阅读说明：本技术 摄像机装置 (Camera device ) 是由 岩崎启佑 永崎健 远藤健 于 2019-09-19 设计创作，主要内容包括：本发明提供一种能够提高限制解除标志的检测精度的摄像机装置。运算处理部(搜索部)从图像中搜索斜线候选(斜线搜索504)。运算处理部(选择部)从检测出的斜线候选中选择限制解除标志的斜线候选,该限制解除标志表示与主标志对应的限制的解除(斜线判定505)。运算处理部(限制解除标志识别部)从选择出的限制解除标志的斜线候选的图像中识别限制解除标志(识别处理506)。(The invention provides a camera device capable of improving detection precision of a restriction release mark. The arithmetic processing unit (search unit) searches for a diagonal line candidate from the image (diagonal line search 504). The arithmetic processing unit (selection unit) selects a diagonal line candidate of a restriction cancellation flag indicating cancellation of the restriction corresponding to the main flag, from among the detected diagonal line candidates (diagonal line determination 505). The arithmetic processing unit (limitation canceling mark recognizing unit) recognizes the limitation canceling mark from the image of the diagonal line candidate of the selected limitation canceling mark (recognition processing 506).)

1. A camera device is characterized by comprising:

a search unit that searches for a diagonal line candidate from an image;

a selection unit that selects, from the detected diagonal line candidates, a diagonal line candidate of a restriction cancellation flag indicating cancellation of restriction corresponding to a main flag; and

and a restriction cancellation flag recognition unit that recognizes the restriction cancellation flag from the image of the diagonal line candidate of the selected restriction cancellation flag.

2. The camera device of claim 1,

the search unit scans the image in a horizontal direction, searches for a pair of a left edge and a right edge, and detects 2 or more pairs arranged in series as the diagonal line candidates.

3. The camera device of claim 2,

further comprising a storage unit for storing a size of the main mark and a range of a vertical length of a diagonal line of the restriction release mark in association with each other,

the selection unit selects the diagonal line candidate whose vertical length is within a range of the vertical length of the diagonal line of the restriction cancellation flag associated with the size of the main flag.

4. The camera device of claim 3,

the storage unit stores a size of the main mark and a range of a lateral length of a diagonal line of the restriction release mark in association with each other,

the search section searches for the pair of the left edge and the right edge whose distance between the left edge and the right edge is within a range of a lateral length of an oblique line of the limitation lifting sign associated with a size of a main sign.

5. The camera device of claim 3,

further comprises a main mark recognition unit for recognizing the main mark,

the storage unit further stores information indicating a relative position of the restriction release flag with respect to the position of the main flag,

the search unit searches for the slant line candidate from an area of the image corresponding to a relative position of the restriction release flag with respect to the position of the identified main flag.

6. The camera device of claim 5,

the search unit searches for the slant line candidate by identifying the main flag as a trigger.

7. The camera device of claim 5,

the storage unit stores information indicating a relative position of the restriction release flag with respect to the position of the main flag for each travel area,

the search unit searches for the slant line candidate from an area of the image corresponding to a relative position of the restriction release flag with respect to the position of the identified main flag for each of the travel area.

Technical Field

The present invention relates to a camera device.

Background

In recent years, with the spread of in-vehicle camera devices, there has been an increasing demand for various recognition functions for safe driving or automatic driving. In particular, since the stereo camera device simultaneously measures visual information based on an image and distance information to an object, it is possible to grasp various objects (people, cars, three-dimensional objects, road surfaces, road surface signs, billboard signs, etc.) around the car in detail, and it is also helpful to improve safety during driving support.

The demand for the identification function of the mark is increasing at home and abroad, and improvement of the identification accuracy is being sought. One of the causes of the accuracy deterioration is difficulty in detecting and recognizing the restriction cancellation flag. The limitation lifting flag is difficult to detect because of reasons such as a small size due to a different design from the speed flag and the like, and a sufficient contrast difference from the background due to a small width of the peripheral ring. As a result of failing to detect and recognize the limitation canceling flag, the previous display is continued even in a situation where the speed limitation display should be ended, and therefore, a problem arises in that accurate speed information is provided to the driver.

Various technologies and devices related to an in-vehicle camera device mounted on a vehicle and recognizing a situation ahead of the vehicle have been proposed. For example, patent document 1 is known as a technique for improving the performance of the marker recognition and focusing on the improvement of the recognition accuracy.

