Denso Corporation

Nippondenso Co., Ltd.

Toyota Jidosha Kabushiki Kaisha

Nippon Soken, Inc.

Nagoya Institute of Technology

Toyota School Foundation

Noriaki Shirai

Katsuhiro Morikawa

Katsuhiko Hibino

Takao Nishimura

Takeshi Matsui

Yoshiaki Hoashi

Yoshie Samukawa

Keiji Matsuoka

Hirotake Ishigami

Toyohito Nozawa

Kazuhisa Ishimaru

Takayuki Kimura

Naohide Uchida

Toshikazu Murao

Kentarou Shiota

Hiroshi Ookata

Takamoto Watanabe

Akihiro Watanabe

Masayuki Imanishi

Jun Sato

Toshiyuki Matsubara

Yoshinao Takemae

Yuji Kimura

Satoshi Osanai

Ken Tanabe

Naoki Sugiyama

Masaki Kuwahara

Nobuharu Kawai

Katsuji Kosaka

Fumihiko Sakaue

Hossein Tehrani Niknejad

Seiichi Mita

Qiwei Xie

Qian Long

A parallax calculating apparatus comprises first parallax calculating means for calculating a first parallax on a basis of a reference image for all pixels in the reference image using SGM method, second parallax calculating means for calculating a second parallax on a basis of the reference image for at least a part of pixels among pixels in the reference image using BM method, and final parallax calculating means for calculating a final parallax of each of pixels in the reference image based on the first and second parallaxes. The final parallax calculating means calculates the first parallax as the final parallax for a pixel for which only the first parallax has been calculated and calculates a parallax where a decimal part of the first parallax is replaced with that of the second parallax as the final parallax for a pixel for which the first and second parallaxes have been calculated.

Parallax calculating apparatus

The distance measuring device detects parallax between right and left captured images where a front object is present ahead of the own vehicle, and calculate a parallax distance between the front object and the own vehicle. The radar device detects a radar detected distance therebetween. The distance measuring device calculates a parallax error based on the difference between the parallax calculated distance and the radar detected distance. A correction region is set in the right captured image and divided into correction divided regions. The distance measuring device sets an individual correction parallax for every correction divided regions, based on the parallax error and the identified correction divided regions.

Apparatus for measuring distance

A distance detection device calculates a pixel cost, every reference pixel, based on a difference between reference pixel information in a reference image and comparative pixel information in a comparative image while switching the reference and comparative images. The device calculates a parallax cost, every reference pixel, representing a cost regarding a change-amount of the parallax as a coordinate difference between a reference pixel and a comparative pixel when the reference image is switched. The device calculates a combination of each reference pixel and a comparative pixel having a minimum total cost every reference pixel. The minimum total cost represents a sum of the pixel cost and the parallax cost. The device obtains a relationship of a corresponding point between each reference pixel and its corresponding comparative pixel, and calculates a distance to an object in each captured image based on the relationship of the corresponding point.

Distance detection device

A position measuring apparatus detects, from respective first and second imaging planes of first and second captured images, first and second corresponding points estimated to represent a common three-dimensional position. The apparatus calculates first to fourth projected points. Each of the first and second projected points represents a projected point of the first corresponding point on a corresponding one of the first and second common planes. Each of the third and fourth projected points represents a projected point of the second corresponding point on a corresponding one of the first and second common planes. The apparatus calculates a first beam connecting the first and second projected points, a second beam connecting the third and fourth projected points, and a point having a minimum square distance relative to each of the first and second beams as a restored point representing the three-dimensional position of the first and second corresponding points.

Apparatus for measuring three-dimensional position of target object

A corresponding point searching method searches corresponding points in plural images, acquired by in-vehicle cameras, for each pixel in a reference image by using a predetermined first method, for example, the Viterbi algorithm. The method searches corresponding points in the plural images for each pixel in the reference image by using a predetermined second method, for example, an optical flow method. The method detects whether or not a search accuracy of the corresponding points in each region divided in the reference image obtained by the predetermined first method is not less than a reference value. When not less than the reference value, the method selects the corresponding points obtained by the predetermined first method. When less than the reference value, the searching method selects the corresponding points obtained by the predetermined second method. The searching method provides the corresponding points between the plural images with a high accuracy.

Corresponding point searching method and distance detection device

An object detection apparatus includes a camera and an ECU. The camera is mounted to a vehicle and captures an image. The ECU is configured to obtain a depth distance for each pixel area of the image based on the image; extract at least one potential object based on the depth distance; calculate an amount of change over time in the depth distance of the at least one potential object; and detect an object around the vehicle from among the at least one potential object using the amount of change over time. When a first potential object and a second potential object that are adjacent in the image are extracted, and a second amount of change over time is twice a first amount of change over time, the second potential object is determined to be the same object as the first potential object.

