Patent Application
20080021616
Hereinafter, embodiments of the present invention will be described in detail with reference to drawings. First, description will be made as regard to an occupant restraint system 100 as an embodiment of the “occupant restraint system” according to the present invention with reference to
The arrangement of the occupant restraint system 100 to be installed in a vehicle according to this embodiment is shown in
As shown in
The photographing device 110 comprises a 3D (three-dimensional) camera 112 of a C-MOS or CCD (charge-coupled device) type in which light sensors are arranged into an array (lattice) arrangement. The camera 112 may be a monocular C-MOS 3D camera or a pantoscopic stereo 3D camera. The camera 112 is installed to be built in an instrument panel, an A-pillar, or the periphery of a windshield in a front portion of a vehicle and is disposed to face in a direction capable of photographing one or more occupants.
A perspective view of the cabin of the vehicle 10 taken from the camera 112 side is shown in
The control device 120 comprises at least an image processing device 130, a storage device 140, a computing device (MPU: micro processing unit) 150, an actuating device 160, an input/output device, a peripheral device, and the like, but the input/output device and the peripheral device are not shown.
The image processing device 130 is a device for processing images taken by the camera 112. Based on distance information and position information about the photographed object, the image processing device 130 clips a three-dimensional object within a specific region of the image range and divides the object into a combination of vehicle occupant and a vehicle seat and vehicle parts other than the combination. Also in this embodiment, the image processing device 130 comprises a coordinate transformation unit 131. The coordinate transformation unit 131 is adapted to transform the coordinate system about the camera 112 into a coordinate system about the vehicle body. Specifically, the coordinate transformation unit 131 transforms a view of the vehicle occupant C taken from the camera 112 into a view of the vehicle occupant C taken from the left side of the vehicle body. Further, the image processing device 130 is adapted to roughly recognize features of the three-dimensional object or roughly categorize the position and size of the vehicle occupant C into groups based on the volume distribution of the three-dimensional object.
The storage device 140 is a device for storing (recording) various data and the computed results to be used in the control device 120 and, in this embodiment, comprises at least a body information storage unit 141 and an estimated body size information storage unit 142. The storage device 140 corresponds to “a storage device for previously storing body information about surface profiles of a human body” of the present invention.
The body information storage unit 141 is adapted to previously store the body information (data of body features) such as profiles (contours) and sizes of respective body regions (for example, head, face, neck, jaw, shoulder, arm, leg, and knee) of a person and the positional relations among the body regions. The estimated body size information storage unit 142 is adapted to temporally record (store) information as a result of estimation by a body size estimation unit 153 as will be later described. The information as a result of estimation by the body size estimation unit 153 is read out from the estimated body size information storage unit 142 and is suitably used for controlling the occupant restraint device 170 based on the information.
The computing device 150 comprises at least an occupant information extracting unit 151, a seat information extracting unit 152, and the body size estimation unit 153. The computing device 150 corresponds to “a deriving device” of the present invention.
The occupant information extracting unit 151 is adapted to extract various information relating to the vehicle occupant C based on the information processed by the image processing device 130. Specifically, the positions, distances, profiles (contours) of respective body regions (for example, head, face, neck, jaw, shoulder, arm, leg, and knee) of the vehicle occupant C, the positional relations among the body regions, and the like are extracted by the occupant information extracting unit 151. The occupant information extracting unit 151 corresponds to “an information extraction device” of the present invention.
The seat information extracting unit 152 is adapted to extract various information relating to the driver seat 12 based on the information processed by the image processing device 130. Specifically, the positions, distances, angles, profiles (contours), and the like of the driver seat 12 and its components (such as a seat back, a seat cushion, a headrest and the like) are extracted by the seat information extracting unit 152.
The body size estimation unit 153 is adapted to estimate the body size of the vehicle occupant C based on the information extracted by the occupant information extracting unit 151 and the information extracted by the seat information extracting unit 152. Specifically, the indexes relating to the body size such as the sitting height, the chest thickness, the shoulder width and the like of the vehicle occupant C are estimated by the body size estimation unit 153. When there is no information extracted by the occupant information extracting unit 151, the body size estimation unit 153 determines that “the seat is not occupied”.
The actuating device 160 outputs an actuation signal (output signal) to the occupant restraint device 170 as a subject to be actuated (subject to be operated) and can vary the actuation signal to be outputted based on the estimated body size information by the body size estimation unit 153. Therefore, the mode for restraining the vehicle occupant C by the occupant restraint device 170 when operated is variable according to the estimated body size information. Accordingly, the actuating device 160 functions as a substantial control device relative to the occupant restraint device 170.
The occupant restraint device 170 is composed of one or more of occupant restraint devices such as an airbag apparatus (airbag module) and a seat belt apparatus which operate for restraining the vehicle occupant in the event of a vehicle accident. The occupant restraint device 170 corresponds to “an occupant restraint device” of the present invention. In addition to the occupant restraint device 170, a warning device (indication output, audio output) and the like may be installed.
