IPC분류정보
| 국가/구분 |
United States(US) Patent
등록
|
| 국제특허분류(IPC7판) |
|
| 출원번호 |
UP-0480507
(2002-06-14)
|
| 등록번호 |
US-7570793
(2009-08-24)
|
| 우선권정보 |
DE-101 28 954(2001-06-15); DE-101 32 335(2001-07-04); DE-101 48 062(2001-09-28); DE-101 54 861(2001-11-08) |
| 국제출원번호 |
PCT/EP02/006594
(2002-06-14)
|
| §371/§102 date |
20040907
(20040907)
|
| 국제공개번호 |
WO03/001241
(2003-01-03)
|
|
발명자
/ 주소 |
- Lages, Ulrich
- Willhoeft, Volker
- Dittmer, Martin
|
| 출원인 / 주소 |
- IBEO Automobile Sensor GmbH
|
| 대리인 / 주소 |
Harness, Dickey & Pierce, P.L.C.
|
| 인용정보 |
피인용 횟수 :
65 인용 특허 :
18 |
초록
▼
The invention relates to a method for providing corrected data in order to generate a model of a monitoring area which is located in the respective visual range of at least two opto-electronic sensors for determining the position of detected objects, based on the amounts of raw data elements corresp
The invention relates to a method for providing corrected data in order to generate a model of a monitoring area which is located in the respective visual range of at least two opto-electronic sensors for determining the position of detected objects, based on the amounts of raw data elements corresponding to object points in said monitoring area, said amounts of raw data elements being respectively detected by one of the sensors when the visual range is sensed and associated therewith, and the amounts of raw data elements from various sensors which are temporally linked to each other forming a group. The raw data elements corresponding to said amounts respectively comprise at least the coordinates of object points detected by the associated sensor in relation to the position of the detecting sensor. In order to form corrected amounts of corrected data elements corresponding to the amounts of raw data elements of a group for each group quantity, the coordinates contained in the raw data elements are transformed into a common coordinate system, taking into account the relative position of the respective sensors.
대표청구항
▼
The invention claimed is: 1. A method for provisioning data from a monitored zone, which lies in respective fields of view of at least two, a first and a second, optoelectronic sensors, comprising: capturing sets of raw data elements using the at least two sensors, wherein the raw data elements of
The invention claimed is: 1. A method for provisioning data from a monitored zone, which lies in respective fields of view of at least two, a first and a second, optoelectronic sensors, comprising: capturing sets of raw data elements using the at least two sensors, wherein the raw data elements of the sets include coordinates of object detected by the respective detecting sensor and for each set of the coordinates associating a corresponding position of the respective detecting sensor; forming a group of the sets of raw data elements from the sets of raw data elements captured by a different sensor of the at least two sensors, where the sets of raw data elements in the group have a specific time association relative to one another; performing object tracking for each set of the raw data elements in the group before transforming the coordinates contained therein; and for each set of the group, transforming the coordinates contained in the sets of raw data elements into a common coordinate system, while taking account of the relative position of the detecting sensors; wherein the steps of forming, performing and transforming are implemented by one or more processors. 2. A method in accordance with claim 1, characterized in that the coordinates of the raw data elements are corrected for each of the sets of raw data elements, in each case in accordance with the actual movement of the sensor detecting it, or with a movement approximated thereto, and in accordance with the difference between a time defined as the point in time of the detection of the respective raw data elements and a reference point in time. 3. A method in accordance with claim 2, characterized in that a time defined as the point in time of the detection of the set is used as the point in time of the detection of the raw data elements for all raw data elements of a set. 4. A method in accordance with claim 2, characterized in that, on the fixing of the time defined as the point in time of the detection of a raw data element, the time interval of the detection of the individual raw data elements of the set with respect to one another are taken into account. 5. A method in accordance with claim 1, characterized in that the coordinates of the raw data elements are corrected for each set in accordance with the movement data associated with them and in accordance with the difference between a time defined as the point in time of the detection of the raw data elements and a reference point in time of the group or set. 6. A method in accordance with claim 2, characterized in that the reference point in time lies between the earliest time (defined as the detection time) of a raw data element of one of the sets of the group and the timewise last time (defined as the detection time) of a raw data element of one of the sets of the group. 7. A method in accordance with claim 1 characterized in that virtual object groups are formed which are associated in each case with an object and which have virtual objects which were prepared on the basis in each case of one set of raw data and are recognized as corresponding to an object; in that, for each virtual object group associated with an object, the associated raw data elements in each set are sought; in that for each virtual object group associated with an object, a reference point in time associated with it is fixed; and in that for each virtual object the coordinates of the raw data elements associated with it in all sets of the group are corrected in accordance with the movement of the respective sensor detecting these raw data elements and/or in accordance with the movement data associated with these raw data elements and in accordance with the difference between a time defined as the point in time of the detection of the raw data element and the reference point in time for the virtual object. 