JP6534261B2 - Object recognition device - Google Patents
Object recognition device Download PDFInfo
- Publication number
- JP6534261B2 JP6534261B2 JP2015003413A JP2015003413A JP6534261B2 JP 6534261 B2 JP6534261 B2 JP 6534261B2 JP 2015003413 A JP2015003413 A JP 2015003413A JP 2015003413 A JP2015003413 A JP 2015003413A JP 6534261 B2 JP6534261 B2 JP 6534261B2
- Authority
- JP
- Japan
- Prior art keywords
- edge
- image
- lowest point
- attention area
- determination unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Description
本発明は、カメラの撮像画像に基づいて対象物を認識する対象物認識装置に関する。 The present invention relates to an object recognition apparatus that recognizes an object based on a captured image of a camera.
従来より、車両に搭載されたカメラにより撮像された車両前方の道路の画像から、抽出目的の対象物を認識し、前記車両から前記対象物までの距離を算出する対象物認識装置が知られている(例えば、特許文献1参照)。 BACKGROUND ART Conventionally, an object recognition apparatus is known that recognizes an object for extraction purpose from an image of a road ahead of the vehicle taken by a camera mounted on the vehicle and calculates a distance from the vehicle to the object (See, for example, Patent Document 1).
特許文献1に記載された対象物認識装置では、前記カメラによる撮像画像から周囲部に対する輝度の変化量が所定値以上であるエッジ点を抽出したエッジ画像を生成し、前記エッジ画像から対象物の画像部分を含む注目領域を抽出する。 In the object recognition device described in Patent Document 1, an edge image is generated by extracting an edge point whose change amount of luminance with respect to the surrounding part is equal to or more than a predetermined value from an image captured by the camera. An attention area including an image portion is extracted.
また、カメラと対象物間の距離を算出する方法として、撮像画像中の消失点と対象物の画像部分の最下点(接地部)との位置関係を用いる手法が用いられている。 Further, as a method of calculating the distance between the camera and the object, a method of using the positional relationship between the vanishing point in the captured image and the lowest point (grounding portion) of the image portion of the object is used.
しかしながら、通常、対象物認識装置では、前記注目領域の最下点を対象物の画像部分の接地部として用いているので、前記注目領域の最下点が対象物の画像部分の接地部と合致しない場合には、車両から対象物までの距離を正確に算出することができないという不都合がある。 However, since the lowest point of the attention area is usually used as the ground part of the image portion of the object in the object recognition apparatus, the lowest point of the attention area matches the ground part of the image part of the object If not, there is a disadvantage that the distance from the vehicle to the object can not be calculated accurately.
本発明はかかる背景に鑑みてなされたものであり、カメラの撮像画像に基づいて対象物を認識する際に、対象物の画像部分の接地部を正確に特定することができる対象物認識装置を提供することを目的とする。 The present invention has been made in view of such background, and when recognizing an object based on a captured image of a camera, an object recognition apparatus capable of accurately identifying the ground portion of the image portion of the object. Intended to be provided.
本発明は、上記目的を達成するためになされたものであり、本発明の対象物認識装置は、
カメラの撮像画像から、周囲部に対する輝度の変化量が所定値以上であるエッジ点を抽出したエッジ画像を生成するエッジ画像生成部と、
前記エッジ画像から、対象物の画像部分を含む注目領域を抽出する注目領域抽出部と、
前記注目領域の下部領域を垂直方向に所定幅を有する複数の参照領域によって分割し、水平方向のエッジ強度が最大である前記参照領域の垂直方向位置を前記対象物の画像部分の最下点と判定する最下点判定部とを
備え、
前記最下点判定部は、前記対象物の種類に応じて前記注目領域における前記参照領域の水平方向の範囲を設定することを特徴とする。
The present invention has been made to achieve the above object, and the object recognition apparatus of the present invention is
An edge image generation unit configured to generate an edge image in which an edge point whose amount of change in luminance with respect to the peripheral portion is a predetermined value or more is extracted from a captured image of a camera;
An attention area extraction unit for extracting an attention area including an image portion of an object from the edge image;
The lower region of the region of interest is divided by a plurality of reference regions having a predetermined width in the vertical direction, and the vertical position of the reference region where the edge strength in the horizontal direction is maximum is the lowest point of the image portion of the object the lowest point determination unit determines <br/> Bei example,
The lowest point determination unit may set a horizontal range of the reference area in the attention area in accordance with the type of the object .
