IS'sN ,‘0917-3?£)_E§_
`CODEN : TOTBEH
`
`
`
`|PR2013-00419 - Ex. 1011
`
`Toyota Motor Corp., Petitioner
`1
`
`IPR2013-00419 - Ex. 1011
`Toyota Motor Corp., Petitioner
`
`1
`
`

`

`We are hereby sending you "TOYOTA Technical Review" Vol. 43,
`No.1.
`With this edition, we are pleased to announce a new line-up of
`editorial staff. We will be doing our best to make this magazine as
`interesting as possible, and count on your support.
`
`1993
`Editorial Staff
`
`To be perfectly honest , until I was invited to join the editorial team
`in February, I had no idea that the old TOYOTA ENGINEERING had
`changed to the TTR. In the former days of the TOYOTA ENGINEER
`- lNG, I had dearly wanted to publish a report on certain development
`work, but was disappointed when I didn't get the opportunity to doso.
`That was my main experience with the journal. The TTR is Toyota's
`only journal publishing technical reports, and is in that sense one of the
`faces of Toyota. Consequently, I will use this opportunity as a mem(cid:173)
`ber of the editorial staff to let more people know about the journal
`and its contents.
`(M. Yamashita)
`
`The history of the automobile goes back over a century, and in(cid:173)
`dustrially it appears to have reached the saturation region of the growth
`curve. Automobile technology is already adequate if we think of mo(cid:173)
`tor vehicles as instruments to get us from A to B. Recent technical
`development has focused on making the trip there more comfortable
`and safe. However, our attention is now turning to the harm the au(cid:173)
`tomobile brings to the environment, seen in such problems as carbon
`dioxide gas control and disposal of scrapped cars. We are now facing
`the task of developing technologies that will remove the contradic(cid:173)
`tions between motoring convenience and conservation of the environ(cid:173)
`ment. When these problems are solved, I believe the automobile will
`move along a new growth curve that may be very dramatic indeed.
`(T. Mori)
`
`From this year I have been given the responsibility of supervising
`the editorial team. Considering the outstanding record of this maga(cid:173)
`zine, I hope I'm up to the task. At any rate, I'll give it my best shot.
`The theme for this issue is "Intelligent Vehicles" . This is the maga(cid:173)
`zine's first attempt at active editing, in contrast to the passive stance
`it has assumed until now. We are anticipating that this issue will ap(cid:173)
`peal to a wider audience, and that TTR will become even more popu(cid:173)
`lar. Happy reading!
`(Y. Masuda)
`
`Masahiro Yamashita
`
`Takeo Mori
`
`Research & Advanced Development
`Planning Div.
`
`Vehicle Research & Advanced
`Engineering Div.
`
`Yoshihiko Masuda
`
`Power Train Engineering Div. IV
`
`Yasunobu lufuku
`
`Research & Development Div. 21
`
`Toshimitsu Hamashima Chassis Component Engineering
`Div.
`
`Kazuhiko Goto
`
`Vehicle Evaluation & Engineering
`Div. I
`
`Kazuhiko Funato
`
`Electronics Engineering Div. I
`
`Shin-ichi Matsumoto
`
`Material Research & Development
`Div. I
`
`Koji Kazuoka
`
`Unit & Pans Engineering
`Development Div.
`
`Takashi Okada
`
`Machines & Tools Engineering Div.
`
`Tadashi Naito
`
`Factory Automation Systems Div.
`
`Hidetoshi Taniguchi
`
`Administration Div.
`
`Secretariat
`
`*Osamu Kondo
`
`Technical Administration Div.
`
`Tomoyuki Sugino
`
`Technical Administration Div.
`
`Norie Nakashima
`
`Technical Administration Div.
`
`Hitomi Fujiwara
`
`TOYOTA TECHNO SERVICE CORP.
`
`'Chief Editor
`
`TOYOTA Technical Review Vol. 43 No.1
`© 1993 TOYOTA MOTOR CORPORATION, Printed in Japan
`Copyrights of all articles published in the TOYOTA Technical Review are the prop(cid:173)
`erty of TOYOT A MOTOR CORPORATION.
`For permission to reproduce articles in quantity or for use in other printed material,
`contact the chairman of the Editorial Committee.
`
`Publisher's
`Office
`
`Publisher
`
`Editor
`
`Printer
`
`Printed
`
`Technical Administration Div .
`TOYOTA MOTOR CORPORA nON
`I Toyota-cho, Toyota, Aichi, 471 Japan
`Tel. (565) 28-2121
`Fax. (565) 23-5788
`
`Hideo Hatlori
`
`Osamu Kondo
`
`CMC Co., Ltd.
`1-1-19 Heiwa, Nakaku, Nagoya, Aichi , 460 Japan
`
`Sep. 1993
`
`Printed on recycled paper
`
`2
`
`

