Activity recognition systems and methods
An activity recognition system is disclosed. A plurality of temporal features is generated from a digital representation of an observed activity using a feature detection algorithm. An observed activity graph comprising one or more clusters of temporal features generated from the digital representation is established, wherein each one of the one or more clusters of temporal features defines a node of the observed activity graph. At least one contextually relevant scoring technique is selected from similarity scoring techniques for known activity graphs, the at least one contextually relevant scoring technique being associated with activity ingestion metadata that satisfies device context criteria defined based on device contextual attributes of the digital representation, and a similarity activity score is calculated for the observed activity graph as a function of the at least one contextually relevant scoring technique, the similarity activity score being relative to at least one known activity graph.
1. A activity recognition robot device comprising:
a memory storing known activity data objects, wherein each known activity data object represents a known activity and includes similarity scoring techniques and clustered temporal features; and
an activity recognition device coupled with the memory having a processor, wherein, upon execution of software instructions stored on a non-transitory computer readable medium, the processor is configurable to:
generate a plurality of temporal features from a digital representation of an observed action involving at least one recognized object using at least one feature detection algorithm;
establish an observed activity data object comprising one or more observed temporal feature clusters generated from the plurality of temporal features;
calculate a similarity activity score for the observed activity data object relative to at least one of the known activity data objects as a function of the similarity scoring techniques that are contextually relevant to the activity recognition device, the clustered temporal features, and the observed temporal feature clusters;
access an activity recognition results set as a function of the similarity activity score; and
cause the robot to take action based on the activity recognition results set.
2. The robot device of claim 1 , wherein the activity recognition results set comprises an action prediction.
3. The robot device of claim 2 , wherein the action prediction is based on variations of known activities.
4. The robot device of claim 1 , wherein the known activity data objects comprise known activity graphs.
5. The robot device of claim 4 , wherein the known activity graphs comprise directed acyclic graphs.
6. The robot device of claim 1 , wherein the observed activity data objects comprise observed activity graphs.
7. The robot device of claim 6 , wherein the observed activity graphs comprise directed acyclic graphs.
8. The robot device of claim 1 , wherein the known activity data objects are stored in an activity database.
9. The robot device of claim 1 , wherein the activity recognition device is further configured to receive the known activity data objects based on a contextual query submitted to an activity database.
10. The robot device of claim 1 , wherein the clustered temporal features comprise trajectories of features derived from the at least one feature detection algorithm.
11. The robot device of claim 1 , wherein the observed temporal feature clusters comprise trajectories of the plurality of temporal features.
12. The robot device of claim 1 , wherein the at least one recognized object comprises a person.
13. The robot device of claim 12 , wherein the person comprises a patient.
14. The robot device of claim 1 , wherein the at least one of the known activity data objects represents a therapy.
15. The robot device of claim 14 , wherein the therapy comprises a physical therapy regime.
16. The robot device of claim 1 , wherein the at least one of the known activity data objects represents an interaction among multiple objects.
17. The robot device of claim 1 , wherein the digital representation comprises video data of the observed action.
18. The robot device of claim 1 , wherein the digital representation comprises one or more of image data, audio data, tactile data, kinesthetic data, temperature data, kinematic data, and radio signal data.
19. The robot device of claim 1 , wherein the at least one of the known activity data objects comprises domain-specific attributes.
20. The robot device of claim 19 , wherein the domain-specific attributes are associated with at least one of the following domains: a medical domain, a healthcare domain, and a sports domain.
21. The robot device of claim 1 , wherein the similarity score comprises a measure of an estimated entitlement.
22. The robot device of claim 1 , wherein the action comprises executing a command.
23. The robot device of claim 1 , wherein the action comprises generating an alert.
24. The robot device of claim 1 , wherein the at least one feature detection algorithm includes one of the following: a scale-invariant feature transform (SIFT), Fast Retina Keypoint (FREAK), Histograms of Oriented Gradient (HOG), Speeded Up Robust Features (SURF), DAISY, Binary Robust Invariant Scalable Keypoints (BRISK), FAST, Binary Robust Independent Elementary Features (BRIEF), Harris Corners, Edges, Gradient Location and Orientation Histogram (GLOH), Energy of image Gradient (EOG), and Transform Invariant Low-rank Textures (TILT) feature detection algorithm.
25. The robot device of claim 1 , wherein the similarity scoring techniques include at least one of a Euclidean distance, linear kernel, polynomial kernel, Chi-squared kernel, Cauchy kernel, histogram intersection kernel, Hellinger's kernel, Jensen-Shannon kernel, hyperbolic tangent (sigmoid) kernel, rational quadratic kernel, multiquadratic kernel, inverse multiquadratic kernel, circular kernel, spherical kernel, wave kernel, power kernel, log kernel, spline kernel, Bessel kernel, generalized T-Student kernel, Bayesian kernel, wavelet kernel, radial basis function (RBF), exponential kernel, Laplacian kernel, ANOVA kernel and B-spline kernel function.