本発明の対象物認識装置では、まず、エッジ画像生成部により、カメラの撮像画像から、周囲部に対する輝度の変化量が所定値以上であるエッジ点を抽出したエッジ画像を生成する。次に、注目領域抽出部により、前記エッジ画像から、対象物の画像部分を含む注目領域を抽出する。次に、最下点判定部により、前記注目領域の下部領域を垂直方向に所定幅を有する複数の参照領域によって分割し、水平方向のエッジ強度が最大である参照領域の垂直方向位置を前記対象物の画像部分の最下点と判定する。 In the object recognition device of the present invention, first, the edge image generation unit generates an edge image by extracting an edge point whose change amount of luminance with respect to the surrounding portion is a predetermined value or more from an image captured by a camera. Next, an attention area extraction unit extracts an attention area including the image portion of the object from the edge image. Next, the lowermost point determination unit divides the lower area of the target area into a plurality of reference areas having a predetermined width in the vertical direction, and the vertical position of the reference area having the largest edge strength in the horizontal direction is the target. Determined as the lowest point of the image portion of the object.
本発明の対象物認識装置によれば、後述するように、対象物の画像部分の最下点付近では、他の部分と比較して水平方向のエッジ強度が強くなる傾向があることから、前記対象物の画像部分の最下点を特定することができ、前記対象部の画像部分の接地部を正確に特定することができる。 According to the object recognition apparatus of the present invention, as described later, the edge strength in the horizontal direction tends to be stronger in the vicinity of the lowermost point of the image part of the object compared to other parts. The lowest point of the image portion of the object can be identified, and the grounding portion of the image portion of the object portion can be accurately identified.
また、本発明の対象物認識装置において、前記最下点判定部は、前記対象物の種類に応じて前記注目領域における前記参照領域の水平方向の範囲を設定することが好ましく、前記最下点判定部が判定対象とする参照領域を狭くして処理速度を短縮することができる。 In the object recognition apparatus according to the present invention, preferably, the lowest point determination unit sets a range in the horizontal direction of the reference area in the attention area according to the type of the object, and the lowest point The processing speed can be shortened by narrowing the reference area to be judged by the judgment unit.
また、本発明の対象物認識装置において、前記最下点判定部は、水平方向のエッジ強度が最大であり、且つ、前記対象物の種類に応じた所定の方向のエッジ成分が抽出された前記参照領域の垂直方向位置を、前記対象物の画像部分の最下点と判定することが好ましく、前記対象物の画像部分の接地部をより正確に特定することができる。 Further, in the object recognition device of the present invention, the lowest point determination unit has the maximum edge strength in the horizontal direction, and the edge component in a predetermined direction corresponding to the type of the object is extracted. Preferably, the vertical position of the reference area is determined to be the lowest point of the image portion of the object, and the grounding portion of the image portion of the object can be identified more accurately.
本発明の対象物認識装置の実施形態について、図1〜図5を参照して説明する。 An embodiment of an object recognition apparatus according to the present invention will be described with reference to FIGS. 1 to 5.
図1を参照して、対象物認識装置10は、カメラ2(カラーカメラ)を備えた車両1(本発明の車両に相当する)に搭載されている。 Referring to FIG. 1, an object recognition device 10 is mounted on a vehicle 1 (corresponding to a vehicle of the present invention) provided with a camera 2 (color camera).
対象物認識装置10は、図示しないCPU、メモリ、各種インターフェース回路等により構成された電子ユニットであり、メモリに保持された対象物認識用のプログラムをCPUで実行することにより、撮像画像取得部11、エッジ画像生成部12、注目領域抽出部13、最下点判定部14、及び距離算出部15として機能する。 The object recognition device 10 is an electronic unit configured by a CPU, a memory, various interface circuits, etc. (not shown), and the CPU executes a program for object recognition held in the memory by the CPU to obtain the captured image acquisition unit 11 It functions as the edge image generation unit 12, the attention area extraction unit 13, the lowest point determination unit 14, and the distance calculation unit 15.
