In the case shown in FIG. 4, the host vehicle 21 is moving at a speed of 60 km / h in the direction of the paper surface. At this time, the vector of the host vehicle 21 is positive (+). Also, the other vehicle 22 located in front of the host vehicle 21 is also moving at a speed of 60 km / h in the direction of the paper surface. Since the other vehicle 22 is not moving in the direction approaching the host vehicle 21, the vector of the other vehicle 22 is positive (+). At this time, the speed at which the other vehicle 22 moves with respect to the host vehicle 21 calculated by the determination reference speed calculation unit 13 is 0 km / h. Also, combining the speed of the host vehicle 21, which is 60 km / h, the speed of the other vehicle 22 is calculated as 60 km / h.

[0034] Since the moving speed of the host vehicle 21 is 60 km / h and the vector is positive, and the moving speed of the other vehicle 22 is 60 km / h and the vector is positive, the determination reference speed calculation unit 13 calculates the determination reference speed as "+60-(+60)=0 km / h". The region of interest extraction unit 14 extracts, as the region of interest, a region including an object for which the determination reference speed calculated in this way satisfies a predetermined condition. For example, when the speed of the host vehicle 21 is set as a predetermined condition, since the determination reference speed of 0 km / h is lower than the speed of the host vehicle 21 of 60 km / h, the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest. In other words, when the host vehicle 21 is traveling, the region of interest extraction unit 14 does not extract, as the region of interest, a region including an object that exists in the traveling direction of the host vehicle 21 and has a positive vector in the direction away from the host vehicle 21. Also, the region of interest extraction unit 14 does not extract, as the region of interest, a region including an object that is not moving (vector is zero) with respect to the host vehicle 21. In this case, the image quality setting unit 15 sets the image including the other vehicle 22 to the same image quality as the images of the other regions.

[0035] In the example shown in FIG. 4, when the moving speed of the other vehicle 22 is 80 km / h, the speed at which the other vehicle 22 moves with respect to the host vehicle 21 calculated by the determination reference speed calculation unit 13 is 20 km / h. Combining with the speed of the host vehicle 21 of 60 km / h, the speed of the other vehicle 22 is calculated as 80 km / h. Since the vector of the other vehicle 22 is positive, the determination reference speed is "+60-(+80)=-20 km / h". In this case, since the determination reference speed of -20 km / h is lower than the speed of the host vehicle 21 of 60 km / h, the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest. That is, when the other vehicle 22 is traveling in front of the host vehicle 21 and the moving speed of the other vehicle 22 is higher than the speed of the host vehicle 21, the determination reference speed becomes a negative value, so the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest.

[0036] On the other hand, when the moving speed of the other vehicle 22 is 40 km / h, the speed at which the other vehicle 22 moves with respect to the host vehicle 21 calculated by the determination reference speed calculation unit 13 is 20 km / h. Combining with the speed of the host vehicle 21 of 60 km / h, the speed of the other vehicle 22 is calculated as 40 km / h. Since the other vehicle 22 approaches the host vehicle 21, the vector is negative. In this case, the determination reference speed is "+60 - (-40) = 100 km / h". Since the determination reference speed 100 km / h is faster than the speed of the host vehicle 21 of 60 km / h, the region of interest extraction unit 14 extracts the region including the other vehicle 22 as the region of interest. Then, the image quality setting unit 15 sets the image quality of the region of interest including the other vehicle 22 to be higher than the image quality of the other regions. That is, when the other vehicle 22 is traveling in front of the host vehicle 21 and the moving speed of the other vehicle 22 is slower than the moving speed of the host vehicle 21, the vector is negative because the other vehicle 22 approaches the host vehicle 21. In this case, since the determination reference speed is faster than the speed of the host vehicle 21, the region of interest extraction unit 14 extracts the region including the other vehicle 22 as the region of interest. In other words, when the host vehicle 21 is traveling, the region of interest extraction unit 14 extracts, as the region of interest, a region including an object that exists in the traveling direction of the host vehicle 21 and shows a movement having a negative vector in the direction approaching the host vehicle 21.