`

`TOYOTA MOTOR CORPORATION
`
`TOYCYfA TECHNICAL REVIEW
`10810--3
`~ fi 8 : 9309
`~ : 43
`~- : 1
`
`"\'110J-[.": ACA
`
`<lf1l~jv- r>
`
`'9.3.10.22
`
`3
`
`

`

`Conten s
`
`Dspecial Edition for lnte11igent vehicles
`Introduction
`
`. Toward lnteⅡigent vehicles
`By Mitsuo Kawai
`Technical papers
`. Reseach projects on lnte11igent vehicle and participation of TOYOTA
`By Kazumasa Nakamura/Yoshikazu Noguchi Hideki Kusunokv
`Akihiko Nojima
`' overview and perspective on Techn010gical Developments for lnteⅡigent vehicles
`By lsao Yoshikawa
`. TOYOTA Automated Highway vehicle system
`By Akihide Tachibana/Keiji Aoki
`Technical Articles
`
`. cruise contr01
`
`By Yukinori Harada
`. Electro Multivision -voice Navigation system
`By Toru RO
`.1nteⅡigent parking system
`By Toshiyasu Katsuno Akira ohata Masahiro Mio Yoichilwata
`. Driving Enviroment Recognition for Active safety
`"' By Toshihiko sU2UkvYoshiyuki Nakayama/YukinoriYamada Masato Kume
`.1nteⅡigent sensor.
`By Yoshinori ohno
`.1ntegrated circuits for supporting Automotive lnte川gent EleC訂onic systems
`By AkiTa KawahashvMasumi KawakamvKazumasa Kimura
`. Human・Machine lnterface
`By Fumihiro Ushijima/Masaaki NishiwakvBunji Astumi
`. Development of Automatic Driving system on Rough Road
`By Junsuke Komura/Takao lshibashvKenichi ohnishvTakashi shigematsu
`Yoshiyuki Hashimoto/Yukihisa okada
`
`DTechnical papers
`. Finite Element Analysis of Magnetic Field for Electromagnetic parts in Automobile
`By Naofumi Hotta Yoichi Mizuno Toru ohara
`. Development of Assembly une verification
`By Fumioki shibata Kiyoyukilmayoshi Yoshinori ri satoshiogata
`
`DTechnical Articles
`
`. Development of Body parts Made of Galvanized Aluminum sheets
`By Masamichi Aono/Kouichi Kaneko/Asao Mochizuki/Yasusi Kubota/
`Hiroki Nakajima
`. Development of vehicle lntegrated control system
`" By KOZO Fujita/Kiyotaka lse Yoshiakilnoue Kazuya Akita
`. oxidation catalyst in cor011a Dieselfor Export to Germany
`By Yoshitsugu ogura/Kazuya Kibe satoshi Kaneko Yukarilto Norihiko Aono
`. Development of Tooth surface Measuring Machine for Hypoid Gears
`By Hiroshi Kagimoto/Nob0川 Aoyama/Norihiko Kondo
`
`6
`
`14
`
`18
`
`25
`
`32
`
`38
`
`44
`
`52
`
`58
`
`67
`
`73
`
`79
`
`86
`
`93
`
`99
`
`109
`
`115
`
`121
`
`125
`
`144
`
`147
`
`148
`
`4
`
`

