JP4528320B2 - Object detection device - Google Patents

Description

  The present invention relates to an optical object detection device that detects an object outside a traveling vehicle.

An apparatus for detecting a vehicle or other object ahead or behind using a laser radar has been proposed. For example, in Japanese Patent Laid-Open No. 06-150196 (Patent Document 1), in a device that detects a moving object ahead by a laser radar, stores information on the detected moving object in a storage device, and performs control such as tracking traveling. When the moving object stored in the storage device is not detected in the current detection process, the information on the moving object is held in the storage device as a detection error for some reason until a non-detection occurs for a predetermined number of times. A method is described in which information relating to a moving object is deleted from a storage device when the moving object is not detected a predetermined number of times.
Japanese Unexamined Patent Publication No. 06-150196

  However, according to such a method, it is possible to continue to recognize an external object more continuously if the number of times (the number of interpolations) that an undetected object is held without being deleted from the storage device is increased. Even when the object moves outside the detection area, an error occurs as if there is an object in the detection area by the interpolation process. Conversely, if the number of interpolations is reduced, there is a problem that the recognition of the object becomes intermittent due to a detection error of the apparatus.

  In order to solve such a problem, the present invention is an object detection device mounted on a vehicle, and can determine an imaging device capable of measuring a distance to an object and a road region in an image input from the imaging device. A road area determination unit that detects an object in an area that is in front of the road area and that has not been determined as a road area, and a block that is obtained by dividing the detection area in front of the vehicle into a plurality of blocks in advance. An object recognizing unit for recognizing an object based on object detection of a set number of detection times, and the preset number of detections is a block at the center of the detection area for a block at the end of the detection area. The configuration is set to be smaller.

  According to the present invention, the frequency of false recognition due to false detection is reduced and objects that have entered the boundary of the detection area can be recognized quickly compared to the case where the object is recognized by a certain number of detections regardless of the detection area. Can do. When detecting an object in front of the detection area, the object cannot suddenly appear in the center of the area, and conversely, at the end of the detection area, a moving object enters the detection area from outside the detection area. When viewed, an object may suddenly appear in the detection area. In view of such a realistic situation, in order to prevent erroneous recognition at the center of the detection area, a large number of detections until recognition is set. Further, at the end of the detection area, the object may suddenly appear due to the movement of the moving object or the behavior of the own vehicle, so the number of detections until the object recognition is set to be small.

  Another object detection device related to the present invention is an object detection device mounted on a vehicle, an object recognition unit for recognizing an object outside the vehicle, an object storage unit for storing information on the object, Information related to an object stored in the object storage unit but not included in the current recognition by the object recognition unit when updating information stored in the object storage unit with information on an object provided by the object recognition unit An interpolation control unit that interpolates the number of times according to the position of the object in the detection area of the object detection device, and the interpolation control unit includes a peripheral unit for an object located in the center of the detection area. The interpolation is executed a greater number of times than the object located in the position.

  According to the another object detection device, in the running state of the vehicle, in the central portion of the detection area where an object such as another vehicle outside the vehicle (typically in front of or behind the vehicle) is normally stable. Since the number of interpolations is higher than the peripheral parts that frequently cause moving objects to enter and exit, it prevents objects from missing at the center of the detection area and processes erroneously if there is an object that does not exist in the periphery of the detection area Can be reduced.

  Next, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is an overall block diagram of an object detection apparatus according to an embodiment of the present invention. FIG. 2 is a diagram for explaining the principle of distance measurement by the triangulation method used in this embodiment. First, a distance measuring method using a pair of imaging devices will be described with reference to FIG.

  The line sensor 21 and the lens 23 constituting one of the pair of imaging devices are arranged at a predetermined interval, that is, a base line length B, spaced from the line sensor 22 and the lens 24 constituting the other imaging device in the horizontal direction or the vertical direction. Has been. Line sensors 21 and 22 are typically one-dimensional CCDs and may be an array of linearly arranged photosensors. Considering use at night, it is better to use an imaging device using infrared rays. In this case, an infrared transmissive filter is placed in front of the lenses 23 and 24 so that the object 20 is irradiated using an infrared light source so that the line sensors 21 and 22 detect infrared rays reflected from the object 20. It is good.