In addition, an input element is installed in the vehicle 10 to detect information about collision prediction or collision occurrence of the vehicle, information about the driving state of the vehicle, information about traffic conditions around the vehicle, information about weather condition and about time zone, and the like and to input such detected information to the control device 120, but not shown.
Hereinafter, the action of the occupant restraint system 100 having the aforementioned arrangement will be described with reference to
In step S110 shown in
The camera 112 is set to be actuated, for example, when an ignition key is turned on or when a seat sensor (not shown) installed in the driver seat 12 detects a vehicle occupant C seated in the driver seat 12.
Then in step S120 shown in
In step S130, a segmentation process is conducted to segment a dot image of the three-dimensional profile obtained in the step S120 into a large number of pixels. In the segmentation process, the dot image of the three-dimensional surface profile is segmented into three-dimensional lattices, for example, (X64)×(Y64)×(Z32). An aspect of pixel segmentation in this embodiment is shown in
In step S140, a coordinate transformation process of the segmentation-processed image obtained in the step S130 is conducted. In the coordinate transformation process, the segmentation-processed image as the coordinate system about the camera 112 is transformed into a coordinate system about the vehicle body. Specifically, the image of the vehicle occupant C from a viewpoint of the camera 112 is transformed into an image of the vehicle occupant C from a viewpoint of a left side of the vehicle body. That is, in transformation, the X axis is set to extend in the front-to-rear direction of the vehicle, the Y axis is set to extend in the upward direction of the vehicle, and the Z axis is set to extend in the left-to-right direction of the vehicle. Accordingly, for example, the segmentation-processed image is transformed into a transformation-processed image C1 as shown in
These processes in step S110 through step S140 are carried out by the image processing device 130 shown in
Then, in step S150, a process for deriving the position of specific body region of the vehicle occupant C is conducted. This process is carried out by the occupant information extracting unit 151 shown in
This process corresponds to “associating occupant surface profile information relating to the specific body region of said vehicle occupant in the information extracted by said information extraction device with said body information which is previously stored in said storage device” of one form or the “compares the surface profile information of said specific body region to the body surface profile information of respective body regions which are previously stored in said storage device and derives the position of said specific body region based on a result of the comparison” of another form.
In this embodiment, the neck region to be set as the specific body region has significant feature in surface profile. Further, its contour is hardly influenced by the slight shifting of the photographing direction of the camera 112 and its level is hardly changed relative to the movement of the vehicle occupant C. In addition, since the neck region is exposed from clothes or the like, the neck region is hardly influenced by the thickness of the clothes when it is required to detect the actual body size of the vehicle occupant. Therefore, among regions of the body, the neck region is a region especially effective to estimate the body size of the vehicle occupant C precisely. It should be noted that one or more of regions such as head, face, jaw, shoulders, arms, legs, knees, and the like other than the neck region set in this embodiment may be used in the present invention.
In the aforementioned process of the step S150, the feature such as the contour of the specific body region which is previously stored in the body information storage unit 141 may be similar to the features of a plurality of regions of the processed image C1, depending on the size and the configuration of the specific body region. In this case, it is difficult to identify the specific body region. Therefore, for this case, it is effective to make a comparison relating to the positional relation between the specific body region and its peripheral regions, in addition to a comparison relating to the configuration of the specific body region. Specifically, in addition of the feature of the contour of the neck region, a condition that the neck is near the shoulders and the jaw is also employed. With this condition, the process compares the body information, which is previously stored in the body information storage unit 141, to the processed image C1, thereby precisely refining the candidate regions.
This process corresponds to “associating occupant surface profile information relating to the specific body region of said vehicle occupant in the information extracted by said information extraction device with said body information which is previously stored in said storage device” of one form or “compares the positional relation between the specific body region and a region around the specific body region to the positional relation between body regions which are previously stored in the storage device in addition to comparing the surface profile information of the specific body region to the body surface profile information of respective body regions which are previously stored in the storage device, and derives the position of the specific body region based on a result of the comparison” of another form.
For comparing the body information, which is previously stored in the body information storage unit 141, with the processed image C1, the specific body region may be previously set or selected from body regions taking the photographing quality of the camera 112 into consideration. For example, the degree of quality or the degree of similarity of image information may be employed as criterion for determination (“criterion for determination” of the present invention). Accordingly, among a plurality of body regions, only a region having high quality image information (region having high reliability as image information) or a region of which occupant information actually obtained by the camera 112 has high similarity to the body information previously stored in the body information storage unit 141 can be set as the specific body region. Therefore, it is possible to screen out image information of which quality is decreased due to irregular posture and movement of the vehicle occupant C or abnormal optical reflection.