Documents of the prior art

Patent document

Patent document 1: japanese patent laid-open publication No. 2015-191621

Disclosure of Invention

Problems to be solved by the invention

However, the technique disclosed in patent document 1 has a problem that a flag (limitation canceling flag) for instructing limitation canceling such as speed limitation is not detected as one of causes of accuracy deterioration.

In view of the above problems, an object of the present invention is to provide a camera device capable of improving the detection accuracy of a restriction cancellation flag.

Means for solving the problems

In order to achieve the above object, the present invention includes: a search unit that searches for a diagonal line candidate from an image; a selection unit that selects, from the detected diagonal line candidates, a diagonal line candidate of a restriction cancellation flag indicating cancellation of a restriction corresponding to a main flag; and a restriction cancellation flag recognition unit that recognizes the restriction cancellation flag from the image of the diagonal line candidate of the selected restriction cancellation flag.

Effects of the invention

According to the invention, the detection precision of the restriction release flag can be improved. Problems, configurations, and effects other than those described above will be apparent from the following description of the embodiments.

Drawings

Fig. 1 is a block diagram showing an overall configuration of an in-vehicle stereo camera device according to an embodiment of the present invention.

Fig. 2 is a diagram showing a basic processing flow of the in-vehicle stereo camera apparatus.

Fig. 3 is a timing chart showing various processes.

Fig. 4A is a diagram showing a part of an image stored in an image buffer memory.

Fig. 4B shows the result of the image processing performed on the image of fig. 4A, and shows an image having luminance at a portion where the change in shading is large.

Fig. 4C is a diagram showing a basic processing flow of the identification flag.

Fig. 5 is a diagram showing a processing flow of the restriction release flag detection in the embodiment of the present invention.

Fig. 6A is a diagram showing an outline of processing of the diagonal line search shown in fig. 5.

Fig. 6B is a diagram showing a pair of continuous edges (left and right pairs).

Fig. 7 is a diagram for explaining locking (selection) of the diagonal line candidates in the diagonal line determination shown in fig. 5.

Fig. 8 is a diagram for explaining cooperation with another system that gives a trigger to the processing of the restriction release flag detection.

Detailed Description

Embodiments of the present invention will be described below with reference to the drawings. Although the above object is partially overlapped, the present embodiment aims to provide a camera device that detects a mark according to a restriction-lifted design and can suppress a pattern erroneously determined as a tree, a utility pole, or the like.

Fig. 1 is a block diagram showing an overall configuration of an in-vehicle stereo camera device 100 (camera device) according to the present embodiment. The in-vehicle stereo camera device 100 according to the present embodiment is mounted on a vehicle, and recognizes an environment outside the vehicle based on image information of a photographing target area in front of the vehicle. The in-vehicle stereo camera device 100 recognizes white lines of roads, pedestrians, vehicles, other three-dimensional objects, traffic lights, signs, illumination lamps, and the like, and adjusts braking, steering, and the like of a vehicle (own vehicle) on which the stereo camera device is mounted.

The in-vehicle stereo camera device 100 includes: 2 cameras 101 and 102 arranged on the left and right sides for acquiring image information, and an image input interface 103 for controlling the shooting by the cameras 101 and 102 and receiving the shot images. The image received through the interface is transmitted via the bus 109 and processed by the image processing unit 104 and the arithmetic processing unit 105. Image data and the like that are the results of the processing and the final results are stored in the storage unit 106. In addition, control lines of the camera 101, the camera 102, and the like are not shown in fig. 1 for easy viewing of the drawing.

The image processing unit 104 compares the 1 st image obtained from the image pickup device of the camera 101 with the 2 nd image obtained from the image pickup device of the camera 102, performs image correction such as correction of device-specific variation due to the image pickup device and noise interpolation on the respective images, and stores them in the storage unit 106. Further, the image processing unit 104 calculates the portions corresponding to each other between the 1 st image and the 2 nd image, calculates the parallax information, and stores these in the storage unit 106 in the same manner as before.

The arithmetic processing unit 105 recognizes various objects necessary for sensing the environment around the vehicle using the image and the parallax information (distance information with respect to each point on the image) stored in the storage unit 106. The various objects include people, cars, other obstacles, traffic lights, signs, tail lights or head lights of cars, and the like. A part of these recognition results or intermediate calculation results is recorded in the storage section 106 in the same manner as before. The arithmetic processing unit 105 performs various object recognition processes on the captured image, and then calculates the control of the vehicle using the recognition results.