  The line sensors 21 and 22 are disposed at the focal lengths f of the lenses 23 and 24, respectively. An image of an object at a distance a from the plane on which the lenses 23 and 24 are located is formed at a position shifted by X1 from the optical axis of the lens 23 in the line sensor 21, and shifted by X2 from the optical axis of the lens 24 in the line sensor 22. If it is formed at a certain position, the distance a from the surfaces of the lenses 23 and 24 to the object 20 is obtained by a = B · f / (X1 + X2) according to the principle of the triangulation method.

  In this embodiment, since the image is digitized, the distance (X1 + X2) is calculated digitally. While shifting one or both of the images obtained by the line sensors 21 and 22, the sum of the absolute values of the differences between the digital values indicating the luminance of the corresponding pixels of both images is obtained, and this is used as the correlation value. The shift amount of the image when the correlation value becomes the minimum value indicates a positional deviation between both images, that is, (X1 + X2). Conceptually, as shown in FIG. 2, the distance that the two images must be moved in order to overlap the two images obtained from the line sensors 21 and 22 is (X1 + X2).

  Here, for the sake of simplicity, the image pickup apparatus has been described as being one-dimensional line sensors 21 and 22, but as described below, in one embodiment of the present invention, a two-dimensional CCD or a two-dimensional photosensor array is used. Used as an imaging device. In this case, the two-dimensional images obtained from the two imaging devices are shifted in the horizontal direction to perform the same correlation calculation as described above for a plurality of rows, and the shift amount when the correlation value is minimized is obtained. This shift amount corresponds to (X1 + X2).

Next, the overall configuration of an embodiment of the present invention will be described with reference to FIG. The first imaging device 3 corresponds to one imaging device including the lens 23 and the line sensor 21 in FIG. 2, and the second imaging device 3 ′ corresponds to the other imaging including the lens 24 and the line sensor 22 in FIG. Corresponds to the device. In this embodiment, as shown in FIG. 3B, the imaging area is divided into a plurality of windows (small areas) W ₁₁ , W ₁₂ ,... And the distance is measured for each window. A whole two-dimensional image is required. For this reason, the imaging means 3, 3 ′ is composed of a two-dimensional CCD array or a two-dimensional photosensor array.

FIG. 3A shows an example of an image obtained by imaging another vehicle traveling in front of the host vehicle by the imaging means 3 or 3 ′, and FIG. 3B shows the image of FIG. Conceptually divided into multiple windows. FIG. 3B shows rows in the vertical direction and columns in the horizontal direction and is divided into windows of 10 rows × 15 columns for the sake of simplicity. Each window is numbered. For example, W ₁₂ indicates a window in one row and two columns.

The image of the object imaged by the imaging means 3, 3 ′ is converted into digital data by analog / digital converters (A / D converters) 4, 4 ′ and stored in the image memories 5, 5 ′. By the window cutout unit 13, an image portion corresponding to the window W ₁₁ is sent to the correlation calculation section 6 cut out respectively from the image memory 5 and 5 '. When the correlation calculation unit 6 shifts the extracted two images by a predetermined unit and performs the above-described correlation calculation to obtain the shift amount when the correlation value is minimized, the shift amount is (X1 + X2). The correlation calculation unit 6 sends the value (X1 + X2) thus obtained to the distance calculation unit 7.

The distance calculation unit 7 obtains the distance a ₁₁ to the object in the window W ₁₁ using the above-described formula a = B · f / (X1 + X2). The distance a ₁₁ obtained in this way is stored in the distance storage unit 8. A similar calculation process is sequentially executed for each window, and the distances a ₁₁ , a ₁₂ ,... Are stored in the distance storage unit 8.

  This calculation of the distance can be executed only for a window necessary for use by the road area determination unit 34 and the object detection unit 35 described below. Hereinafter, the distance to the object calculated for a certain window is referred to as the measurement distance of that window.

  Since the resolution of the image data used in the above correlation calculation is determined by the element pitch of the image sensor array, when using a light receiving element with a relatively large pitch, such as a photosensor array, the image data is calculated by interpolation between the pitches. It is preferable to perform a correlation calculation on the image data whose density has been increased in this way.