以下、図2に示したフローチャートに従って、対象物認識装置10により、道路上に存在する対象物(人、自転車等)を認識する処理について説明する。対象物認識装置10は、所定の制御周期毎に図2に示したフローチャートによる処理を実行して、車両1が走行している道路上に存在する対象物を認識し、該対象物までの距離を測定する。 Hereinafter, processing for recognizing an object (person, bicycle, etc.) present on a road by the object recognition device 10 will be described according to the flowchart shown in FIG. The object recognition device 10 executes the processing according to the flowchart shown in FIG. 2 every predetermined control cycle to recognize the object existing on the road on which the vehicle 1 is traveling, and the distance to the object Measure
図2のSTEP1は撮像画像取得部11による処理である。撮像画像取得部11は、車両に搭載されたカメラ2から出力される車両1の周囲(前方)の映像信号を入力して、この映像信号のカラー成分(R値,G値,B値)から、各画素のデータとしてR値,G値,B値を有するカラーの撮像画像21を取得する。そして、この車両1の前方の撮像画像21のデータを画像メモリ20に保持する。 STEP 1 in FIG. 2 is processing by the captured image acquisition unit 11. The captured image acquisition unit 11 receives an image signal of the surroundings (front) of the vehicle 1 output from the camera 2 mounted on the vehicle, and generates color components (R value, G value, B value) of the image signal. A color captured image 21 having R value, G value, and B value as data of each pixel is acquired. Then, the data of the captured image 21 in front of the vehicle 1 is stored in the image memory 20.
続くSTEP2はエッジ画像生成部12による処理である。エッジ画像生成部12は、撮像画像21の前記カラー成分から輝度に変換する処理を行って、グレースケール画像(多値画像)を生成する。そして、エッジ画像生成部12は、グレースケール画像からエッジ点(周囲部の画素(画像部分)との輝度差(輝度の変化量)が所定値以上である画素)を抽出して、エッジ画像22(図1参照)を生成する。 The subsequent STEP 2 is processing by the edge image generation unit 12. The edge image generation unit 12 performs processing of converting the color components of the captured image 21 into luminance to generate a gray scale image (multi-value image). Then, the edge image generation unit 12 extracts, from the gray scale image, pixels having a luminance difference (amount of change in luminance) greater than or equal to a predetermined value with respect to edge points (pixels in the peripheral portion (image portion)). Generate (see FIG. 1).
なお、カメラ2がモノクロカメラであるときには、各画素の輝度からグレースケールの撮像画像が得られるので、上述したカラーの撮像画像からグレースケール画像を生成する処理は不要である。 When the camera 2 is a monochrome camera, a gray scale captured image can be obtained from the luminance of each pixel, so the process of generating a gray scale image from the color captured image described above is unnecessary.
続くSTEP3〜STEP5は、注目領域抽出部13による処理である。注目領域抽出部13は、STEP3で対象物の画像部分32を含む注目領域31を抽出する。注目領域31の抽出は、例えば、探索領域を全探査してROI(Resion of Interest)から注目領域31を探索する方法や、所定数以上のエッジが含まれる領域を注目領域31として設定する方法により行うことができる。 The subsequent STEPs 3 to 5 are processing by the region of interest extraction unit 13. The attention area extraction unit 13 extracts the attention area 31 including the image portion 32 of the object in STEP 3. Extraction of the region of interest 31 is performed, for example, by a method of searching the region of interest 31 from the ROI (Resion of Interest) by completely searching the search region, or setting a region including a predetermined number or more of edges as the region of interest 31 It can be carried out.