A part of the vehicle control policy and the object recognition result obtained as the calculation result is transmitted to a vehicle-mounted Network CAN (Controller Area Network) through a CAN interface 107, whereby the vehicle is braked. In addition, these operations are configured (configured) to prevent abnormal operations by monitoring whether or not each processing unit has not caused abnormal operations, whether or not errors have occurred during data transmission, and the like by the control processing unit 108.

The image processing unit 104 is connected to a control processing unit 108, a storage unit 106, an arithmetic processing unit 105, an image input interface 103 (an input/output unit with the image pickup devices of the cameras 101 and 102), and a CAN interface 107 (an input/output unit with an external in-vehicle network) via a bus 109 (an internal bus).

The image processing unit 104, the arithmetic processing unit 105, the storage unit 106, the image input interface 103, the CAN interface 107, and the control processing unit 108 are configured by one or more computer units. The storage unit 106 is configured by a memory that stores, for example, image information obtained by the image processing unit 104, image information created as a result of scanning by the arithmetic processing unit 105, and the like. The CAN interface 107 outputs information output from the in-vehicle stereo camera device 100 to another control system of the own vehicle via the CAN 110.

Fig. 2 shows a processing flow of the in-vehicle stereo camera apparatus 100.

The left and right cameras 101, 102 capture images. The image processing unit 104 performs image processing 205 such as correction for absorbing characteristics (image distortion and the like) inherent in the image pickup devices of the cameras 101 and 102 on each of the image data 203 and 204 captured by the left and right cameras 101 and 102. The processing result is stored in the image buffer memory 206. The image buffer memory 206 is provided in the storage section 106 of fig. 1.

Further, the image processing unit 104 performs a matching process 207 of obtaining parallax information of the images obtained by the left and right cameras by performing a matching process (matching) between the images using the corrected 2 images. The position and position of a certain target point on the target object on the images of the left and right cameras are clarified by the parallax of the left and right images, and the distance to the target object can be obtained according to the principle of triangulation. The image and the parallax information finally obtained by the image processing 205 and the parallax processing 207 are stored in the storage unit 106.

The arithmetic processing unit 105 further performs various object recognition processing 209 using the stored image and parallax information. The object to be recognized includes a person, a vehicle, another three-dimensional object, a sign, a traffic signal, a tail lamp, and the like, and the arithmetic processing unit 105 uses the recognition dictionary 210 as necessary when recognizing.

Further, the arithmetic processing unit 105 performs the vehicle control processing 211 in consideration of the result of the object recognition and the state (speed, steering angle, etc.) of the host vehicle. The vehicle control processing 211 is processing as follows: for example, a warning is issued to the occupant, braking such as braking of the vehicle or steering angle adjustment is performed, or a policy for avoiding control of the object is determined based on the braking, and the result is output via the CAN interface 107.

As described above, the various object recognition processing 209 and the vehicle control processing 211 are performed by the arithmetic processing unit 105 in fig. 1, and output to the CAN is performed by the CAN interface 107. These respective processing means are constituted by, for example, a single or a plurality of computer units, and are configured to be able to exchange data with each other.

Fig. 3 is a timing chart showing the in-vehicle stereo camera apparatus 100.

In the timing chart of fig. 3, flows of approximately 2 systems are represented as 301 and 302. The flow of 301 indicates the processing time in the image processing unit 104 of fig. 1, and the flow of 302 indicates the processing time in the arithmetic processing unit 105 of fig. 1. First, right image input 303 is performed. This corresponds to the processing until the camera 102 (right camera) in fig. 2 captures an image, and then the image processing 104 stores the right image in the image buffer memory 206 after the image processing 205.

The left image input 304 is next performed. This corresponds to the processing until the camera 101 (left camera) in fig. 2 captures an image, and the image processing unit 104 stores the left image in the image buffer memory 206 after the image processing 205. The parallax processing 207 is performed next. This corresponds to the processing until the image processing unit 104 reads out 2 left and right images from the image buffer memory 206 in fig. 2, calculates the parallax by performing the matching between the 2 images, and stores the calculated parallax information in the storage unit 106. At this time, the image and the parallax information are already aligned in the storage section 106. Next, the arithmetic processing unit 105 performs various object recognition processing 209, performs vehicle control processing 211, and outputs and conveys the result to the CAN.