  Further, in order to correct a change in characteristics of the image sensor array due to temperature, a temperature sensor can be arranged near the image sensor array, and the distance calculation can be corrected based on temperature information obtained from the temperature sensor.

  The object recognition unit 14 in FIG. 1 recognizes an object based on the distance of each window stored in the distance storage unit 8 and the image data provided from the image memory 5 ′. FIG. 4 is a block diagram illustrating a configuration of the object recognition unit 14. The object recognition unit 14 in this embodiment uses a method of determining a road area from an image and determining an object that is not a road area as an object.

  Next, with reference to FIG. 1 and FIG. 4, the determination of the road area in the image will be described. As described above, FIG. 3B is divided into windows of 10 rows × 15 columns for convenience of explanation, but in reality, the image area is divided very finely. In order to determine the road area more precisely, each window can be composed of one pixel. Alternatively, a plurality of pixels may be combined to form one window. Each window may be the same size as the window used to measure the distance described above, or a different size.

  When the image obtained from the imaging unit 3 ′ and converted into digital data is stored in the image memory 5 ′, the window cutout unit 13 in FIG. 1 includes a plurality of images including the image area immediately before the vehicle from the image memory 5 ′. Cut out the window. The luminance extraction unit 31 acquires a plurality of luminance values from the cut window.

  The reason why the brightness value of the window including the image area immediately before the vehicle is acquired is that the image area immediately before the host vehicle is very likely to be a road, and the plurality of brightness values are acquired on the road surface. This is because the luminance value of the original road can be acquired even if there is a sign area such as a character / white line. Which window of the input image is acquired as a plurality of windows including the image area immediately before the host vehicle is determined in advance according to the size of the vehicle and the position of the imaging device in the vehicle.

  Next, in order to extract the original luminance value of the road, the luminance value of the window including the sign on the road surface is removed from the acquired plurality of luminance values. For example, if the window in the bottom row of the image contains several signage windows on the road surface, the brightness value of the signage on the road surface is generally very different from that of the road, so the brightness value of the window in this row is very small. Variation occurs. Therefore, it is possible to average the luminance values of the windows in this row and remove the luminance values having a value that is a predetermined value or more away from the average value.

  Alternatively, the color of the sign on the road surface is mainly white or yellow, which is very different from the color of the road, so that the luminance value in a range corresponding to white or yellow can be removed. Furthermore, based on the reference luminance value extracted from the image input last time, it can be estimated whether the luminance value acquired from the image input this time is the original luminance value of the road.

  After removing the luminance value of the window including the sign on the road surface, the luminance extracting unit 31 extracts the reference luminance value based on the remaining luminance value and stores it in the luminance storage unit 32. One or more of the remaining luminance values can be selected and stored as a reference luminance value. Alternatively, a value obtained by averaging a plurality of luminance values can be stored as one reference luminance value. The luminance value can be represented as digital data having, for example, 256 gradations (between true black “0” and true white “255”).

  Next, the window cutout unit 13 (FIG. 1) cuts out another window from the image, and the luminance extraction unit 31 extracts the luminance value of the window. The luminance comparison unit 33 compares the extracted luminance value with the reference luminance value stored in the luminance storage unit 32.

  When each window is composed of a plurality of pixels, the sum of the luminance values of the pixels can be averaged and the average value can be extracted as the luminance value of the window. Further, the process of extracting and comparing the luminance values can be executed in parallel with the process of calculating the distance.

  The road area determination unit 34 determines the road area based on the comparison result received from the luminance comparison unit 33. If the comparison result is within a predetermined range, the window is determined to be a road area. This is because the road area has similar brightness and is different from the vehicle traveling ahead. The luminance value of the window determined to be a road area is stored in the luminance storage unit 32 as a new luminance value.

With reference to FIG. 3B, an example of road area determination based on the luminance value will be described. Windows W _A7 and W _A9 (windows filled with diagonal lines) including the image area immediately before the vehicle are cut out by the window cutout unit 13, and the luminance extraction unit 31 extracts the luminance values L1 and L2 of the respective windows, The luminance value is stored in the luminance memory 32. Next, the window W _A6 adjacent to the window W _A7 is cut out, and the luminance extraction unit 31 extracts the luminance value of the window W _A6 . The luminance comparison unit 33 compares the extracted luminance value with the reference luminance value L1. If the comparison result is within a predetermined range (for example, a range of ± 3 with respect to the reference luminance value can be set as the predetermined range), the road region determination unit 34 determines that the window _{WA 6} is a road region, The brightness value of W _A6 is stored in the brightness storage unit 32 as a new reference brightness value L3.