次に、注目領域抽出部13は、STEP4で、STEP3で抽出された注目領域31に対して、HOG(Histogram of Oriented Gradients)特徴量を算出し、得られたHOG特徴量に基づいて対象物のラベルを付す。 Next, the attention area extraction unit 13 calculates an HOG (Histogram of Oriented Gradients) feature quantity for the attention area 31 extracted in STEP 3 in STEP 4 and, based on the obtained HOG feature quantity, Label it.
次に、注目領域抽出部13は、STEP5で、STEP4で付加されたラベルが識別対象(人や自転車等)である場合にはSTEP6へ進み、識別対象以外(背景)である場合には処理を終了する。 Next, the attention area extraction unit 13 proceeds to STEP 6 when the label added in STEP 4 is an identification target (such as a person or a bicycle) in STEP 5 and performs processing when the label is not the identification target (background). finish.
続くSTEP6〜STEP8は、注目領域31内に人、自転車の画像部分が含まれる場合に行われる最下点判定部14による処理である。最下点判定部14は、STEP6で、図3に示したように、対象物の画像部分32を含む注目領域31の下部領域(例えば、注目領域31の下1/3程度の領域)を、垂直方向(y方向)に所定幅を有する複数の参照領域33a,33b,33c,33d,33e,33fによって分割する。すなわち、注目領域31の下部領域を複数の参照領域33a〜33fによって水平方向(x方向)に分割する。 The following steps 6 to 8 are processing by the lowest point determination unit 14 performed when the image area of a person or a bicycle is included in the attention area 31. The lowest point determination unit 14 determines, in STEP 6 as shown in FIG. 3, the lower area of the attention area 31 including the image portion 32 of the object (for example, an area around the lower 1/3 of the attention area 31) It divides | segments by several reference area | regions 33a, 33b, 33c, 33d, 33e, and 33f which have predetermined width in the orthogonal | vertical direction (y direction). That is, the lower area of the attention area 31 is divided in the horizontal direction (x direction) by the plurality of reference areas 33a to 33f.
続くSTEP7で、最下点判定部14は、各参照領域33a〜33fの水平方向のエッジ成分のエッジ強度34a,34b,34c,34d,34e,34fを算出する。ここで、水平方向のエッジ成分の強度としては、水平方向のエッジ成分を構成するエッジ点の個数、当該エッジ点の輝度変化値(輝度微分値)の加算値、これらの組み合わせ等が用いられる。 In the following STEP 7, the lowest point determination unit 14 calculates edge intensities 34a, 34b, 34c, 34d, 34e, 34f of edge components in the horizontal direction of the reference areas 33a to 33f. Here, as the strength of the edge component in the horizontal direction, the number of edge points constituting the edge component in the horizontal direction, the added value of the luminance change value (luminance differential value) of the edge point, a combination thereof, or the like is used.
ここで、例えば、人体において、足の甲や足の裏は、足首や脛、膝、太腿等と比較して、水平方向に広がっていることから、前記下部領域を分割した複数の参照領域33a〜33fのうち足の甲や足の裏の画像部分を含む参照領域は、水平方向のエッジ強度が最大となる。 Here, for example, in the human body, a plurality of reference regions obtained by dividing the lower region, since the back of the foot and the sole of the foot are spread in the horizontal direction as compared to the ankles, shins, knees, thighs, etc. The reference area including the image portion of the back of the foot and the sole of the foot among 33a to 33f has the maximum edge strength in the horizontal direction.