Object detection apparatus and object detection method

An object estimation apparatus estimates a position and a speed of an object in images based on the images taken by an image taking means from different positions. The object estimation apparatus includes a shift information taking means that takes temporal shift information of a position of a corresponding pixel from frames arranged in time series in a reference image, which is a reference between the images, a parallax information taking means that takes parallax information of each corresponding pixel from the images with reference to the reference image, an estimated value taking means that estimates estimated values of the position and the speed of the object in three-dimensional space by using a filter based on the shift information taken by the shift information taking means and the parallax information taken by the parallax information taking means, a determination means that determines whether or not each of the shift information taken by the shift information taking means and the parallax information taken by the parallax information taking means is an abnormal value, and a correction means that corrects the estimated value taken by the estimated value taking means based on a determination result of the determination means. The correction means corrects the estimated value taken by the estimated value taking means by using different methods between a case where the determination means determines that the shift information taken by the shift information taking means is an abnormal value and a case where the determination means determines that the parallax information taken by the parallax information taking means is an abnormal value.

Object estimation apparatus and object estimation method

A recognition object detecting apparatus is provided which includes an imaging unit which generates image data representing a taken image, and a detection unit which detects a recognition object from the image represented by the image data. The imaging unit has a characteristic in which a relation between luminance and output pixel values varies depending on a luminance range. The detection unit binarizes the output pixel values of the image represented by the image data by using a plurality of threshold values to generate a plurality of binary images, and detects the recognition object based on the plurality of binary images.

Recognition object detecting apparatus

There is provided an apparatus for generating a disparity map. According to the apparatus, an image acquisition section acquires a right-camera image and a left-camera image which are picked up from mutually different viewpoints by cameras. A disparity map generation section generates a disparity map that includes disparity expressed in terms of a difference in pixel positions between each of pixels and a corresponding one of pixels in the right-camera image and the left-camera image, respectively, as acquired. A weight determination section determines a weight that serves as a degree of contribution to disparity correction, for each of weight-calculation-target pixels composed of surrounding pixels. The weight-calculation-target pixels include a correction-target pixel or surrounding pixels that are present around the correction-target pixel in the disparity map. A disparity map correction section corrects the disparity of the correction-target pixel, using weighted average based on the determined weight.

Method and apparatus for generating disparity map

In a system for detecting a target object, a similarity determining unit sets a block in a picked-up image, and compares a part of the picked-up image contained in the block with a pattern image data while changes a location of the block in the picked-up image to determine a similarity of each part of the picked-up image contained in a corresponding one of the different-located blocks with respect to the pattern image data. A specifying unit extracts some different-located blocks from all of the different-located blocks. The determined similarity of the part of the picked-up image contained in each of some different-located blocks is equal to or greater than a predetermined threshold similarity. The specifying unit specifies, in the picked-up image, a target area based on a frequency distribution of some different-located blocks therein.

Object detection system with improved object detection accuracy

A device including a radar and a camera for detecting an object located in front of an automobile is mounted on the automobile. The radar detects a distance from the automobile to the front object, and the camera takes an image of the object. When the object such as a preceding vehicle moves out of a region detectable by the radar while remaining in a region covered by the camera, a present distance to the object is calculated based on the distance previously detected by the radar and memorized in a memory and a present object image taken by the camera. More particularly, the present distance is calculated by multiplying the memorized distance by a ratio of an object size in the memorized image to an object size in the present image.

Device for detecting object in front of vehicle

A scanning device periodically changes the direction of the transmission of an electromagnetic wave from an electromagnetic wave generating device. A first driving device operates for repetitively driving the electromagnetic wave generating device a plurality of times per one period of the change of the direction by the scanning device, and thereby for repetitively transmitting a distance measurement electromagnetic wave. A second driving device operates for, before the first driving device drives the electromagnetic wave generating device, driving the electromagnetic wave generating device and thereby transmitting a judgment electromagnetic wave having an energy smaller than that of the distance measurement electromagnetic wave. An obstacle judging device permits the first driving device to drive the electromagnetic wave generating device next in cases where a detected obstacle is absent, and inhibits the first driving device from driving the electromagnetic wave generating device next in cases where a detected obstacle is present.

Distance measurement apparatus

A method and apparatus of measuring a distance to a reflection object is disclosed. A sensitivity time control (STC) process is applied to a received signal from the reflection object to provide an STC-processed signal. The radar apparatus includes a controller. The controller obtains a quantity corresponding to the distance from a transmission time of the transmission signal and a detection time of the STC-processed signal. The quantity is corrected by using a first correction value associated with the intensity of the STC-processed reflection signal to provide a corrected quantity. The corrected quantity is further corrected by using a second correction value associated with the corrected quantity and the intensity of the STC-processed reflection signal to correct the error regardless of the intensity of the STC-processed reflection signal.

Method and apparatus for measuring distance to a detection object

A forward electromagnetic wave is generated in accordance with a succession of pseudo random noise code signals. An echo electromagnetic wave caused by reflection of the forward electromagnetic wave at an object is converted into a received signal. Direct-current and low-frequency components are removed from the received signal to generate a filtering-resultant signal. The filtering-resultant signal is compared with a preset decision reference voltage to generate a binary signal. The binary signal is sampled into received data. Calculation is made as to a correlation between the received data and the pseudo random noise code signal. The distance to the object is computed on the basis of the calculated correlation. The pseudo random noise code signal is repetitively generated to produce a succession of the pseudo random noise code signals during a surplus time covering a stabilization time taken by the received signal to stabilize in direct-current voltage level.

Growing community of inventors

Kariya, Japan

Noriaki Shirai