Next, the window W _A5 adjacent to the window W _A6 is cut out, and the luminance value of the window W _A5 is extracted by the luminance extraction unit 31. The luminance comparison unit 33 compares the extracted luminance value with the reference luminance value L3. If the comparison result is within a predetermined range, the road area determination unit 34 determines that the window W _A5 is a road area, and stores the luminance value of the window W _{A5 in} the luminance storage unit 32 as a new reference luminance value L4. As described above, the windows are sequentially cut out from the image, and the road area is determined by comparing the luminance value for each window.

The window cut out by the window cutout unit 13 is preferably in the vicinity of a window having a reference luminance value. Specifically, if the reference luminance value is the luminance value of the window W _A6, preferably to compare the luminance value by cutting a window belonging to the window or adjacent rows belonging to the same row as the window W _A6. This is because if the difference in measurement distance between the two windows to be compared is large, the luminance value may be substantially different even on the same road. According to this embodiment, the road area can be accurately detected even when the luminance of the road in the image changes according to the distance from the host vehicle.

  As in the above embodiment, the brightness value determined as the road area is not set as a new brightness value, but is first extracted from the window including the image area immediately before the vehicle (in the above example, L1 and L2 ) As a constant reference luminance value, and the road area can be determined by comparing the luminance value of each window of the image.

  Further, in the above embodiment, the luminance value is extracted based on one image obtained from one imaging means 3 ′, but it is obtained by two or more imaging means necessary for the distance measurement described above. You may extract using two or more images. For example, it is possible to extract the reference luminance value L2 from the image obtained by the imaging unit 3 and extract the reference luminance value L1 from the image obtained by the imaging unit 3 '.

The process of comparing the luminance values to determine the road area preferably performs some parallel processing. For example, the luminance values of the windows W _{A1 to} W _A6 and W _{91 to} W ₉₇ are compared with the reference luminance value L1, and then the luminance values of the windows W _{81 to} W ₈₇ become, for example, new reference luminance values. The window can be processed in units of lines, such as comparing the brightness values of the window W ₉₃ at once. Further, in order to process at high speed, the left half window of the image is processed using the reference luminance value L1 as a base point, the right half window of the image is processed using the reference luminance value L2 as a base point, and both are processed in parallel. preferable.

  Note that an area surrounded by an image area determined as a road area can be automatically determined as a road area. Thus, for example, even if a region surrounded by a region determined to be a road region has a sign region having a luminance different from that of the road, the sign region can be determined as a road region. The size of the area surrounded by the road area can be determined as a road area depending on how large an object is detected.

  In this way, since the road surface itself is detected based on the luminance value, the road area can be determined even if the host vehicle is leaning by pitching or rolling or running on a slope or bank. It can be determined that there is no vehicle or object.

  Here, the sign area on the road can be accurately extracted using the measured distance of the window. The road area determination unit 34 acquires the measured distance of the window in which the comparison result is determined not to be within the predetermined range from the distance storage unit 8, and determines whether this distance is a distance to the road. If the distance is to the road, this window can be determined as a sign area on the road.

  The distance to the road of the window can be estimated from the measured distance of another window determined as the road area (that is, the measured distance to the road). For example, it can be estimated that the distance to the road is the same for all windows included in the row to which the other window belongs. Furthermore, the distance to the road can be estimated for each row of the window from the measured distance of the window determined as a road. Therefore, the road area determination unit 34 can determine whether the image area of the window is a sign area on the road by comparing the distance actually measured for the window with the estimated distance to the road.

For example, as shown in FIG. 3B, the window W ₉₅ includes characters on the road surface. Road area judgment unit 34 receives the comparison result of the window W _95, the comparison result is not within a predetermined range, acquires the measured distance of the window W ₉₅ from the distance memory unit 8. Further, for example, the measured distance of another window W ₉₃ belonging to the same row as the window W ₉₅ and determined as a road area is acquired from the distance storage unit 8. As a result of comparing the two distances, since the distances are substantially the same, the image area of the window W ₉₅ is determined as a sign area on the road surface. By repeating such determination, a sign “60” on the road as shown in FIG. 3B can be recognized.