そこで、続くSTEP8で、最下点判定部14は、水平方向のエッジ強度が最大である参照領域33cの垂直方向位置(参照領域33cの上端)を、対象物の画像部分32の最下点35と判定する。 Therefore, in the subsequent STEP 8, the lowest point determination unit 14 determines the vertical position (upper end of the reference area 33 c) of the reference area 33 c where the edge strength in the horizontal direction is maximum as the lowest point 35 of the image portion 32 of the object. It is determined that
STEP9は、距離算出部15による処理である。距離算出部15は、図4(a)に示したように、まず、エッジ画像22内で、走行車線を区画するレーンマーク(白線)の画像部分37a,37bの交点から無限遠点である道路消失点38の座標を求め、道路消失点38と対象物の画像部分32との最下点35との距離Δyを求める。次に、距離算出部15は、図4(b)に示したように、以下の式(1)により、無限遠点に対する角度θを算出し、以下の式(2)により、カメラ2が搭載されている車両1と対象物39との間の距離Dを算出する。Hはカメラ2の高さ、focalはカメラ2の焦点距離である。 STEP 9 is processing performed by the distance calculation unit 15. As shown in FIG. 4A, first, the distance calculation unit 15 in the edge image 22 is a road at an infinite distance point from the intersection of the image portions 37a and 37b of the lane mark (white line) partitioning the traveling lane. The coordinates of the vanishing point 38 are determined, and the distance Δy between the road vanishing point 38 and the lowermost point 35 of the image portion 32 of the object is determined. Next, as shown in FIG. 4B, the distance calculation unit 15 calculates the angle θ with respect to the infinity point by the following equation (1), and the camera 2 is mounted by the following equation (2) The distance D between the vehicle 1 and the object 39 being calculated is calculated. H is the height of the camera 2 and focal is the focal length of the camera 2.
tanθ=Δy/focal …(1)
D=H/tanθ …(2)
tan θ = Δy / focal (1)
D = H / tan θ (2)
本実施形態の対象物認識装置10によれば、対象物の画像部分32の最下点35を特定することができ、対象部の画像部分32の接地部を正確に特定することができる。これにより、車両1から対象物39までの距離を正確に算出することができる。 According to the object recognition device 10 of the present embodiment, the lowest point 35 of the image portion 32 of the object can be identified, and the ground contact portion of the image portion 32 of the object portion can be accurately identified. Thereby, the distance from the vehicle 1 to the object 39 can be accurately calculated.
本実施形態では、最下点判定部14は、対象物の画像部分32を含む注目領域31の下部領域全体を、複数の参照領域33a〜33fによって分割しているが、対象物の種類に応じて変更してもよい。例えば、対象物が正面を向いた人である場合には、図3に示したように、注目領域31の下部領域の中央部31aのみを複数の参照領域33a〜33fによって分割してもよい。また、対象物が横を向いた人又は横を向いた自転車である場合には、図5に示したように、エッジ画像22において、対象物の画像部分32を含む注目領域31の下部領域のうち、注目領域31の左端部31b及び右端部31cのみを複数の参照領域33a〜33fによって分割してもよい。 In the present embodiment, the lowest point determination unit 14 divides the entire lower area of the attention area 31 including the image portion 32 of the object by the plurality of reference areas 33a to 33f, but according to the type of the object May be changed. For example, when the object is a person facing the front, as shown in FIG. 3, only the central portion 31a of the lower area of the attention area 31 may be divided by a plurality of reference areas 33a to 33f. In addition, when the object is a person facing sideways or a bicycle facing sideways, as shown in FIG. 5, in the edge image 22, in the lower region of the attention region 31 including the image portion 32 of the object. Among them, only the left end 31b and the right end 31c of the attention area 31 may be divided by the plurality of reference areas 33a to 33f.
このようにすることにより、最下点判定部14は、判定対象とする参照領域33a〜33fの処理面積を狭くして処理速度を短縮することができる。 By doing this, the lowest point determination unit 14 can reduce the processing area of the reference regions 33a to 33f to be determined, and shorten the processing speed.
また、最下点判定部14は、水平方向のエッジ成分のエッジ強度が最大である参照領域33cの垂直方向位置のみから、対象物の画像部分32の最下点と判定するとしているが、さらに、水平方向のエッジ成分のエッジ強度が最大であり且つ対象物の種類に応じた所定方向のエッジ成分が抽出された参照領域の垂直方向位置を、対象物の画像部分32の最下点と判定してもよい。例えば、対象物が横を向いた人又は横を向いた自転車である場合には、水平方向のエッジ成分のエッジ強度が最大であり、且つ、右下斜め方向のエッジ成分又は左下斜め方向のエッジ成分が抽出された参照領域の垂直方向位置を、対象物の画像部分32の最下点と判定する。このようにすることにより、対象物の画像部分32の接地部をより正確に特定することができる。 Also, although the lowest point determination unit 14 determines that the lowest point of the image portion 32 of the object is only from the vertical direction position of the reference area 33c where the edge strength of the edge component in the horizontal direction is maximum, The vertical position of the reference area in which the edge strength of the horizontal edge component is maximum and the edge component in a predetermined direction according to the type of the object is extracted is determined as the lowest point of the image portion 32 of the object You may For example, when the object is a person facing sideways or a sideways bicycle, the edge strength of the horizontal edge component is maximum, and the lower right diagonal edge component or the lower left diagonal edge The vertical position of the reference area from which the component is extracted is determined to be the lowest point of the image portion 32 of the object. By doing this, the ground portion of the image portion 32 of the object can be identified more accurately.