`

`Intelligent Vehicle
`
`Driving Environment Recognition for
`Active Safety
`
`Toshihiko Suzuki*
`Yoshiyuki Nakayama*
`Yukinori Yamada*
`Masato Kume**
`
`Peripheral Recognition for Active Safety Peripheral enhancement/advisory systems which provide perceptual
`enhancements and warnings of hazards for drivers are expected to contribute to active safety. This paper
`describes three types of peripheral recognition techniques which have been researched and developed by TOYO(cid:173)
`TA Motor Corp. since 1980's, that is, millimeter-wave radar and laser radar based on active-sensing and CCO
`image processing based on passive-sensing. Both millimeter-wave radar and laser radar feature excellent weather
`resistance and provide range detection for relatively far objects. The CCO image processing system adopts
`template matching method to perform lane-line recognition and approaching vehicle detection by stereo vision
`and optical-flow detection.
`
`Fig. 1 shows four definite types of perceptual enhance(cid:173)
`ment/advisory systems that may be put into practical use.
`The peripheral recognition technologies for such systems
`must involve minimum lowering of the detecting performance
`due to changes in weather and other environmental condi(cid:173)
`tions and less cost burden on the user side. Manufacturers
`have been studying various methods, but they have not been
`established as technologies for recognition of vehicle peripher(cid:173)
`al conditions.
`Toyota Motor Corp. has been studying and developing
`millimeter-wave radar, laser radar and image processing tech(cid:173)
`nologies shown in Table 1 as peripheral recognition technol(cid:173)
`ogies for perceptual enhancement/recognition systems.
`While active-sensing systems detect the electromagnetic
`wave (beam) emitted from the built-in device and reflected
`from targets, passive-sensing systems detect reflected elec(cid:173)
`tromagnetic waves existing in the ordinary state or and the
`electromagnetic wave radiated from targets. Because an
`active-sensing system irradiates the wave itself, the SIN of
`the received signal is high. As compared with a passive-sensing
`system, an active-sensing system is less affected by changes
`in weather conditions such as rain and fog. The existing active(cid:173)
`sensing systems have problems such as insufficient resolution
`for accurate locating of targets and difficulty in mounting
`on vehicles.
`This paper describes the results of our studies on various
`peripheral recognition methods and themes to be studied in
`the future.
`
`1. Introduction
`
`It has been well known that driving operation by a driver
`is performed in three steps: perception/recognition, decision
`making and control/response. Along with complication of
`driving environment due to increasing traffic in recent years,
`the driver's load for perception/recognition and decision mak(cid:173)
`ing has been increasing. One of Japanese highway accident
`statistics shows that collisions with roadside structures and
`rear-end collisions account for over 50070 of total accidents.
`Most of fatal accidents may be avoided by preventing depar(cid:173)
`ture from the traveling lane and rear-end collisions.
`One conceivable method for preventing these is to install
`electronic perceptual enhancement/advisory systems for ac(cid:173)
`tive safety. In other words, it is to make vehicles have intelli(cid:173)
`gence for recognizing the driving environment and informing
`drivers of the surrounding conditions and any possible danger.
`Such a perceptual enhancement/advisory system, however,
`is to provide the driver with only the information required
`for safe driving, and the driver must assume the final respon(cid:173)
`sibility for driving operation.
`Sufficient discussion may be required for obtaining social
`consensus on the system reliability and resultant change in
`the driver's safety consciousness while clarifying the scope
`of responsibility.
`To make perceptual enhancement/advisory systems more
`reliable, infrastructure such as roadside monitoring and ve(cid:173)
`hicle/roadway communication systems should be
`im(cid:173)
`plemented.
`Intelligent vehicle systems can be used more efficiently when
`they are well coordinated with the roadside infrastructure.
`
`*Research & Development Div. ill
`**Research & Advanced Development Planning Di\'.
`
`44
`
`5
`
`