  As mentioned above, it is possible to extract and recognize the sign area on the road using the measured distance, so it is possible to control the vehicle to alert the driver about excessive speed or lane change, for example it can.

  The determination of the road area described so far may be executed for the entire area of the image input from the imaging means, or may be executed for only a part of the area. For example, it is possible to execute only the image region newly input as an image with the traveling of the host vehicle with respect to the image input last time. Furthermore, the road area can be determined using a preset road model of the car navigation system. In this way, by limiting the image area to be determined, the road area can be determined more efficiently.

  Since the road area is determined, the windows in the image are classified into road areas and non-road areas. The road area determination unit 34 can output a road area including a window determined as a road area in the form of an image as necessary. (C) of FIG. 3 is an example of this output image, and the detected road area is filled and displayed.

  The object detection unit 35 detects an object on the road based on the road region determined by the road region determination unit 34. Since the road area is determined, an object can be detected by extracting a window that is in front of the road area and has not been determined to be a road area.

For example, as shown in (c) of FIG. 3, since the road area is determined, the road area is traced forward, and the windows W ₅₇ , W ₅₈ , and W ₅₉ that are not determined as the road area are extracted. As shown in FIG. 3B, these windows include other vehicles traveling in front. The object detection unit 35 acquires the measurement distances of these windows from the distance storage unit 8. The distance from the host vehicle to the other vehicle can be detected from the acquired measurement distance. Furthermore, it can be determined that the other vehicle is at the center of the road from the positions of the windows W ₅₇ , W ₅₈ and W ₅₉ of the object area with respect to the windows W _{66 to} W _6A determined as the road area.

  As described above, the object detection unit 35 can detect the inter-vehicle distance from another vehicle traveling ahead based on the detected distance to the object, and thus can warn the driver of the inter-vehicle distance. Further, when there is an object that obstructs driving of the vehicle in front of the road, an alarm can be sounded to alert the driver.

  Returning to FIG. 1 again, the object recognizing unit 14 can recognize an object according to the number of detections set in advance for each detection area segment as shown in FIG. FIG. 5A shows a detection area which is a target range of object detection by the object detection apparatus in one embodiment of the present invention. The detection range can be set as a fixed range, for example, a distance range of 60 meters and an angle range of 30 degrees. However, it is preferable to set the detection range dynamically according to the speed of the vehicle. In this case, the distance range is increased as the speed is increased, and the angle range is decreased.

  FIG. 5B shows an example of dividing a fixed detection area. In this example, the detection area is divided into blocks S1 to S12. When the detection area is changed dynamically, the blocks S1 to S12 change in proportion to the change of the detection area. When the host vehicle speed increases and the angle range becomes smaller than about 20 degrees, the lateral division with respect to the angle range becomes too dense, so the blocks S5 and S12 on both sides are omitted.

  The number of detections in blocks S1, S2 and S4 is 2, the number of detections in blocks S3, S5, S6, S8 and S12 is 3, the number of detections in blocks S7, S9 and S11 is 4, and the number of detections in block S10 is 5 is set. The number of detections in the blocks S1, S2, S3, S4, S5, S6, S8, and S12 which are the end portions of the area is set to be smaller than that in the central blocks S7, S9, and S11. This is based on the empirical rule that the moving object (vehicle) detected in these peripheral blocks changes greatly as the vehicle travels, whereas the moving object detected in the central block changes little. Is based. In other words, the number of detections is reduced in the surrounding area where the change in and out of the vehicle is severe, and the change in the vehicle is immediately reflected in the vehicle detection state. In the central part where the change in and out of the vehicle is small, the detection number is increased and the vehicle is stable. The detection state is obtained.

  In one aspect of the present invention, instead of using the object recognition method in which the number of detections is changed as described above, when the information of the detected object is stored in the object storage unit 16, the interpolation control unit 15 An interpolation method is used.