Fig. 4A to 4C are diagrams for explaining the flow of processing of the flag identifying function.

The various object recognition processes 209 include a marker recognition process 209 a. The flag identifying process 209a is composed of a circle detecting process 406 and an identifying process 407. Fig. 4A is a part of an image stored in the image buffer memory 206 through the image processing 205. Fig. 4B is a result of image processing performed on the image of fig. 4A for use in the marker recognition processing 209a, and is an image having luminance in a portion where a change in shade is large in the vicinity. Fig. 4C is an example of a basic processing flow of the identification flag.

In the marker recognition processing 209a, first, the circle detection processing 406 is performed using the image of fig. 4B. In the circle detection processing 406, the center of the circle is found by the center calculation. The circle detection process 406 is divided into a center estimation step 408 and a radius estimation step 409.

Initially, the center is estimated in step 408. A line segment 404 is drawn from each edge in the normal direction, and a center 400 is estimated as a point where a certain number or more of points overlap at the intersection of the line segments (fig. 4A). Note that the number of edges may be omitted from the center 400 to a predetermined radius. In view of the fact that the marker is usually 30cm or more in diameter or the fact that the identification processing 407 cannot process the marker even when a marker located very far is detected, the calculation load can be reduced by omitting the region by this calculation.

Further, since the processing capability of hardware such as a processor that performs the flag identification processing 209a is improved, the calculation omission region can be reduced to identify a flag located at a very far position and improve the security. In this example, the description has been given taking the detection of a circular mark as an example, but in the graph detection processing described later, marks such as a rectangle, an octagon, and a triangle may be detected.

Fig. 5 is a flowchart showing a process of detecting the restriction release flag in the embodiment of the present invention.

The search for the restriction cancellation flag (restriction end flag) is performed at the timing of the flag recognition processing 209a among the various object recognition processing 209. In the flag identifying process 209a, first, by performing the pattern detection 502, a flag candidate group called a main flag, such as a speed flag or an overtaking prohibition, is extracted from the image buffer memory 501 in which the image of the target frame is stored.

Next, for the extracted plurality of marker candidates, each pattern is cut from the image and identified 503. In recognition, the recognition dictionary 210 is used to combine a weak recognizer such as a binomial discriminant tree, a strong recognizer such as a nearest neighbor algorithm or a discriminant function, and the like, and to check the type of the mark.

Here, the arithmetic processing unit 105 (processor) functions as a main flag identifying unit that identifies a main flag.

Next, when a flag that is likely to appear in a co-occurrence relationship with the restriction cancellation flag is detected among the recognized flags, an individual process suitable for detection and determination of the restriction cancellation flag is performed as described below. The unique processing for the restriction release flag includes a diagonal line search 504, diagonal line determination 505, and recognition processing 506 for the restriction release flag.

The diagonal line search 504 is a process of detecting a diagonal line portion located in the center of the restriction release flag based on an edge image obtained by extracting an edge component from a frame image to be recognized. Here, the arithmetic processing unit 105 (processor) functions as a search unit for searching for diagonal line candidates from an image. The detection accuracy of the restriction release flag can be improved by searching for a characteristic oblique line as the restriction release flag. The arithmetic processing unit 105 (search unit) searches for diagonal line candidates, for example, when the main flag is recognized. This makes it possible to detect the slope of the limitation lifting flag that co-exists with the main flag at a proper timing. The specific contents of the processing are described in fig. 6.

The diagonal line determination 505 is a process for discriminating between a diagonal line considered as a mark and a diagonal line considered as a wire, a pillar, or the like from the detected diagonal line candidates. Here, the arithmetic processing unit 105 (processor) functions as a selection unit that selects a restriction cancellation flag indicating cancellation of restriction corresponding to the main flag from among the detected diagonal candidates, and this point will be described later with reference to fig. 7.

Further, the recognition processing 506 is processing for recognizing the restriction release flag from the image of the diagonal line candidate of the selected restriction release flag. The arithmetic processing unit 105 (processor) functions as a restriction cancellation flag recognition unit that performs the recognition processing 506.

Fig. 6A is a diagram showing an outline of processing of the diagonal line search 504 (diagonal line detection) shown in fig. 5.