`

`Driving Environment Recognition for Active Safety
`
`Crossi ng-path
`warn ing sy stefJl
`
`I ( Run -off road
`Il warning system J
`
`,
`
`Distance to vehic le
`ahead and relative
`speed
`
`Lane marker Iwh ite
`line ) position and
`road shape
`
`Lane-change
`warning sy stem
`
`Distance to vehicle
`approaching from
`behind (or motor
`cycle at right/ left
`\Urn) and relative
`speed
`
`I
`I ( Coll ision
`Il w arning system J
`
`Distance to approaching
`vehicle, motor cycle or
`predestrian and relative
`speed
`
`Fig, 1 Perceptual Enhancement/Advisory System
`
`2. Millimeter-Wave Radar(11.(2)
`
`This system allows relatively long range detection with less
`influence by environmental conditions such as rain, fog and
`snow.
`The FM-CW type millimeter-wave radar we have been de(cid:173)
`veloping detects the relative speed by sensing the variation
`of the phase according to the moving speed of the target. For
`actual application to the collision warning system, however,
`electromagnetic interference with the radars on other vehi(cid:173)
`cles exists as a big problem.
`To solve this problem, we have developed a system using
`45 ° polarization to prevent interference with opposing vehi(cid:173)
`cles by 90 D difference in polarization.
`
`Receiving antenna Transmitti ng antenna
`
`Directional coupler
`
`Gunn oscillator
`
`Circulator
`
`Fig. 2 Millimeter-wave Radar
`
`Table 1 Recognition Methods for Perceptual
`Enhancement! Advisory System
`
`Active
`methods
`
`Method
`
`Applied system
`
`Millimeter-wave radar
`
`.Collision warnmg system
`.Lane-change warning system
`
`Laser radar
`
`• Collision warning system
`
`Passive
`methods
`
`Image
`processing
`
`Template-
`matching
`
`Stereo
`Ision
`
`• Run-off road warning system
`
`• Collision warning system
`• Lane-change warning system
`
`Optical flow
`detection
`
`• Collision warning system
`• Lane -change warn ing system
`• Crossing-path warning system
`
`Fig. 2 shows the exterior view of the millimeter-wave ra(cid:173)
`dar in V shape for 45 ° polarization. Fig. 3 shows the method
`of experiment and an example of evaluation results of the ef(cid:173)
`fect of suppressing interference from other vehicles by adop(cid:173)
`tion of this system. Fig. 4 shows the case where the radar
`on the vehicle running in parallel is directed to the same tar(cid:173)
`get vehicle.
`The experimental results indicate almost no electromagnetic
`interference with the radars on other vehicles .
`Future themes to be studied are how to improve the signal
`processing method and antenna shape for recognition per(cid:173)
`formance improvement and how to facilitate installation on
`vehicles.
`
`TOYOTA Technical Review Vol. 43 No.1 Sep, 1993
`
`45
`
`6
`
`

`

`Measuring vehicle
`
`Target vehicle
`
`(m)
`20 R = 10m, e = 0°
`
`10~--------------
`
`R = 10m, e = 5°
`Distance signal
`
`O~~~~~~~~~~~--~~--­
`Radar ON/OFF signal from vehicle running in opposite
`direction
`
`ON
`
`OFF
`
`Fig. 3 Electromagnetic Interference (from Vehicle Running
`in Opposite Direction) Evaluation Result
`
`Fig. 5 shows the principle of detection. The pulse method
`is adopted to increase the measurable distance and to improve
`the reliability.
`This system involves possible lowering of the detecting pre(cid:173)
`cision due to variation in the receiving level resulting from
`change in the laser beam reflection factor of the target and
`environmental changes such as rainfall.
`We have, therefore, improved the AGC (automatic gain
`control) and STC (sensitivity time control) circuits to reduce
`the error to within ± 2 m for a detecting distance of 100 m.
`
`GaAs laser (wave
`length: 0.904 I'm)
`
`~#
`ta(get vehicle )l
`
`Distance (R) ;
`t x c/2
`Dis(tRan) ce I L _______ - ' L._(C_i...:S _th_e_v_e_'O_ci_ty_---'
`of light)
`~
`
`I+-------'R-'----+i Measuring vehicle
`
`Fig. 5 Principle of Detection by Laser Radar
`
`Single
`radar
`
`Tripod
`R= 10m, r= 10m
`e = 5·
`
`(m)
`20
`
`R = 10m, r = 10m
`e = 20·
`Distance signal
`10~-------------
`
`O~--------------~----------
`Radar IN/ OFF signal from vehicle running in same
`direction
`
`OFF
`
`3. Laser Radar(31
`
`This system will reduce the size and weight of the active(cid:173)
`sensing range monitoring system in comparison with the case
`of millimeter-wave radar. It is not subject to frequency regu(cid:173)
`lation, signal processing is easy, and narrow range detection
`is possible by concentrating beam irradiation.
`
`46
`
`4. Image Recognition(41
`
`For image recognition, feature extraction from the image
`data for recognition is necessary. The methods for feature
`recognition can roughly be classified into the boundary ex(cid:173)
`traction method and region segmentation method as shown
`in Fig. 6. We have adopted the template matching method
`which is one of the simplest region segmentation methods.
`Fig. 7 shows the basic principle. This method is capable of
`simultaneous processing of feature extraction and initial
`recognition for simplification of the whole processing as it
`searches the region having the highest correlation with the
`template image.
`Table 3 shows three characteristics that can be detected by
`using the template matching method. These are because the
`stereo vision and optical flow can be detected in the same way
`as template matching.
`The template matching method enables a single processor
`to perform multiple types of recognition jobs as its merit. We
`have made a prototype compact compact high-speed proces(cid:173)
`sor board using a special IC for calculating correlation be(cid:173)
`tween images that would otherwise require high operation
`load. (Photo. 1)
`In comparison with other recognition methods, the image
`processing system using a CCD camera as the input device
`has the following features:
`
`7
`
`