  In this embodiment, the number of interpolations in the blocks S1, S2 and S4 is 2, the number of interpolations in the blocks S3, S5, S6, S8 and S12 is 3, the number of interpolations in the blocks S7, S9 and S11 is 4, and the block S10 The number of interpolations in is set to 5. The number of interpolations in the blocks S1, S2, S3, S4, S5, S6, S8, and S12 that are the periphery of the area is set to be smaller than that in the central blocks S7, S9, and S11. This is based on an empirical rule that the change in the vehicle detected in the central block is small while the change in the vehicle detected in the peripheral block is small as the vehicle travels. In other words, the number of interpolations is reduced in the peripheral part where the change in and out of the vehicle is severe, and the change of the vehicle is reflected in the vehicle detection state quickly, and the number of interpolations is increased in the central part where the change in and out of the vehicle is small and the vehicle is stable. The detection state is obtained.

  The object detection calculation is executed, for example, at a cycle of 100 milliseconds, and the content of the object storage unit 16 is updated via the interpolation control unit 15 every 100 milliseconds. FIG. 6 is a block diagram of the interpolation control unit 15. Now, when the detection device obtains an image as shown in FIG. 3A from the imaging device, the object recognition unit 14 uses the method described in relation to FIG. 4 to display the windows W37, W38, W39, W47, The presence of the object is recognized in W48, W49, W57, W58, and W59, and it is recognized that the distances to the objects in these windows are the same. Based on this recognition, the object recognition unit 14 determines that the objects present in these windows are integral objects, and the detection block determination unit 41 of the interpolation control unit together with the window information and distance information as the first object. Send to. When the second and third objects are detected from the image, the same information is also sent to the detection block determination unit 41.

  For example, the format shown in FIG. 7 is used. The object ID field is simply for entering an object ID for distinguishing a plurality of objects, and may be a code such as 001 for the first object, 010 for the second object, and 011 for the third object. The distance field of the format contains a value indicating the distance to the object in meters. In the window ID field, identification codes of a plurality of windows in which the corresponding object is detected are entered.

  The detection block determination unit 41 applies the detection area to the window information and distance information sent from the object recognition unit 14, and determines, for example, that the first object exists in the block S8 of the detection area.

  The object storage unit 16 (FIG. 1) is a table composed of random access memories, and the presence / absence of an object for each block in the detection area, the relative speed information between the vehicle and the object, and fixed interpolation for the block. The number of times and the remaining number of times indicating how many times interpolation is performed are stored. Typically, the format of this table is as shown in FIG. In FIG. 8, the first object 1 (code 001) exists in the block S8, the distance from the own vehicle to the object 1 is 15 meters, and the relative speed between the own vehicle and the object 1 is +3 km / h. The number of interpolations is 3 and the remaining number of interpolations for object 1 is 2, indicating that the first interpolation was performed as a result of no object being detected in this block in the detection cycle that caused table writing. ing.

  The data update control unit 42 in FIG. 6 receives information indicating the presence / absence of an object for each block from the detection block determination unit 41. In response to this, the data update control unit 42 reads the information of the corresponding block from the table (FIG. 8) of the object storage unit 16. Depending on the information from the detection block determination unit 41 and the information read from the table, the processing of the data update control unit 42 for each block is as follows.

  1) When information indicating that no object is present is received from the detection block determination unit 41, and no object information is stored in the corresponding block of the table. In this case, the data update control unit 42 does not do anything to the next detection block. Move on to the process.

  2) When the information indicating that no object exists is received from the detection block determination unit 41 and the object information is stored in the corresponding block of the table. For example, the information indicating that no object exists is received from the detection block determination unit 41 for the block S8. When the record of the block S8 having the contents shown in FIG. 8 is read from the table, the data update control unit puts a value obtained by subtracting 1 from the value of the remaining number field of the record, and changes the data in the other fields. Without overwriting the table with the record of block S8. As a result, the remaining number field of the block S8 becomes 1.

  When the value of the “remaining number of times” field of the record of the block S8 is 0 at the beginning of this processing, the data update control unit 42 sets the data other than the “interpolation number” field of the record of the block S8 to null or all 0s or Reset to all 1 (collectively referred to as the null state), and overwrite the record after reset in the table. As a result, in the record of block S8, the value of the “number of interpolations” field is 3, and the other fields are null.