In step S160 following the aforementioned step S150, a process for deriving the position of specific seat region (vehicle-side reference region) of the driver seat 12 is conducted. This process is carried out by the seat information extracting unit 152 shown in
When a seat slide position detection sensor, a seat cushion height detection sensor, a seat back angle detection sensor, and the like are installed, the position of the upper portion of the seat back can be presumed from information such as the seat slide position, the seat cushion height, the seat back angle, and the like obtained from these sensors.
In step S170, body size estimation process of the vehicle occupant C is conducted by using the position of the specific body region derived in step S150 and the position of the specific seat region derived in step S160. This process is conducted by the body size estimation unit 153 shown in
Specifically, the seating height of the vehicle occupant C is estimated by obtaining the relative height of the neck region as the specific body region relative to the upper portion of the seat back as the specific seat region. When the position of the upper portion of the seat back is not derived, the position of the upper portion of the seat back can be assumed as being positioned at a preset reference position.
Relating to the body size estimation process in the step S170, the chest thickness, the shoulder width, the configuration of the upper torso (volume, peripheral length), and the like other than the seating height of the vehicle occupant C may be estimated.
For example, for estimating the chest thickness of the vehicle occupant C, the positions of the shoulder and chest are derived as the specific body regions in step S150 and the position of the upper portion of the seat back is derived as the specific seat region in step S160. From the positional relation in anteroposterior direction between the shoulder and the upper portion of the seat back, it is detected whether or not the back of the vehicle occupant C is in close contact with the seat back. Then, from differential distance between the position of the chest and the position of the seat back, the chest thickness is estimated.
By performing the aforementioned processes in step S110 through step S170 sequentially, the body size of the vehicle occupant C detected by the camera 112 can be estimated. Information as result obtained by the body size estimation process in step S170 is used for controlling an object of actuation such as the occupant restraint device 170 or is temporally stored in the estimated body size storage unit 142 of
In step S210 shown in
When it is determined that the airbag actuating condition is satisfied (YES in step S210), the process proceeds to step S220 where information temporally stored in the estimated body size information storage unit 142 shown in
As an example, in case where the occupant restraint device 170 is an airbag module comprising an inflator (gas generator) and an airbag, the inflator is actuated in the event of a vehicle collision based on an actuation signal from the actuating device 160 so as to supply gas for deployment to the airbag. The pressure and flow volume of gas supplied from the inflator to the airbag are variable according to the information about the body size of the vehicle occupant C. Accordingly, the restraint capability (occupant restraining mode) by the airbag which is deployed into a region for occupant restraint is varied according to the body size of the vehicle occupant.
As mentioned above, the vehicle restraint system 100 of this embodiment can detect information about the vehicle occupant C precisely by performing the “occupant detection process” shown in
Further, this embodiment provides a vehicle 10 provided with an occupant restraint system 100 which is effective for achieving thorough restraint of a vehicle occupant.
The present invention is not limited to the aforementioned embodiments and various applications and modifications may be made. For example, the following respective embodiments based on the aforementioned embodiments may be carried out.
In the present invention, the operating mode of another occupant restraint device other than the airbag module, for example, the winding/unwinding mode of a seat belt and the operating mode of a warning device (indication output, audio output), may be controlled to be varied according to the “occupant detection process” of the aforementioned embodiment shown in
Besides the aforementioned structure of controlling the operating mode of the occupant restraint device 170 according to the body size information of the vehicle occupant C as the “occupant restraint process” of the aforementioned embodiment shown in
Though the aforementioned embodiment has been described with regard to a case where the neck region is set as the specific body region, another region (such as head, face jaw, shoulder, arm, leg, knee and the like) other than the neck region may be set as the specific body region or a plurality of regions including the neck region or a wide-range area from the head to the shoulders may be set as the specific body region in the present invention.
Though the aforementioned embodiment has been described with regard to the occupant restraint system 100 to be installed for a vehicle occupant in the driver seat, the arrangement of the occupant restraint system of the present invention may be adapted to be installed not only for a vehicle occupant in a driver seat but also for a vehicle occupant in a front passenger seat and a vehicle occupant in a rear seat. In this case, the camera as the photographing device may be suitably installed in various vehicle body components such as an instrument panel positioned in an anterior portion of an automobile body, a pillar, a door, a windshield, a seat and the like, according to need.
Though the aforementioned embodiment has been described with regard to a case for deriving information about the vehicle occupant C directly seated in the driver seat 12, the present invention can be used for an arrangement for deriving information about a vehicle occupant seated in a vehicle seat indirectly via a child seat or a junior seat.
Though the aforementioned embodiment has been described with regard to the arrangement of the occupant restraint system to be installed in an automobile, the present invention can be adopted to various vehicles other than automobile such as an airplane, a boat, a train, a bus, a truck, and the like.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2005-208990 | Jul 2006 | JP | national |