`

`Driving Environment Recognition for Active Safety
`
`(1) Capability of lane marker and road sign recognition
`(2) Concurrent high-speed pick-up of various image signals
`in a wide range
`(3) Relatively low cost because of the construction using
`general parts for consumer products
`Basically drivers operate according to visual information.
`Thus the image recognition system has wide applicability
`for use other than perceptual enhancement/advisory systems
`shown in Fig. 1.
`
`4.1 Lane-Line Recognition by Template-Matching
`
`Lane recognition by the lane line provides the most basic
`information for recognition of run-off (lane departure) and
`obstacles in peripheral recognition. One of the important fac(cid:173)
`tors in lane-line recognition is the robustness against changes
`in shade/brightness of the road surface and in lane-line shape
`at curved portions.
`Fig. 8 shows the template image update method we have
`
`S.W.7 ~_~ __ ~~~ __ - -J
`
`_----Feature extraction method--__ _....
`
`Boundary extraction
`method
`
`Region segmentation
`method
`• Template-matching
`method
`
`Extraction of boundary line]
`where the light intensity
`changes by differentiating
`the image
`
`[
`
`Extraction of regions Where]
`the intensity of light or
`color is the same
`
`[
`
`Fig. 6 Feature Extraction Method for Image Recognition
`
`o
`
`or-~------'
`
`I.I=l_N-1 ---'-~I :.ttJ .....
`1 + [±]
`
`M-1L!:J
`
`Template
`
`k-1 L..-______ .....I
`Search window g (i, j)
`
`Correlation coefficient 0 i, j = ~ I f (m,n) - 9 (m+i, n+j) I
`
`M-l N-l
`
`Fig. 7 Principle of Template-matching Method
`
`Table 2 Application of Template-matching Method
`
`Template-matching
`Stereo vision
`Optical flow
`
`Object detection/recognition
`Detection of 2-dimensional depth (distance)
`Detection of motion vector of moving object
`
`Vehicle side
`
`Fig. 8 Template Image Updating Method
`
`developed. Knowledge on continuous variation of the posi(cid:173)
`tion and shape of the lane line on the road surface is used
`as a basic premise.
`The area to be searched in front of the vehicle is divided
`into plural narrow search windows for speedy processing and
`minimization of the influence of change in shape. In each
`search window, the template moves only in the horizontal
`direction to search the position where the correlation is max(cid:173)
`imized. To cope with any change in the lane line shape, search
`windows are searched in the ascending order of the distance
`from the vehicle. The lane line image obtained in the search
`window nearer from the vehicle is used for updating the tem(cid:173)
`plate for use in the next window. To stabilize the lane-line
`position in the updated template image, a predefined image
`is used as the template for the search window nearest to the
`
`Photo. 1 Image Recognition Board
`
`TOYOTA Technical Review Vol. 43 No.1 Sep. 1993
`
`47
`
`8
`
`