[0037] In the present embodiment, by setting the vector of the object approaching the host vehicle 21 to be negative in this way, the determination reference speed can be intentionally increased. That is, the calculation of the determination reference speed in the present embodiment changes the direction of the vector depending on whether the object approaches the host vehicle 21 or not, which is different from the calculation of the so-called relative speed. Therefore, the calculated numerical value itself does not match the relative speed and is a calculated value unique to the present embodiment. By using such a calculated value, the region of interest can be appropriately extracted.

[0038] Next, as shown in FIG. 5, a case where the host vehicle 21 is traveling on a road with roadside trees (scenery) 25 will be described. In the case shown in FIG. 5, the host vehicle 21 is moving at a speed of 60 km / h in the direction of the paper surface. At this time, the vector of the host vehicle 21 is positive (+). Also, since the roadside trees (scenery) 25 located in front of the host vehicle 21 are stationary, the moving speed is 0 km / h. Since the roadside trees (scenery) 25 approach the host vehicle 21, the vector becomes negative. At this time, the speed at which the roadside trees (scenery) 25 move with respect to the host vehicle 21, which is calculated by the determination reference speed calculation unit 13, is 60 km / h. Combining with the speed of the host vehicle 21 of 60 km / h, the speed of the roadside trees (scenery) 25 is calculated as 0 km / h.

[0039] Since the moving speed of the host vehicle 21 is 60 km / h, the vector is positive, the moving speed of the roadside trees 25 is 0 km / h, and the vector is negative, the determination reference speed calculation unit 13 calculates the determination reference speed as "+60 - (0) = 60 km / h". Since the determination reference speed of 60 km / h is the same as the speed of the host vehicle 21 of 60 km / h, the region of interest extraction unit 14 does not extract the roadside trees 25 as the region of interest. In this case, the image quality setting unit 15 sets the image including the roadside trees 25 to the same image quality as the images of other regions.

[0040] Here, although neither the other vehicle 22 shown in FIG. 4 nor the street tree 25 shown in FIG. 5 is extracted as an area of interest, the other vehicle 22 shown in FIG. 4 is moving at the same speed as the host vehicle 21. Therefore, compared with the stationary street tree 25 shown in FIG. 5, the other vehicle 22 shown in FIG. 4 may be considered to have a higher degree of danger to the host vehicle 21. In this case, in the present embodiment, the other vehicle 22 shown in FIG. 4 may be extracted as an area of interest. That is, even when the determination reference speed is slower than a predetermined speed, the area-of-interest extraction unit 14 may extract, as an area of interest, an area including an object moving in the same direction as the host vehicle. For example, at this time, the area-of-interest extraction unit 14 sets as a predetermined condition that the speed at which the other vehicle 22 moves relative to the host vehicle 21, i.e., 0 km / h, is within a predetermined range (for example, ±3 km / h). Since the predetermined condition is satisfied, the area including the other vehicle 22 can be extracted as an area of interest. The predetermined range is preferably variable according to the moving speed of the host vehicle 21.

[0041] In this case, the image quality setting unit 15 may set the image quality in three levels. For example, the image quality setting unit 15 may set the area not extracted as an area of interest to low image quality, and set the area of interest including an object whose determination reference speed is faster than a predetermined speed to high image quality. Further, the image quality setting unit 15 may set the area of interest including an object whose determination reference speed is slower than a predetermined speed and whose moving direction is the same as that of the host vehicle to an image quality (medium image quality) between low image quality and high image quality.

