IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0678552
(2007-02-23)
|
등록번호 |
US-8121345
(2012-02-21)
|
발명자
/ 주소 |
- Jochem, Todd
- Batavia, Parag
- Ollis, Mark
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
9 인용 특허 :
13 |
초록
▼
A system and method of identifying a position of a crop row in a field, where an image of two or more crop rows is transmitted to a vision data processor. The vision data processor defines a candidate scan line profile for a corresponding heading and pitch associated with a directional movement of a
A system and method of identifying a position of a crop row in a field, where an image of two or more crop rows is transmitted to a vision data processor. The vision data processor defines a candidate scan line profile for a corresponding heading and pitch associated with a directional movement of a vehicle, for example, traversing the two or more crop rows. The candidate scan line profile comprises an array of vector quantities, where each vector quantity comprises an intensity value and a corresponding position datum. A preferential scan line profile in a search space about the candidate scan line profile is determined, and the candidate scan line profile is identified as a preferential scan line profile for estimating a position (e.g., peak variation) of one or more crop rows if a variation in the intensity level of the candidate scan line profile exceeds a threshold variation value. In addition, a template scan line profile may be utilized, where a candidate scan line profile is identified to be a preferential scan line profile if it is consistent with the template scan line profile.
대표청구항
▼
1. A method of identifying crop rows in a field comprising: collecting, via an imaging unit coupled to a data processor, image data comprising a template scan line profile representative of a known relationship between the imaging unit and a reference crop row, the template scan line profile compris
1. A method of identifying crop rows in a field comprising: collecting, via an imaging unit coupled to a data processor, image data comprising a template scan line profile representative of a known relationship between the imaging unit and a reference crop row, the template scan line profile comprising a series of mean intensity vectors associated with a desired minimum degree of variation between a minimum mean scan line intensity and a maximum scan line intensity;defining a candidate scan line profile for a corresponding heading and pitch of directional movement associated with the imaging unit and relative to the reference crop row;searching for a preferential scan line profile in an angular search space about the candidate scan line profile;identifying the candidate scan line profile as a preferential scan line profile and a selected one dimensional position data as a preliminary row position if the candidate scan line profile is consistent with a template scan line profile. 2. The method of claim 1, wherein the candidate scan line profile comprises an array of vector quantities, each vector quantity comprising an intensity value and the corresponding one-dimensional position data. 3. The method of claim 1, wherein the angular search space is defined by the corresponding pitch and heading of the imaging unit. 4. The method of claim 1 wherein the candidate scan line profile is generally consistent with the template scan line profile except for an offset in position. 5. The method of claim 1, further comprising updating the template scan line profile on a regular basis. 6. The method of claim 1, further comprising detecting a change in crop type or crop density to trigger an update of the template scan line profile. 7. The method of claim 1, further comprising updating the template scan line profile to comprise a weighted function of the template scan profile and a new mean intensity vector. 8. The method of claim 1, further comprising: normalizing an intensity of the image data collected in the collecting of the image data. 9. The method of claim 8, further comprising: defining a virtual, substantially horizontal plane in the collected image data; andsubtracting out the virtual, substantially horizontal plane to reduce the image intensity variation throughout the collected image data. 10. The method of claim 8, wherein the intensity of the collected image data indicates one of either an illumination value, a brightness value, and a luminance value of at least one pixel which at least in part comprises the collected image data. 11. An apparatus for identifying crop rows in a field comprising: a processor; anda memory unit communicatively connected to the processor and including: computer code for collecting image data comprising a template scan line profile representative of a known relationship between an imaging unit and a reference crop row, the template scan line profile comprising a series of mean intensity vectors associated with a desired minimum degree of variation between a minimum mean scan line intensity and a maximum scan line intensity;computer code for defining a candidate scan line profile for a corresponding heading and pitch of directional movement associated with the imaging unit and relative to the reference crop row;computer code for searching for a preferential scan line profile in an angular search space about the candidate scan line profile; andcomputer code for identifying the candidate scan line profile as a preferential scan line profile and a selected one dimensional position data as a preliminary row position if the candidate scan line profile is consistent with a template scan line profile. 12. The apparatus of claim 11, wherein the candidate scan line profile comprises an array of vector quantities, each vector quantity comprising an intensity value and the corresponding one-dimensional position data. 13. The apparatus of claim 11, wherein the angular search space is defined by the corresponding pitch and heading of the imaging unit. 14. The apparatus of claim 11 wherein the candidate scan line profile is generally consistent with the template scan line profile except for an offset in position. 15. The apparatus of claim 11, wherein the memory unit further comprises computer code for, updating the template scan line profile on a regular basis. 16. The apparatus of claim 11, wherein the memory unit further comprises computer code for, detecting a change in crop type or crop density to trigger an update of the template scan line profile. 17. The apparatus of claim 11, wherein the memory unit further comprises computer code for, updating the template scan line profile to comprise a weighted function of the template scan profile and a new mean intensity vector. 18. The apparatus of claim 11, wherein the memory unit further comprises computer code for: normalizing an intensity of the image data collected in the collecting of the image data. 19. The apparatus of claim 18, wherein the memory unit further comprises computer code for: defining a virtual, substantially horizontal plane in the collected image data; andsubtracting out the virtual, substantially horizontal plane to reduce the image intensity variation throughout the collected image data. 20. The apparatus of claim 18, wherein the intensity of the collected image data indicates one of either an illumination value, a brightness value, and a luminance value of at least one pixel which at least in part comprises the collected image data. 21. A computer program product, embodied on a non-transitory computer-readable medium, for identifying crop rows in a field comprising: computer code for collecting image data comprising a template scan line profile representative of a known relationship between an imaging unit and a reference crop row, the template scan line profile comprising a series of mean intensity vectors associated with a desired minimum degree of variation between a minimum mean scan line intensity and a maximum scan line intensity;computer code for defining a candidate scan line profile for a corresponding heading and pitch of directional movement associated with the imaging unit and relative to the reference crop row;computer code for searching for a preferential scan line profile in an angular search space about the candidate scan line profile; andcomputer code for identifying the candidate scan line profile as a preferential scan line profile and a selected one dimensional position data as a preliminary row position if the candidate scan line profile is consistent with a template scan line profile. 22. A system for identifying crop rows in a field comprising: an imaging unit, coupled to a data processor, configured to collect image data comprising a template scan line profile representative of a known relationship between an imaging unit and a reference crop row, the template scan line profile comprising a series of mean intensity vectors associated with a desired minimum degree of variation between a minimum mean scan line intensity and a maximum scan line intensity;an imaging unit interface configured to receive the collected image data;a definer communicatively connected to the imaging unit interface configured to define a candidate scan line profile for a corresponding heading and pitch of an imaging unit, the candidate scan line profile comprising an array of vector quantities, each vector quantity comprising an intensity value and a corresponding one-dimensional position data;a search engine configured to search for a preferential scan line profile in an angular search space about the candidate scan line profile, the search space defined by the corresponding pitch and heading of the imaging unit; the search engine identifying the candidate scan line profile as a preferential scan line profile and the selected one dimensional position data as a preliminary row position if the candidate scan line profile is consistent with a template scan line profile; anda control port configured to output directional movement instructions to a vehicle steering controller, the directional movement instructions derived from the preferential scan line profile and being associated with the imaging unit and relative to the reference crop row.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.