For an example image 601 of the restriction release flag as a target, a scanning line 602 in the horizontal direction is determined, and image scanning is performed in a direction 603 determined to be one direction such as from left to right. The scanned image is an edge image. In europe, japan, or the like, the restriction release flag is a design characterized by the presence of a diagonal line. The left edge 604 and the right edge 605 of the oblique line are distinguished by observing the direction and the strength of the edges, and the edge pair is further determined by using the distance between the left edge and the right edge.

Here, the arithmetic processing unit 105 (search unit) scans the image in the horizontal direction, searches for a pair of the left edge and the right edge, and detects 2 or more pairs arranged in series as diagonal line candidates. By searching for a pair of a left edge and a right edge of at least 2 pixels or more, diagonal line candidates of the restriction release flag can be narrowed down. Pairs of left and right edges as diagonal candidates are continuously arranged while being adjacent without a gap.

The distance (length in the lateral direction) determined in the edge centering can be determined to be within a fixed range according to the size of the main mark that is a trigger for searching for the limitation canceling mark, or can be converted using the distance to the mark that is the target mark in the case of the stereo camera.

Specifically, the storage unit 106 stores the size of the main flag and the range of the length in the lateral direction of the diagonal line of the restriction cancellation flag in association with each other. The arithmetic processing unit 105 (search unit) searches for a pair of left and right edges whose distance between the left and right edges is within the range of the lateral length of the oblique line of the limitation lifting flag associated with the size of the main flag. This makes it possible to narrow down the diagonal candidates by the length of the diagonal of the restriction cancellation flag corresponding to the size of the main flag.

With respect to the edge pairs to be further extracted, as shown in fig. 6B, diagonal line candidates are locked according to the lengths of the continuous edge pairs. Locking (selection) of candidates for oblique lines will be described with reference to fig. 7. The output information of the diagonal line search (diagonal line detection) includes the position, length, intensity, contrast with the peripheral portion, color component, line thickness, and the like of the edge pair.

The diagonal line determination (upper limit and lower limit determination) in fig. 7 is a process of determining a diagonal line component which is considered to be a design in a sign, and a diagonal line component which is not related to the sign, such as a wire or a pillar. The basic thinking method is to determine the length, thickness, contrast with the periphery, color tone, and the like of an edge pair.

In fig. 7, a length-based thinking approach is described. The length has an upper limit and a lower limit, and edge pairs having a length exceeding the upper limit are excluded as long-diagonal lines such as utility poles, and edge pairs having a length below the lower limit are excluded as short-diagonal lines such as patterns.

Specifically, the storage unit 106 stores the size of the main flag and the range of the length in the vertical direction of the diagonal line of the restriction release flag in association with each other. The arithmetic processing unit 105 (selection unit) selects a diagonal line candidate whose vertical length of the detected diagonal line candidate is within the range of the vertical length of the diagonal line of the restriction cancellation flag associated with the size of the main flag. This can prevent erroneous detection of the slope of the restriction cancellation flag.

The problem is how to set the upper and lower limits. This is set based on the size of the main flag that becomes a trigger for the search of the restriction cancellation flag. In general, the size of the main flag and the size range allowed by the restriction cancellation flag are defined according to the traveling region and country, and the upper limit and the lower limit of the size allowed by the restriction cancellation flag can be estimated from the size of the main flag using this information. The information on the travel area can be obtained in cooperation with an external position information system as shown in fig. 8.

The storage unit 106 may further store information indicating a relative position of the restriction release flag with respect to the position of the main flag. In this case, the arithmetic processing unit 105 (processor) searches for a diagonal line candidate from an area of the image corresponding to the relative position of the restriction cancellation flag with respect to the position of the recognized main flag (for example, in japan, above the main flag). This restricts the region of the diagonal line candidate of the search restriction release flag. As a result, the slant line candidates of the restriction cancellation flag can be efficiently searched.

Fig. 8 is a diagram for explaining a configuration (structure) of a trigger for obtaining a search for the restriction release flag in cooperation with GPS or map information.

Image processing 805 is performed using the left camera 801 and the right camera 802 as starting points, and a region around the traveling road is observed by parallax processing 807 to detect a three-dimensional object such as a side road of a forest or a forest. Further, the latitude and longitude information is obtained from the GPS, and since the stereo camera has data of the national border therein, the current driving area is determined by the country determination process. Further, information on which country the vehicle is traveling in, which heading is, when the traveling time zone is, and the like is obtained from the travel log 809.