8. A method in accordance with claim 7, characterized in that the reference points in time respectively associated in each case with the virtual object groups lie between the earliest time (defined as the point in time of the detection) of a raw data element associated with a virtual object of the respective virtual object group and the timewise last time (defined as the point in time of the detection) of a raw data element associated with a virtual object of the respective virtual object group. 9. A method in accordance with claim 1, characterized in that the object tracking is carried out on the basis of the raw data elements of a set in an evaluation unit of the sensor detecting the raw data of the set and the other steps are carried out in another data processing device. 10. A method in accordance with claim 7, characterized in that the corrected data elements for an object group also contain the reference point in time associated with this object group. 11. A method in accordance with claim 1, characterized in that it is carried out iteratively for respective sequential scans of the sensors, wherein, after reading in of at least one original set of raw data elements which are associated with one of the sensors and which were detected in a later scan than the raw data elements of the set of raw data elements previously contained in the group of sets of raw data elements and associated with the sensor, a original group is formed which contains the sets of raw data elements of the previous group associated with other sensors and contains the original set of raw data elements; and in that is it subsequently also carried out for the original group of sets of raw data elements, with data already obtained in the preceding iteration preferably being used. 12. A method in accordance with claim 1, characterized in that the model is only produced for a monitored zone in which the fields of view of the sensors overlap. 13. A method for the production of a model of a monitored zone which lies in respective fields of view of at least two optoelectronic sensors for the determination of the position of detected objects and contains object points, in which the method for the provision of corrected data is carried out in accordance with claim 1; and an object recognition or object tracking takes place on the basis of all corrected data elements. 14. A method in accordance with claim 13, characterized in that an object recognition and/or object tracking is/are carried out on the basis of the corrected data elements separately for each virtual object group, with the associated reference points in time preferably being taken into account. 15. A method in accordance with claim 1, characterized in that it is completely carried out in an evaluation device of one or more sensors. 16. A computer program embodied as computer executable instructions on a computer readable medium, the computer program implementing a method for the provision of corrected data of a monitored zone (26), which lies in respective fields of view (22, 24) of at least two, a first and a second, optoelectronic sensors (10, 12), the computer executable instructions performing the steps of: capturing sets of raw data elements using the at least two sensors, wherein the raw data elements of the sets include coordinates of object detected by the respective detecting sensor and for each set of the coordinates associating a corresponding position of the respective detecting sensor; forming a group of sets of raw data elements from sets of raw data elements captured by a different sensor of the at least two sensors, where the sets of raw data elements in the group have a specific time association relative to one another; performing object tracking for each set of the raw data elements in the group before transforming the coordinates contained therein; and for each set of the group, transforming the coordinates contained in the sets of raw data elements into a common coordinate system, while taking account of the relative position of the detecting sensors. 17. A computer program product with program code means which are stored on a computer readable medium to carry out a method for the provision of corrected data of a monitored zone (26), which lies in respective fields of view (22, 24) of at least two, a first and a second, optoelectronic sensors (10, 12), the program code means comprising: means for capturing sets of raw data elements using the at least two sensors, wherein the raw data elements of the sets include coordinates of object detected by the respective detecting sensor and for each set of the coordinates associating a corresponding position of the respective detecting sensor; means for forming a group of sets of the raw data elements from the sets of raw data elements captured by different sensors of the at least two sensors, where the sets of raw data elements in the group have a specific time association relative to one another; means for performing object tracking for each set of the raw data elements in the group before transforming the coordinates contained therein; and means for transforming the coordinates contained in the sets of raw data elements into a common coordinate system for each set of the group, while taking account of the relative position of the detecting sensors. 18. An apparatus for the production of a model of a monitored zone (26) comprising at least two optoelectronic sensors (10, 12), in particular laser scanners, whose fields of view (22, 24) include the monitored zone; a data processing device (20) designed to carry out the method in accordance with claim 1; and data links (16, 18) for the transfer of the raw data elements detected by the sensors (10) to the data processing device (20). 19. An apparatus for the production of a model of a monitored zone (26) comprising at least two optoelectronic sensors (10, 12), in particular laser scanners, whose fields of view (22, 24) include the monitored zone (26) and which each have an evaluation device for the object recognition and/or object tracking and for the output of corresponding virtual object data, a data processing device (20) designed to carry out the method in accordance with claim 1, and data links (16, 18) for the transmission of the raw data elements detected by the sensors (10, 12) and virtual object data to the data processing device (20). 20. The method in accordance with claim 1 characterized in that each sensor scans its filed of view.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.