`

`vehicle.
`The intensity transformation to cope with the changes in
`shade and light intensity on the road surface is performed only
`in each search window. The basic algorithm uses linear trans(cid:173)
`formation so that the intensity distribution in the histogram
`of pixels in the search window matches that in the template
`image.
`As a result of intensity transformation, the robustness
`against the change in light intensity has been improved greatly.
`In the test for evaluating the effect by manually changing the
`electronic shutter speed, lane line detection was possible in
`the light intensity variation range corresponding to the shut(cid:173)
`ter speed change between 11125 and 114000 sec (32 times).
`Owing to the template image update control, stabilized lane
`line detection was possible up to 50 m ahead at a corner where
`
`Photo. 2 Lane-line Recognition on Shady Road
`
`the curvature was 80 R. Photo. 2 shows an example of the
`test for evaluating the robustness of recognition on a shady
`road. Accurate recognition in rainy weather involving strong
`reflection from the road surface is the next task to be accom(cid:173)
`plished.
`
`4.2 Vehicle Recognition by Stereo Vision
`
`3-dimensional depth image is effective information for the
`collision and lane change warning systems. One depth (dis(cid:173)
`tance) measuring technology using image processing is the
`stereo vision method for obtaining the distance distribution
`in the whole screen from the images picked up by two cameras
`according to the principle of triangulation.
`
`48
`
`Righthand image division
`into small blocks
`
`Disparity, Corresponding
`
`@j~':r.pOint
`, ---+
`:Search
`
`, , , ,
`
`: Lefthand image
`
`Execution for all blocks
`
`I""
`
`Fig. 9 Principle of Distance Measurement
`by Stereo Vision
`
`Compare with millimeter-wave and laser radars, stereo vi(cid:173)
`sion features excellent spatial resolution to enable the posi(cid:173)
`tion and size of each object to be obtained from the depth
`map, resulting in more accurate recognition of an obstacle.
`Fig. 9 shows the principle of depth map acquisition
`method. After the image on one side is divided into small
`blocks, the block having the highest correlation with each
`block is searched from the image on the other side by the tem(cid:173)
`plate matching method. The positional deviation between the
`corresponding blocks in the two images is called the dispari(cid:173)
`ty, and the distance is obtained by using this value according
`to equation (1).
`
`D
`
`_ (Distance belween cameras x Lens focal distance)
`.
`Istance-
`(P'
`I
`. h
`'d h
`D'
`. )
`Ixe PItC WI t x
`Ispanty
`
`(1)
`
`The depth map can be obtained by executing this process(cid:173)
`ing for all blocks.
`Obstacle recognition is performed by converting the depth
`map into 3-dimensional arrangement of external objects.
`Then only the blocks existing in the area are extracted. If
`blocks having almost equal distance information exist in ad(cid:173)
`jacent blocks, they are collectively recognized as an obstacle.
`Photos. 3 to 5 show the result of application to the lane(cid:173)
`change warning system for ensuring safety at the time of over(cid:173)
`taking on a highway. Here, two cameras are installed on and
`beneath the door mirror. Photo. 3 shows the image picked
`up by the upper camera, and Photo. 4 the depth map ob(cid:173)
`tained from it. Photo. 5 shows the result of recognizing only
`the vehicle in the adjacent lane.
`The stereo vision method is effective for peripheral recog(cid:173)
`nition, but development of a high-speed processor is a future
`task as a tremendous work load is required for searching the
`
`9
`
`

`

`Driving Environment Recognition for Active Safety
`
`corresponding point.
`
`4.3 Approaching Vehicle Recognition through Optical
`Flow
`
`It is necessary to detect only the approaching vehicle in the
`lane-change warning system and crossing-path warning sys(cid:173)
`tem. In the collision warning system, on the other hand, de(cid:173)
`tection of the vehicle moving direction is important for
`detecting the cutting-in vehicle and a vehicle running out from
`the present lane.
`As the image processing system for detecting the movement
`of objects in the image, it is the most effective to detect the
`optical flow. Optical flow detection is possible by the
`template-matching method. In other words, the moving dis(cid:173)
`tance on the image can be calculated by dividing the block
`having the highest correlation with each block from the im(cid:173)
`age after lapse of a certain time period.
`The time interval between image blocks used for matching
`is important for accurate recognition of the approaching ve(cid:173)
`hicle by optical flow detection. Fig. 10 shows the simulated
`size of the horizontal component of the vector of an object
`that is approaching at a speed of 20 km/h.
`As apparent from the result, a very wide searching area is
`
`Photo. 3 Original Image Picked up by Upper Camera
`in Stereo Vision
`
`Photo. 4 Depth Map by Stereo Vision
`
`50
`+-' c=
`Q) Q)
`§ .~ 40
`c.E:
`
`Flow calculation time interval : 300 msec
`1/2 inch ceo f = 7.5 mm
`Number of horizontal pixels: 512
`
`E ~ 8 B 30
`~ ; 20
`
`()
`Q)
`
`-
`
`N 0
`01: ~
`..... 10
`0
`Io
`
`Photo. 5 Vehicle Recognition by Stereo Vision
`
`5
`
`10
`
`20
`15
`Z-axis (m)
`
`25
`
`30
`
`35
`
`TOYOTA Technical Review Vol. 43 No . 1 Sep. 1993
`
`49
`
`Fig . 10 Flow Calculation Model and Calculation Results
`
`10
`
`