  3) When the information indicating the presence of the object is received from the detection block determination unit 41 and there is no object information in the record of the corresponding block of the table, the data update control unit 42 receives the object ID and distance data received from the detection block determination unit 41 In the “object” field and “distance” field of the record of the corresponding block, the value of the “interpolation count” field is entered in the “remaining count” field, and thus the table is overwritten with the updated record. As can be seen from the above description, the “remaining number of times” field apparently functions as a subtraction counter.

  4) When information indicating the presence of an object is received from the detection block determination unit 41, and there is object information in the record of the corresponding block of the table, the data update control unit 42 receives the distance information (current distance) received from the detection block determination unit The distance information (previous distance) read from the record of the corresponding block in the table is sent to the relative speed calculation unit 43. In response to this, the relative speed calculation unit 43 calculates the relative speed between the object and the own vehicle by a calculation formula of (current distance−previous distance) / detection time interval. The detection time interval is the time difference between the previous measurement and the current measurement, and is 100 milliseconds in this embodiment. The relative speed calculation unit 43 returns a value obtained by converting the value thus obtained to km / h to the data update control unit 42.

  The data update control unit 42 replaces the “object” field and the “distance” field of the record of the corresponding block received from the table based on the data received from the detection block determination unit 41, and received from the relative speed calculation unit 43. Enter the value in the Relative Speed field. The update record obtained in this way overwrites the record of the corresponding block in the table.

  As described above, object information as shown in the table of FIG. 8 is stored in the object storage unit 16 of FIG. The vehicle control unit 18 performs the front vehicle tracking traveling control of the own vehicle based on information stored in the object storage unit 16 and information from the vehicle speed detection device 19 and the yaw rate detection device 2. Controls such as outputting an approach alarm and performing forced deceleration control.

  Correlation calculation unit 6, distance calculation unit 7, distance storage unit 8, window cutout unit 13, object recognition unit 14, interpolation control unit 15, object storage unit 16, relative speed calculation unit 17 and vehicle control unit 18 shown in FIG. Provides a central processing unit (CPU), a read-only memory for storing control programs and control data, an arithmetic work area for the CPU, and can be composed of a random access memory (RAM) for temporarily storing various data. The distance storage unit 8 and the object storage unit 16 can be realized by using different storage areas of one RAM. Also, a temporary storage area for data required for various calculations can be realized by using a part of the same RAM.

  Further, the object detection device of the present invention can be LAN-connected to an engine electronic control unit (ECU), a brake control ECU and other ECUs, and the output from the object detection device can be used for overall control of the vehicle.

  According to the present invention, the frequency of false recognition due to false detection is reduced and objects that have entered the boundary of the detection area can be recognized quickly compared to the case where the object is recognized by a certain number of detections regardless of the detection area. Can do.

  According to another object detection device related to the present invention, it is possible to prevent the object from being lost in the central portion of the detection area and to reduce erroneous processing when there is an object that does not exist in the periphery of the detection area. .

  Although the present invention has been described above with reference to specific embodiments, the present invention is not limited to such embodiments.

1 is a block diagram showing the overall configuration of an embodiment of the present invention. The figure for demonstrating the triangulation method of distance. The conceptual diagram for demonstrating the aspect which detects an object based on the image obtained from an imaging device. The block diagram which shows the detail of the object recognition part 14 of FIG. The figure which shows a detection area and its division. The block diagram which shows the detail of the interpolation control part 15 of FIG. The figure which shows the format of the data passed to the interpolation control part 15 from the object recognition part 14. FIG. The figure which shows an example of the table memorize | stored in the object memory | storage part.

Explanation of symbols

3, 3 ′ imaging device 14 object recognition unit 15 interpolation control unit 16 object storage unit

Claims (1)

An object detection device mounted on a vehicle,
An imaging device capable of measuring the distance to an object ;
A road area determination unit that determines a road area in an image input from the imaging device;
An object detection unit that detects an object in a region that is in front of the road region in the image input from the imaging device and that has not been determined to be a road region, for each predetermined period;
Depending on the distance and position to the object detected by the object detection unit, the object is applied to a block obtained by dividing the detection area in front of the vehicle into a plurality of blocks , and the object is detected based on the number of detections set in advance for each block. An object recognition unit for recognizing,
The object detection device, wherein the preset number of detections is set smaller for a block at an end of the detection area than for a block at the center of the detection area.

Images