[0042] Next, as shown in FIG. 6, a case where a person 26 approaches the host vehicle 21 parked in a parking lot will be described. In the case shown in FIG. 6, since the host vehicle 21 is stopped, the moving speed is 0 km / h. Also, the person 26 located in front of the host vehicle 21 is moving at a speed of 4 km / h. At this time, since the person 26 is moving in a direction approaching the host vehicle 21, the vector of the person 26 is negative (-). At this time, the speed at which the person 26 moves relative to the host vehicle 21 calculated by the determination reference speed calculation unit 13 is 4 km / h. Combining with the speed of the host vehicle 21, which is 0 km / h, the speed of the person 26 is calculated to be 4 km / h.

[0043] Since the moving speed of the host vehicle 21 is 0 km / h, the moving speed of the person 26 is 4 km / h, and the vector is negative, the determination reference speed calculation unit 13 calculates the determination reference speed as "0 - (-4) = 4 km / h". When the speed of the host vehicle 21 is set as a predetermined condition, since the determination reference speed of 4 km / h is faster than the speed of the host vehicle 21 which is 0 km / h, the region of interest extraction unit 14 extracts the region including the person 26 as the region of interest. In other words, when the host vehicle 21 is stopped, the region of interest extraction unit 14 extracts, as the region of interest, the region including an object that exists around the host vehicle and shows a movement having a negative vector in the direction approaching the host vehicle. Then, the image quality setting unit 15 sets the image quality of the region of interest including the person 26 to be higher than the image quality of other regions.

[0044] In the example shown in FIG. 6, when the person 26 is moving in the direction away from the host vehicle 21, since the vector of the person 26 is positive, the determination reference speed is "0 - (+4) = -4 km / h". In this case, since the determination reference speed of -4 km / h is smaller than the speed of the host vehicle 21 which is 0 km / h, the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest.

[0045] Also, when the host vehicle 21 is stopped as in the example shown in FIG. 6, although there are cases where objects such as trees and flags swaying in the wind are recognized as movements and approach the host vehicle 21, it is preferable to record objects with a small displacement amount in the image in low image quality. For this reason, the region of interest extraction unit 14 may extract, as the region of interest, the region including this object when the displacement amount of the object calculated by the object recognition unit 12 is larger than a predetermined value. Thereby, objects such as trees and flags swaying in the wind, which stay in a region with limited movement displacement, are not extracted as the region of interest, and objects with a large displacement amount in the image, such as other vehicles crossing the image from the left end to the right end and a person walking on a crosswalk in front of the host vehicle 21, can be appropriately extracted as the region of interest.

[0046] Next, as shown in FIG. 7, a case where another vehicle 22 approaches the own vehicle 21 parked in a parking lot will be described. In the case shown in FIG. 7, since the own vehicle 21 is stopped, the moving speed is 0 km / h. Also, another vehicle 22 located in front of the own vehicle 21 is trying to park in reverse in the parking lot and is moving at a speed of 5 km / h. At this time, since the other vehicle 22 is moving in the direction approaching the own vehicle 21, the vector of the other vehicle 22 is negative (-).

[0047] Since the moving speed of the own vehicle 21 is 0 km / h, the moving speed of the other vehicle 22 is 5 km / h, and the vector is negative, the determination reference speed calculation unit 13 calculates the determination reference speed as "0 - (-5) = 5 km / h". When the speed of the own vehicle 21 is set as a predetermined condition, since the determination reference speed of 5 km / h is faster than the speed of the own vehicle 21 of 0 km / h, the region of interest extraction unit 14 extracts the region including the other vehicle 22 as the region of interest. In other words, when the own vehicle 21 is stopped, the region of interest extraction unit 14 extracts, as the region of interest, a region including an object that exists around the own vehicle and shows a movement having a negative vector in the direction approaching the own vehicle. Then, the image quality setting unit 15 sets the image quality of the region of interest including the other vehicle 22 to be higher than the image quality of the other regions.

