Generating 3-dimensional maps of a scene using passive and active measurements
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/00
G01S-017/08
G06T-007/20
G01C-003/08
G01S-017/42
G01S-017/89
G05D-001/00
G06K-009/62
G06T-015/00
G01S-017/02
G01S-017/93
G01C-021/36
출원번호
US-0087222
(2016-03-31)
등록번호
US-10024965
(2018-07-17)
발명자
/ 주소
Nehmadi, Youval
Ur, Shmuel
Cohen, Ronny
출원인 / 주소
VayaVision, Ltd.
대리인 / 주소
M&B IP Analysts, LLC
인용정보
피인용 횟수 :
0인용 특허 :
26
초록▼
A method and apparatus for generating 3D-maps for acquiring three-dimensional (3D) maps are presented. The method includes analyzing at least one image acquired by a passive sensor to identify a plurality of objects in the at least one image; classifying the plurality of objects; determining, based
A method and apparatus for generating 3D-maps for acquiring three-dimensional (3D) maps are presented. The method includes analyzing at least one image acquired by a passive sensor to identify a plurality of objects in the at least one image; classifying the plurality of objects; determining, based on the classification, whether to passively measure a distance to each of the plurality of objects; passively measuring the distance to at least one of the plurality of objects based on the determination; actively measuring a distance to some of the plurality of objects, wherein the distance to one of the same of the plurality of objects is actively measured when the distance to the object cannot be passively measured; and generating a 3D map of a scene based on the distance measured to each of the plurality of objects.
대표청구항▼
1. A method for acquiring three-dimensional (3D) maps, comprising: analyzing at least one image acquired by a passive sensor to identify a plurality of objects in the at least one image;classifying the plurality of objects as any of: a stationary object, a non-stationary object, a suspicious object,
1. A method for acquiring three-dimensional (3D) maps, comprising: analyzing at least one image acquired by a passive sensor to identify a plurality of objects in the at least one image;classifying the plurality of objects as any of: a stationary object, a non-stationary object, a suspicious object, and a non-suspicious object;determining, based on the classification, whether to passively measure a distance to each of the plurality of objects;passively measuring the distance to at least one of the plurality of objects based on the determination;wherein the distance to the at least one object is passively measured, for each object classified as a stationary object, when a previous distance to the object is not available;actively measuring a distance to some of the plurality of objects, wherein the distance to one of the same of the plurality of objects is actively measured when the distance to the object cannot be passively measured; andgenerating a 3D map of a scene based on the distance measured to each of the plurality of objects. 2. The method of claim 1, wherein analyzing the at least one image further comprises: segmenting the at least one image to render a segmentation map; andidentifying the plurality of objects in the segmentation map. 3. The method of claim 1, further comprising: identifying a type of each of the plurality of objects; andclassifying each of the plurality of objects based on the identified type of the object. 4. The method of claim 1, further comprising: comparing the at least one image to a previously acquired image; andidentifying a change in a location of each of the plurality of objects based on the comparison, wherein each of the plurality of objects is classified based on the change in the location of the object. 5. The method of claim 1, further comprising: determining, for each object of the plurality of objects, whether the object is identified in at least one geographic map; andclassifying each object identified in the at least one geographic map as a stationary object. 6. The method of claim 1, wherein the passively measuring the distance to the at least one object further comprising: determining if the passive sensor is in motion;determining the distance to the least one object using a motion sensor, when the passive sensor is in motion; anddetermining the distance to the least one object based on the number of the pixels to the object and a known reference measurement, when the passive sensor is not in motion. 7. The method of claim 6, wherein the known reference measurement is at least one of: a number of pixels from a valid reference object, and a dimension of the object. 8. The method of claim 1, wherein passively measuring the distance further comprising, for each object classified as a non-stationary object and as a non-suspicious object: determining a boundary speed of the object;determining a direction of movement of the object; andestimating the distance to the object based on the determined direction and the determined boundary speed. 9. The method of claim 8, further comprising: determining if the estimated distance is below a safe distance threshold; andactively measuring the distance to the at least one object, when the estimated distance is below the safe distance threshold. 10. The method of claim 1, wherein the distance is actively measured to any object classified as any of: a non-stationary object, and a suspicious object. 11. The method of claim 1, wherein the distance to one of the plurality of objects is actively measured when a reliable passive measurement for the object cannot be determined. 12. The method of claim 1, wherein actively measuring the distance to some of the plurality of objects further comprises: performing a number of laser measurements for each actively measured object, wherein the number of laser measurements is determined based on a required resolution. 13. The method of claim 12, further comprising: computing, for each actively measured object, a distance to each point in the object based on the laser measurements. 14. The method of claim 1, wherein generating the 3D-map further comprising: rendering a 3D-surface of each object using the distance measurements. 15. The method of claim 1, wherein the scene is a field of view captured by an apparatus for causing generation of the 3D-map. 16. A non-transitory computer-readable medium having stored thereon instructions for executing the method according to claim 1. 17. An apparatus for acquiring three-dimensional (3D) maps, comprising: a passive sensor for acquiring images of a scene;an active sensor for measuring distances from objects in the scene; anda processing system, wherein the processing system is configured to:analyze at least one image acquired by the passive sensor to identify a plurality of objects in the at least one image;classify the plurality of objects as any of: a stationary object, a non-stationary object, a suspicious object, and a non-suspicious object;determine, based on the classification, whether to passively measure a distance to each of the plurality of objects;passively measure the distance to at least one of the plurality of objects based on the determination;wherein the distance to the at least one object is passively measured, for each object classified as a stationary object, when a previous distance to the object is not available;actively measure, by the active sensor, a distance to some of the plurality of objects, wherein the distance to one of the plurality of objects is actively measured when the distance to the object cannot be passively measured; andgenerate a 3D map of a scene based on the distance measured to each of the plurality of objects. 18. A method for acquiring three-dimensional (3D) maps, comprising: acquiring at least one image by a passive sensor;segmenting the at least one image to render a segmentation map;classifying a plurality of pixels in each segment identified in the segmentation map as any of: a stationary pixel, a non-stationary pixel, a suspicious pixel, and a non-suspicious pixel;determining, based on the classification, whether to passively measure a distance to each of the plurality of pixels;passively measuring the distance to at least one of the plurality of pixels based on the determination;wherein the distance to the at least one pixel is passively measured, for each pixel classified as a stationary pixel, when a previous distance to the pixel is not available;actively measuring a distance value to each pixel of a first number of pixels in each segment identified in the segmentation map, wherein the first number of pixels is less than the number of pixels in each segment;computing a distance value to each pixel in the segment using the distance of pixel in the first number of pixels; andgenerating a 3D map of a scene based on the measured and computed distance values.
Aggarwal,Manoj; Sawhney,Harpreet; Samarasakera,Supun; Kumar,Rakesh; Burt,Peter; Eledath,Jayan; Hanna,Keith J., Method and system for performing surveillance.
Le Parquier Guy (Versailles FRX) Fousse Henri (Nogent sur Marne FRX), Process for estimating the distance between a stationary object and a moving vehicle and device for using this process.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.