また、本実施形態では、カメラ2は車両1に搭載されているとしているが、道路脇や道路上方に設置されたカメラであってもよい。 Further, in the present embodiment, the camera 2 is mounted on the vehicle 1 but may be a camera installed beside the road or above the road.
1…車両(自車両)、2…カメラ、10…対象物認識装置、12…エッジ画像生成部、13…注目領域抽出部、14…最下点判定部、21…撮像画像、22…エッジ画像、31…注目領域、32…対象物の画像部分、33a,33b,33c,33d,33e,33f…参照領域、34a,34b,34c,34d,34e,34f…エッジ強度、35…最下点。 DESCRIPTION OF SYMBOLS 1 ... Vehicle (self-vehicle), 2 ... Camera, 10 ... Target object recognition apparatus, 12 ... Edge image generation part, 13 ... Attention area extraction part, 14 ... Lowest point determination part, 21 ... Captured image, 22 ... Edge image 31, 31: Attention area, 32: Image part of object, 33a, 33b, 33c, 33d, 33e, 33f: Reference area, 34a, 34b, 34c, 34d, 34e, 34f: Edge strength, 35: Lowest point.
Claims (3)
前記エッジ画像から、対象物の画像部分を含む注目領域を抽出する注目領域抽出部と、
前記注目領域の下部領域を垂直方向に所定幅を有する複数の参照領域によって分割し、水平方向のエッジ強度が最大である前記参照領域の垂直方向位置を前記対象物の画像部分の最下点と判定する最下点判定部とを
備え、
前記最下点判定部は、前記対象物の種類に応じて前記注目領域における前記参照領域の水平方向の範囲を設定することを特徴とする対象物認識装置。 An edge image generation unit configured to generate an edge image in which an edge point whose amount of change in luminance with respect to the peripheral portion is a predetermined value or more is extracted from a captured image of a camera;
An attention area extraction unit for extracting an attention area including an image portion of an object from the edge image;
The lower region of the region of interest is divided by a plurality of reference regions having a predetermined width in the vertical direction, and the vertical position of the reference region where the edge strength in the horizontal direction is maximum is the lowest point of the image portion of the object the lowest point determination unit determines <br/> Bei example,
The lowest point determination unit sets a horizontal range of the reference area in the attention area according to the type of the target.
前記最下点判定部は、水平方向のエッジ強度が最大であり、且つ、前記対象物の種類に応じた所定の方向のエッジ成分が抽出された前記参照領域の垂直方向位置を、前記対象物の画像部分の最下点と判定することを特徴とする対象物認識装置。 In the object recognition device according to claim 1,
The lowest point determination unit determines the vertical direction position of the reference area in which the edge strength in the horizontal direction is maximum and the edge component in the predetermined direction corresponding to the type of the object is extracted. An object recognition apparatus characterized in that it is determined to be the lowest point of the image portion of .