`

`necessary near the vehicle and no flow vector having a suffi(cid:173)
`cient size can be detected in a far range. Thus we have adopted
`a configuration for parallel operation of multiple correlation
`calculation boards at varied time intervals. A dominant cause
`of noise generation in the flow detected by the matching
`method is possible mismatching in the images of road sur(cid:173)
`face and vehicle side faces having little characteristics.
`To solve this problem, the stability of the size and the direc(cid:173)
`tion of the flow detected in each block over time are used
`for evaluating the reliability of the flow. As compared with
`the method which evaluates the similarity with the flow de(cid:173)
`tected in the adjacent blocks, this method is effective for de(cid:173)
`tecting a vehicle at a far location or a vehicle traveling at a
`low relative speed. Photos. 6 to 8 show a vehicle, a motor
`cycle and a bicycle, respectively, approaching from right at
`a trifurcate road with poor visibility.
`Results of several researches concerning the methods for
`obtaining the direction, moving speed and position of a mov(cid:173)
`ing object from the flow vector have been reported. In opti(cid:173)
`cal flow detection from the image picked up from a traveling
`vehicle, flow of the background due to the movement of the
`vehicle itself occurs in addition to the moving objects. The
`first problem to be solved is to extract only the flow of the
`object to be watched by compensating for the vector of the
`vehicle motion.
`
`5. Conclusion
`
`The peripheral recognition capabilities of the millimeter(cid:173)
`wave radar, laser radar and image processing technology fall
`far short of the driver's perception and judgment capabilities.
`Partially, however, they have equal or superior detection
`capabilities and the possibility of the perceptual enhancement
`system in limited situations for peripheral recognition is high.
`Finally, the important directions of the intelligence of the
`vehicle to be provided by the perceptual enhancement/advi(cid:173)
`sory system can be summarized as follows:
`• New human interface system
`• Driving environment recognition/judgment with danger
`prediction
`With regard to the former, the navigation system and many
`other intelligent functions using communication means have
`been developed in recent years to provide the driver of many
`types of information. It will, therefore, be indispensable to
`study the method for providing only the necessary informa(cid:173)
`tion for the driver easily and as required.
`With regard to the latter, danger prediction during driving
`naturally lead to how the vehicle should be driven. Some ex(cid:173)
`amples are judgment on the vehicle-to vehicle distance and
`vehicle speed for safe driving under the given traffic environ-
`
`50
`
`ment and weather conditions, and warning the driver of the
`possible danger by selecting the import point to be watched
`while approaching an intersection or a pedestrian crossing.
`An important task in the future will be providing vehicles
`with higher levels of intelligence by integrating various intel(cid:173)
`ligent functions and systems being adopted and developed for
`vehicles.
`
`Photo. 6 Optical Flow (Vehicle)
`
`Photo. 7 Optical Flow (Motor Cycle)
`
`Photo. 8 Optical Flow (8icycle)
`
`11
`
`

`

`We would like to express our deep gratitude to Prof.
`Hirochika Inoue in the Engineering Faculty of the Universi(cid:173)
`ty of Tokyo for his kind advice given for our study on the
`image recognition technologies.
`
`.Authors
`
`Driving Environment Recognition for Active Safety
`
`III References
`
`(1) M. Kotaki, Y. Kakimoto, E. Akutu, Y. Fujita, H. Fuku(cid:173)
`hara et al; "Development of millimeter wave automative
`sensing technology", IEEE MTTS Digest p.709-712, 1992
`(2) Report of the Millimeter-wave Sensing System Study and
`Research Committee, (Japanese), Radio Equipment In(cid:173)
`spection and Certification Institute, Tokyo, March 1990
`and March 1991
`(3) T. Teramoto, K. Fujimura, Y. Fujita; "Study of Laser
`Radar, National Highway Traffic Safety Administra(cid:173)
`tion", The Twelfth Technical Conference on Experimental
`Safety Vehicles, Paper No.89-4b-0-020, 1989
`(4) Suzuki, Tachibana, Aoki, Inoue; "An Automated High(cid:173)
`way Vehicle System Using Computer Vision", JSAE Au(cid:173)
`tumn Convention Proceeding 924, Vol. 1, 1992
`
`T. SUZUKI
`
`Y. NAKAYAMA
`
`Y.YAMADA
`
`M. KUME
`
`TOYOTA Technical Review Vol. 43 No.1 Sep. 1993
`
`5 1
`
`12
`
`