[0048] Next, as shown in FIG. 8, a case where the own vehicle 21 and another vehicle 22 traveling behind the own vehicle 21 are traveling in the same lane and the other vehicle 22 is approaching the own vehicle 21 will be described. In the case shown in FIG. 8, the own vehicle 21 is moving at a speed of 60 km / h in the direction of the paper surface. At this time, the vector of the own vehicle 21 is positive (+). Also, another vehicle 22 located behind the own vehicle 21 is moving at a speed of 100 km / h in the direction of the paper surface. Since the other vehicle 22 is moving in the direction approaching the own vehicle 21, the vector of the other vehicle 22 is negative (-). At this time, the speed at which the other vehicle 22 moves with respect to the own vehicle 21 calculated by the determination reference speed calculation unit 13 is 40 km / h. Combining with the speed of the own vehicle 21 of 60 km / h, the speed of the other vehicle 22 is calculated as 100 km / h.

[0049] Since the moving speed of the host vehicle 21 is 60 km / h and the vector is positive, and the moving speed of the other vehicle 22 is 100 km / h and the vector is negative, the determination reference speed calculation unit 13 calculates the determination reference speed as "+60 - (-100) = 160 km / h". For example, when the speed of the host vehicle 21 is set as a predetermined condition, since the determination reference speed 160 km / h is faster than the speed of the host vehicle 21 which is 60 km / h, the region of interest extraction unit 14 extracts the region including the other vehicle 22 as the region of interest. In other words, when the host vehicle 21 is running, the region of interest extraction unit 14 extracts, as the region of interest, a region including an object showing a movement having a negative vector that exists in the direction opposite to the traveling direction of the host vehicle 21 and is approaching the host vehicle 21. Then, the image quality setting unit 15 sets the image quality of the region of interest including the other vehicle 22 to be higher than the images of other regions.

[0050] In addition, in the example shown in FIG. 8, when the moving speed of the other vehicle 22 is 50 km / h, since the other vehicle 22 is moving away from the host vehicle 21, the vector of the other vehicle 22 becomes positive. In this case, the determination reference speed is "+60 - (+50) = +10 km / h". Since the determination reference speed +10 km / h is slower than the speed of the host vehicle 21 which is 60 km / h, the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest. That is, when the host vehicle 21 and the other vehicle 22 are traveling in the same direction and the moving speed of the other vehicle 22 is slower than the speed of the host vehicle 21, since the determination reference speed is slower than the speed of the host vehicle 21, the region of interest extraction unit 14 does not extract the region including the other vehicle 22 as the region of interest.

[0051] As described above, in the image recording apparatus 1 according to the present embodiment, a predetermined object is recognized from the image acquired by the image acquisition unit, a determination reference speed is calculated using the speed of the recognized object and the speed of the host vehicle, and a region including an object whose determination reference speed satisfies a predetermined condition is extracted as a region of interest. Then, the image quality of the image of the extracted region of interest is set to be higher than the image quality of the images of other regions. Therefore, by selectively setting the image quality of the region of interest, which is important for the user, that is, an object approaching the host vehicle, to be high and setting the image quality of the regions other than the region of interest to be relatively low, it is possible to improve the image quality of the necessary regions while appropriately suppressing the capacity of the image file. As a result, it becomes possible to record the image acquired by the image acquisition unit for a long time. In addition, since the capacity of the image file can be reduced, the burden on the user of adding an additional memory for recording images can be reduced. Further, in the image recording apparatus according to the present embodiment, by selectively setting the image quality of the region of interest to be higher than the image quality of the regions other than the region of interest, it is possible to appropriately suppress the capacity of the image file while enhancing the image quality of the regions important for the user.

[0052] <Embodiment 2> Next, Embodiment 2 of the present invention will be described. FIG. 9 is a block diagram showing a configuration example of an image recording apparatus according to Embodiment 2. As shown in FIG. 9, the image recording apparatus 2 according to the present embodiment includes an image acquisition unit 11, a motion vector detection unit 31, a region of interest extraction unit 14, and an image quality setting unit 15. Note that the image recording apparatus 2 according to the present embodiment is different from the image recording apparatus 1 according to Embodiment 1 in that it includes a motion vector detection unit 31 instead of an object recognition unit 12 and a determination reference speed calculation unit 13. Other than this, since it is the same as the image recording apparatus 1 according to Embodiment 1, the same reference numerals are assigned to the same components, and redundant descriptions are omitted as appropriate.

