Multi-view object detection using appearance model transfer from similar scenes
First Claim
1. A method for determining motion directions for video dataset object images, the method comprising:
- estimating directions of motion, through an optical flow process executing on a processor, for each of a plurality of object images that are extracted from a source training video dataset input, for each of a plurality of different camera scene viewpoints, wherein the object images are collected from each of the different camera scene viewpoints;
representing each space-time point in the estimated optical flow directions of motion of the objects appearing for each respective camera viewpoint by a four-dimensional vector, the vector comprising a location of the each space-time point in an image plane, a magnitude and a direction of its optical flow; and
categorizing the plurality of object images into a plurality of optical flow map clusters as a function of similarities of their determined motion directions by;
discarding the space-time points that have an optical flow magnitude that is above or below certain respective fixed thresholds as noise;
after the discarding the noise points, randomly sub-sampling and clustering a remainder of the space-time points into the optical flow map clusters by clustering that automatically selects a scale of analysis and a total number of the clusters; and
representing different values of the directions of motion of the objects appearing in the scene viewpoint of each optical flow map cluster by a dominant direction of motion of the points within each optical flow map cluster and by a location of the cluster in the image plane.
2 Assignments
0 Petitions
Accused Products
Abstract
View-specific object detectors are learned as a function of scene geometry and object motion patterns. Motion directions are determined for object images extracted from a training dataset and collected from different camera scene viewpoints. The object images are categorized into clusters as a function of similarities of their determined motion directions, the object images in each cluster are acquired from the same camera scene viewpoint. Zenith angles are estimated for object image poses in the clusters relative to a position of a horizon in the cluster camera scene viewpoint, and azimuth angles of the poses as a function of a relation of the determined motion directions of the clustered images to the cluster camera scene viewpoint. Detectors are thus built for recognizing objects in input video, one for each of the clusters, and associated with the estimated zenith angles and azimuth angles of the poses of the respective clusters.
-
Citations
25 Claims
-
1. A method for determining motion directions for video dataset object images, the method comprising:
-
estimating directions of motion, through an optical flow process executing on a processor, for each of a plurality of object images that are extracted from a source training video dataset input, for each of a plurality of different camera scene viewpoints, wherein the object images are collected from each of the different camera scene viewpoints; representing each space-time point in the estimated optical flow directions of motion of the objects appearing for each respective camera viewpoint by a four-dimensional vector, the vector comprising a location of the each space-time point in an image plane, a magnitude and a direction of its optical flow; and categorizing the plurality of object images into a plurality of optical flow map clusters as a function of similarities of their determined motion directions by; discarding the space-time points that have an optical flow magnitude that is above or below certain respective fixed thresholds as noise; after the discarding the noise points, randomly sub-sampling and clustering a remainder of the space-time points into the optical flow map clusters by clustering that automatically selects a scale of analysis and a total number of the clusters; and representing different values of the directions of motion of the objects appearing in the scene viewpoint of each optical flow map cluster by a dominant direction of motion of the points within each optical flow map cluster and by a location of the cluster in the image plane. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method of providing a service for determining motion directions for video dataset object images, the method comprising:
-
providing a motion direction determiner that estimates directions of motion, through an optical flow process, for each of a plurality of object images that are extracted from a source training video dataset input, for each of a plurality of different camera scene viewpoints, wherein the object images are collected from each of the different camera scene viewpoints, and represents each space-time point in the estimated optical flow directions of motion of the objects appearing for each respective camera viewpoint by a four-dimensional vector, the vector comprising a location of each space-time point in an image plane, a magnitude and a direction of its optical flow; and providing an object classifier that categorizes the plurality of object images into a plurality of optical flow map clusters as a function of the similarities of their determined motion directions by; discarding the space-time points that have an optical flow magnitude that is above or below certain respective fixed thresholds as noise; after the discarding the noise points, randomly sub-sampling and clustering a remainder of the space-time points into the optical flow map clusters by clustering that automatically selects a scale of analysis and a total number of the clusters; and representing different values of the directions of motion of the objects appearing in the scene viewpoint of each optical flow map cluster by a dominant direction of motion of the points within the each optical flow map cluster and by a location in the image plane. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A system comprising:
-
a processing unit; a computer readable memory in circuit communication with the processing unit; and a computer-readable storage medium in circuit communication with the processing unit; and wherein the processing unit, when executing the program instructions stored on the computer-readable storage medium via the computer readable memory; estimates directions of motion, through an optical flow process, for each of a plurality of object images that are extracted from a source training video dataset input, for each of a plurality of different camera scene viewpoints, wherein the object images are collected from each of the different camera scene viewpoints; represents each space-time point in the estimated optical flow directions of motion of the objects appearing for each respective camera viewpoint by a four-dimensional vector, the vector comprising a location of the each space-time point in an image plane, a magnitude and a direction of its optical flow; and categorizes the plurality of object images into a plurality of optical flow map clusters as a function of the similarities of their determined motion directions by; discarding the space-time points that have an optical flow magnitude that is above or below certain respective fixed thresholds as noise; after the discarding the noise points, randomly sub-sampling and clustering a remainder of the space-time points into the optical flow map clusters by clustering that automatically selects a scale of analysis and a total number of the clusters; and representing different values of the directions of motion of the objects appearing in the scene viewpoint of each optical flow map cluster by a dominant direction of motion of the points within the each optical flow map cluster and by a location in the image plane. - View Dependent Claims (16, 17, 18, 19)
-
-
20. An article of manufacture, comprising:
-
a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising instructions that, when executed by the computer processor, cause the computer processor to; estimate directions of motion, through an optical flow process, for each of a plurality of object images that are extracted from a source training video dataset input, for each of a plurality of different camera scene viewpoints, wherein the object images are collected from each of the different camera scene viewpoints; represent each space-time point in the estimated optical flow directions of motion of the objects appearing for each respective camera viewpoint by a four-dimensional vector, the vector comprising a location of the each space-time point in an image plane, a magnitude and a direction of its optical flow; and categorize the plurality of object images into a plurality of optical flow map clusters as a function of the similarities of their determined motion directions by; discarding the space-time points that have an optical flow magnitude that is above or below certain respective fixed thresholds as noise; after the discarding the noise points, randomly sub-sampling and clustering a remainder of the space-time points into the optical flow map clusters by clustering that automatically selects a scale of analysis and a total number of the clusters; and representing different values of the directions of motion of the objects appearing in the scene viewpoint of each optical flow map cluster by a dominant direction of motion of the points within the each optical flow map cluster and by a location of the cluster in the image plane. - View Dependent Claims (21, 22, 23, 24, 25)
-
Specification