When the position information sensor located outside further includes high-precision map information and section information of speed limit of the road, the appearance position of the mark and the switching position of the speed limit can be known, and the limit release mark can be searched in more detail.

In cooperation with an external position information system, although the system investment cost is high, it is possible to perform a search matching with search parameters (edge pair thickness, gradient, contrast) for which a restriction release flag is designed to be slightly different in northern europe, eastern europe, southern europe, and the like, and to further control the exposure 811.

By further cooperating with detailed map information, the ratio of processing time allocated to the search of edge pairs is changed at the position of occurrence of a mark or at the switching point of the speed section of a road, and the like, so that the search can be performed using the co-occurrence state of the restriction release mark.

Specifically, the storage unit 106 stores information indicating the relative position of the restriction release flag with respect to the position of the main flag for each travel area. The arithmetic processing unit 105 (search unit) searches for a diagonal line candidate from an area of the image corresponding to the relative position of the restriction release flag with respect to the position of the recognized main flag for each travel area. Thus, the region of the search limit release flag that is a diagonal line candidate is limited according to the travel area. As a result, the slant line candidates of the restriction cancellation flag can be efficiently searched.

For example, in europe, the main flag and the restriction release flag do not coexist, and the installation location of the main flag is different from that of the restriction release flag. When the length of the section between the main flag and the restriction cancellation flag can be acquired, the arithmetic processing unit 105 (search unit) may search for a diagonal line candidate from an area of the image corresponding to a position (front) apart from the main flag by the length of the section.

As described above, according to the present embodiment, the accuracy of detecting the restriction cancellation flag can be improved.

The present invention is not limited to the above embodiment, and various modifications are also included. For example, the above-described embodiments are detailed for the purpose of easily and easily explaining the present invention, and are not necessarily limited to all configurations described.

In the above embodiment, the explanation has been made using the stereo camera, but the number of cameras is arbitrary.

Further, a part or all of the respective configurations, functions, and the like described above may be implemented in hardware by being designed with an integrated circuit or the like, for example. The respective configurations, functions, and the like described above may be realized by software by interpreting and executing programs for realizing the respective functions by a processor. Information such as programs, tables, and files for realizing the respective functions can be stored in a memory, a hard disk, a recording device such as an ssd (solid State drive), or a recording medium such as an IC card, an SD card, and a DVD.

The embodiments of the present invention may have the following configurations.

(1) A camera device is provided with: a circle information acquiring unit (circle detecting unit) for acquiring information on a circle from the image; a recognition unit that recognizes a first mark on the circle obtained by the circle information acquisition unit; a search unit that searches for an oblique object around the circular object from the image; and a determination unit that determines a second marker for the tilted object based on the information on the tilted object obtained by the search unit and the information on the first marker obtained by the recognition unit.

(2) In (1), the search section searches for a pair of left and right edges in a lateral direction of the image, and the determination section performs the determination of the second flag for the tilted object based on an upper limit value and a lower limit value according to the first flag for the rounded object in a case where the pair of left and right edges is formed with a tilt continuous in a vertical direction.

(3) In the camera device described in (1) or (2), the search processing of the limitation lifting flag is performed not only by the camera image but also in cooperation with external GPS information, map information, and the like, thereby setting a trigger for searching for the limitation lifting flag.

Description of the symbols

100 … vehicle stereo camera device

101. 102 … video camera

103 … image input interface

104 … image processing unit

105 … arithmetic processing unit

106 … storage part

107 … CAN interface

108 … control processing unit

109 … bus

203. 204 … image data

205 … image processing

206 … image buffer memory

207 … disparity processing

209 … various object recognition processes

209a … flag identification processing

210 … recognition dictionary

211 … vehicle control process

303 … Right image input

304 … left image input

400 … center

404 … line segment

406 … circle detection processing

407 … identification process

408 … center estimation step

Step of estimating 409 … radius

501 … image buffer memory

502 … Pattern detection

503 … identifying

504 … diagonal search

505 … diagonal determination

506 … recognition processing

601 … example of image of restriction release flag

602 … scanline

603 … a direction

604 … left edge

605 … right edge

801 … left video camera

802 … right camera

805 … image processing

807 … parallax processing

809 … travel log

811 … controls exposure.