[0053] The image acquisition unit 11 acquires an image of the surroundings of the host vehicle. In the present embodiment, the image acquisition unit 11 will be described as acquiring an image from a camera installed to image the front of the vehicle. The motion vector detection unit 31 detects a motion vector using the image acquired by the image acquisition unit 11. For example, the motion vector detection unit 31 detects a motion vector for each pixel in the image acquired by the image acquisition unit 11. Further, the motion vector detection unit 31 may divide the image acquired by the image acquisition unit 11 into a plurality of pre-fixed rectangular regions such as 9 divisions or 16 divisions, and detect a motion vector for each of the divided regions thus obtained.

[0054] The region of interest extraction unit 14 extracts, as a region of interest, a region including a motion vector that satisfies a predetermined condition among the motion vectors detected by the motion vector detection unit 31. For example, when the host vehicle is traveling, an object that is stationary in the image acquired by the image acquisition unit 11 spreads radially outward from the imaging center. This radial motion is a motion corresponding to the traveling speed of the vehicle and the steering wheel angle, and becomes faster toward the edge of the image. When a motion vector that does not match the radially spreading motion is detected by the region of interest extraction unit 14 and the amount of this motion vector is equal to or greater than a predetermined threshold, this motion vector is regarded as a motion vector that satisfies a predetermined condition, and the region including this motion vector is extracted as the region of interest. In other words, when the motion vector detected by the motion vector detection unit 31 does not show the same motion vector as a stationary object and the amount of this motion vector is equal to or greater than a predetermined threshold, the region of interest extraction unit 14 determines that the predetermined condition is satisfied and extracts the region including this motion vector as the region of interest.

[0055] For example, when the motion vector detection unit 31 detects a motion vector for each pixel in the image, the region of interest extraction unit 14 may extract, as the region of interest, a region including motion vectors that satisfy a predetermined condition. At this time, the region of interest may be extracted in a predetermined shape and size such as a rectangle or an ellipse. Also, when the motion vector detection unit 31 detects a motion vector for each divided region, the region of interest extraction unit 14 may extract, as the region of interest, a divided region including motion vectors that satisfy a predetermined condition. For example, when motion vectors that satisfy a predetermined condition span a plurality of divided regions, a plurality of divided regions in which motion vectors that satisfy a predetermined condition exist may be extracted as the region of interest.

[0056] The image quality setting unit 15 sets the image quality of the image of the region of interest extracted by the region of interest extraction unit 14 among the images acquired by the image acquisition unit 11 to be higher than the images of other regions. That is, the image quality setting unit 15 sets the image quality of the image including the pixels or divided regions in which motion vectors that satisfy a predetermined condition are detected to be higher than the images of other regions.

[0057] As described above, in the image recording apparatus 2 according to the present embodiment, motion vectors are detected using the images acquired by the image acquisition unit, and a region including motion vectors that satisfy a predetermined condition among the detected motion vectors is extracted as the region of interest. Then, the image quality of the extracted region of interest is set to be higher than the images of other regions. Therefore, by selectively making the region of interest, which is important to the user, i.e., the object whose motion vector is different from the motion vectors of other objects, have a high image quality and making the image quality of the regions other than the region of interest relatively low, it is possible to improve the image quality of the necessary regions while appropriately suppressing the capacity of the image file. As a result, it becomes possible to record the images acquired by the image acquisition unit for a long time. Also, since the capacity of the image file can be reduced, the burden on the user to add more memory for recording images can be reduced.