前記エッジ画像から、対象物の画像部分を含む注目領域を抽出する注目領域抽出部と、
前記注目領域の下部領域を垂直方向に所定幅を有する複数の参照領域によって分割し、水平方向のエッジ強度が最大である前記参照領域の垂直方向位置を前記対象物の画像部分の最下点と判定する最下点判定部とを備え、
前記最下点判定部は、水平方向のエッジ強度が最大であり、且つ、前記対象物の種類に応じた所定の方向のエッジ成分が抽出された前記参照領域の垂直方向位置を、前記対象物の画像部分の最下点と判定することを特徴とする対象物認識装置。 An edge image generation unit configured to generate an edge image in which an edge point whose amount of change in luminance with respect to the peripheral portion is a predetermined value or more is extracted from a captured image of a camera;
An attention area extraction unit for extracting an attention area including an image portion of an object from the edge image;
The lower region of the region of interest is divided by a plurality of reference regions having a predetermined width in the vertical direction, and the vertical position of the reference region where the edge strength in the horizontal direction is maximum is the lowest point of the image portion of the object And a lowest point determination unit for determining
The lowest point determination unit determines the vertical direction position of the reference area in which the edge strength in the horizontal direction is maximum and the edge component in the predetermined direction corresponding to the type of the object is extracted. An object recognition apparatus characterized in that it is determined to be the lowest point of the image portion of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2015003413A JP6534261B2 (en) | 2014-04-25 | 2015-01-09 | Object recognition device |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2014091618 | 2014-04-25 | ||
| JP2014091618 | 2014-04-25 | ||
| JP2015003413A JP6534261B2 (en) | 2014-04-25 | 2015-01-09 | Object recognition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2015215868A JP2015215868A (en) | 2015-12-03 |
| JP6534261B2 true JP6534261B2 (en) | 2019-06-26 |
Family
ID=54752662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2015003413A Active JP6534261B2 (en) | 2014-04-25 | 2015-01-09 | Object recognition device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP6534261B2 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7143263B2 (en) * | 2019-09-05 | 2022-09-28 | Kddi株式会社 | Object identification method, device and program for determining object identification position using encoded parameters |
| CN116685904A (en) * | 2020-12-28 | 2023-09-01 | 富士胶片株式会社 | Camera support device, camera device, camera support method and program |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012208887A (en) * | 2011-03-30 | 2012-10-25 | Denso Corp | Object tracing device and object tracing system |
-
2015
- 2015-01-09 JP JP2015003413A patent/JP6534261B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| JP2015215868A (en) | 2015-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8391555B2 (en) | Lane recognition apparatus for vehicle, vehicle thereof, and lane recognition program for vehicle | |
| US9508000B2 (en) | Object recognition apparatus | |
| JP5014237B2 (en) | Lane marker recognition device, vehicle, and lane marker recognition program | |
| US9771080B2 (en) | Road surface gradient detection device | |
| JP5591730B2 (en) | Environment recognition device | |
| US9336595B2 (en) | Calibration device, method for implementing calibration, and camera for movable body and storage medium with calibration function | |
| US20150367781A1 (en) | Lane boundary estimation device and lane boundary estimation method | |
| KR101483742B1 (en) | Lane Detection method for Advanced Vehicle | |
| US20150262365A1 (en) | Image processing device and image processing method | |
| US9489585B2 (en) | Lane mark recognition device | |
| JP2011243161A (en) | Lane boundary detection apparatus and lane boundary detection program | |
| JP2007265038A (en) | Road image analysis device and road image analysis method | |
| US9824449B2 (en) | Object recognition and pedestrian alert apparatus for a vehicle | |
| JP6534261B2 (en) | Object recognition device | |
| JP4797846B2 (en) | Lane marking device and lane detection device | |
| JP6677141B2 (en) | Parking frame recognition device | |
| JP2003317106A (en) | Roadway recognition device | |
| KR101999354B1 (en) | Using Curve Line Curvature Information | |
| JP6668740B2 (en) | Road surface estimation device | |
| JP6354963B2 (en) | Object recognition apparatus, object recognition method, and object recognition program | |
| JP6173962B2 (en) | Lane mark recognition device | |
| TWI498831B (en) | System of adaptive variable shape region of interest determination and its control method | |
| KR20140076043A (en) | Device and method for detecting pedestrian candidate | |
| JP7047362B2 (en) | Image processing equipment, control system, and image processing method | |
| JP6270604B2 (en) | Object recognition device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20171129 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20181127 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20181204 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20190204 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20190521 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20190528 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 6534261 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |