End-to end visual recognition system and methods
View Patent ↗We describe an end-to-end visual recognition system, where “end-to-end” refers to the ability of the system of performing all aspects of the system, from the construction of “maps” of scenes, or “models” of objects from training data, to the determination of the class, identity, location and other inferred parameters from test data. Our visual recognition system is capable of operating on a mobile hand-held device, such as a mobile phone, tablet or other portable device equipped with sensing and computing power. Our system employs a video based feature descriptor, and we characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system scores objects in the field of view based on their ranking.
1. A visual recognition method for identifying objects captured in a video stream having a captured time period, the method comprising:
capturing a video stream on an electronic device having an image sensor, said video stream comprising a plurality of temporally adjacent images;
enabling a user of the electronic device to select, from said video stream, a target object or scene for training;
associating each frame in an image with a corresponding frame in temporally adjacent images, or in images taken from nearby vantage points;
temporally aggregating statistics computed at one or more collections of temporally corresponding frames, into a descriptor; and
ranking features according to their structural stability margin;
wherein the structural stability margin is a limit or bounded range of variability acceptable from a nuisance factor.
2. The method recited in claim 1 ,
wherein said aggregation is performed by computing a mean, or median, or mode, or sample histogram of a contrast-invariant function of the image in said frames.
3. The method recited in claim 1 , further comprising:
spatially aggregating such statistics into a representation that is insensitive to the nuisance factor and distinctive;
exploiting such a representation within a classification scheme to enable the detection, localization, recognition and categorization of objects and scenes in video;
and displaying the result of the classification scheme by overlaying information on the live video stream, optionally localized and overlaid on the object of interest.
4. The method recited in claim 1 , further comprising:
selecting a plurality of features corresponding to translational, similarity, affine or more general reference frames from the video stream for objects in a field of view of the video stream; and
performing such a selection at a plurality of scales, and using topological consistency across scale as a criterion for propagating said general reference frames across different scales.
5. A visual recognition method for identifying objects captured in a video stream having a captured time period, the method comprising:
capturing a video stream on an electronic device having an image sensor, said video stream comprising a plurality of temporally adjacent images;
enabling a user of the electronic device to select, from said video stream, a target object or scene for training;
associating each frame in an image with a corresponding frame in temporally adjacent images, or in images taken from nearby vantage points;
temporally aggregating statistics computed at one or more collections of temporally corresponding frames, into a descriptor;
spatially aggregating such statistics into a representation that is insensitive to a nuisance factor and that is distinctive;
exploiting such a representation within a classification scheme to enable the detection, localization, recognition and categorization of objects and scenes in video;
displaying the result of the classification scheme by overlaying information on the live video stream, optionally localized and overlaid on the object of interest; and
ranking features according to their structural stability margin;
wherein the structural stability margin is a limit or bounded range of variability acceptable from said nuisance factor.
6. The method recited in claim 5 , wherein said programming performs steps comprising:
selecting a plurality of features corresponding to translational, similarity, affine or more general reference frames from the video stream for objects in a field of view of the video stream; and
performing such a selection at a plurality of scales, and using topological consistency across scale as a criterion for propagating said general reference frames across different scales.
7. The method recited in claim 5 ,
wherein said temporal aggregating of statistics is performed by computing a mean, or median, or mode, or sample histogram of a contrast-invariant function of the image in said frames.
8. The method recited in claim 6 ,
wherein said plurality of features comprises a plurality of feature points.
9. A visual recognition method for identifying objects captured in a video stream having a captured time period, the method comprising:
capturing a video stream on an electronic device having an image sensor, said video stream comprising a plurality of temporally adjacent images;
enabling a user of the electronic device to select, from said video stream, a target object or scene for training;
optionally selecting a plurality of features corresponding to translational, similarity, affine or more general reference frames from the video stream for objects in a field of view of the video stream;
performing such a selection at a plurality of scales, and using topological consistency across scale as a criterion for propagating said general reference frames across different scales;
associating each frame in an image with a corresponding frame in temporally adjacent images, or in images taken from nearby vantage points;
temporally aggregating statistics computed at one or more collections of temporally corresponding frames, into a descriptor;
spatially aggregating such statistics into a representation that is insensitive to a nuisance factor and that is distinctive;
exploiting such a representation within a classification scheme to enable the detection, localization, recognition and categorization of objects and scenes in video;
displaying the result of the classification scheme by overlaying information on the live video stream, optionally localized and overlaid on the object of interest; and
ranking features according to their structural stability margin;
wherein the structural stability margin is a limit or bounded range of variability acceptable from said nuisance factor.
10. The method recited in claim 9 ,
wherein said temporal aggregating of statistics is performed by computing a mean, or median, or mode, or sample histogram of a contrast-invariant function of the image in said frames.
11. The method recited in claim 9 , wherein said plurality of features comprises a plurality of feature points.