[0058] Using FIG. 10, a hardware configuration example of the control device of the image recording apparatus according to Embodiments 1 and 2 will be described. In FIG. 10, the image recording apparatus has a processor 101 and a memory 102. The processor 101 may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). The processor 101 may include a plurality of processors. The memory 102 is composed of a combination of a volatile memory and a non-volatile memory. The memory 102 may include a storage arranged separately from the processor 101. In this case, the processor 101 may access the memory 102 via an I / O interface (not shown).

[0059] Also, each device in the above-described embodiments is configured by hardware or software, or both, and may be configured from one piece of hardware or software, or may be configured from a plurality of pieces of hardware or software. The functions (processes) of each device in the above-described embodiments may be realized by a computer. For example, a program for performing the operations in the embodiments may be stored in the memory 102, and each function may be realized by the processor 101 executing the program stored in the memory 102.

[0060] Such programs can be stored using various types of non-transitory computer readable media and supplied to a computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (such as flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (such as magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memories (such as mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)). Also, the program may 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 transitory computer readable media can supply the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

[0061] Note that the present invention is not limited to the above embodiments and can be appropriately modified without departing from the gist. For example, regarding Embodiment 1, the operation example was described using FIGS. 3 to 8, but the calculation method of the determination reference speed calculated by the determination reference speed calculation unit 13 is not limited to the above-described calculation method, and the speed (relative speed) at which the other vehicle 22 or the person 26 moves with respect to the host vehicle 21 may be used as it is. In this case, the region of interest extraction unit 14 changes predetermined conditions and extracts the region of interest according to whether the vector in which the other vehicle 22 or the person 26 moves approaches the host vehicle 21, whether the relative speed at which the other vehicle 22 or the person 26 moves is the same as the speed of the host vehicle 21, whether the other vehicle 22 or the person 26 is located in the traveling direction of the host vehicle 21 or in the opposite direction of the traveling direction of the host vehicle 21, etc.

[0062] As described above, the present invention has been described in accordance with the above embodiments. However, the present invention is not limited only to the configurations of the above embodiments, and of course includes various modifications, corrections, and combinations that can be made by those skilled in the art within the scope of the invention of the claims of the present patent application.

Explanation of Signs

[0063] 1, 2 Image recording device 11 Image acquisition unit 12 Object recognition unit 13 Judgment reference speed calculation unit 14 Region of interest extraction unit 15 Image quality setting unit 18 Recording unit 21 Own vehicle 22 Other vehicle 31 Motion vector detection unit 101 Processor 102 Memory

Claims

1. An image acquisition unit that acquires an image around the host vehicle, An object recognition unit that recognizes a predetermined object from the image acquired by the image acquisition unit, A reference speed calculation unit that calculates a reference speed using the speed at which the object recognized by the object recognition unit moves relative to the host vehicle and the speed of the host vehicle, An interest area extraction unit that extracts, as an interest area, an area including an object that satisfies a predetermined condition with respect to the reference speed, A picture quality setting unit that sets the picture quality of the image of the interest area extracted by the interest area extraction unit to be higher in picture quality than the images of other areas among the images acquired by the image acquisition unit, and The predetermined condition is set according to the type of the object recognized by the object recognition unit, An image recording device.

2. The image recording device according to claim 1, wherein the predetermined condition is set according to the environment in which the image recording device is used.

3. The interest area extraction unit extracts, as an interest area, an area including the object when the moving direction of the object is the same as that of the host vehicle even when the reference speed is slower than a predetermined speed. The image recording device according to claim 1 or 2.

4. The object recognition unit further calculates a displacement amount of a position on the image where the object is recognized, The interest area extraction unit extracts, as an interest area, an area including the object on the further condition that the displacement amount is larger than a predetermined value. The image recording device according to any one of claims 1 to 3.

5. Further comprising a motion vector detection unit that detects a motion vector using the image acquired by the image acquisition unit, The interest area extraction unit extracts, as an interest area, an area that includes a motion vector that satisfies a predetermined condition among the motion vectors detected by the motion vector detection unit as a further condition. The image recording device according to any one of claims 1 to 4.

Images