Clustering nodes in a self-organizing map using an adaptive resonance theory network
View Patent ↗Techniques are disclosed for discovering object type clusters using pixel-level micro-features extracted from image data. A self-organizing map and adaptive resonance theory (SOM-ART) network is used to classify objects depicted in the image data based on the pixel-level micro-features. Importantly, the discovery of the object type clusters is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. The SOM-ART network is adaptive and able to learn while discovering the object type clusters and classifying objects.
1. A computer-implemented method for discovering object type clusters for image data captured by a video camera, the method comprising:
receiving a micro-feature vector including multiple micro-feature values, each micro-feature value based on at least one pixel-level characteristic of a foreground patch that depicts a foreground object;
processing the micro-feature vector by a self-organizing map adaptive resonance theory (SOM-ART) network to discover the object type clusters for the image data;
classifying the foreground object as depicting a first object type corresponding to a first object type cluster of the object type clusters when the micro-feature vector matches the first object type cluster; and
indicating that no match is found when the micro-feature vector does not correspond to any of the object type clusters for the image data.
2. The computer-implemented method of claim 1 , further comprising:
receiving additional micro-feature vectors; and
updating the SOM-ART network when a predetermined number of the additional micro-feature vectors is received to produce an updated SOM-ART network.
3. The computer-implemented method of claim 2 , further comprising:
determining that a micro-feature value is invalid; and
excluding the invalid micro-feature value from the updating of the SOM-ART network.
4. The computer-implemented method of claim 1 , further comprising estimating a topology for the SOM-ART network based on the number of input micro-feature vectors.
5. The computer-implemented method of claim 1 , further comprising merging the first object type cluster with a second object type cluster of the object type clusters for the image data when the first object type cluster overlaps the second object type cluster by a specified amount.
6. The computer-implemented method of claim 1 , further comprising:
receiving additional micro-feature vectors; and
removing the first object type cluster when none of the additional micro-feature vectors match the first object type cluster.
7. The computer-implemented method of claim 1 , further comprising adding a new object type cluster when the micro-feature vector does not correspond to any of the object type clusters for the image data.
8. The computer-implemented method of claim 1 , further comprising:
receiving additional micro-feature vectors; and
processing the additional micro-feature vectors to produce a mature SOM-ART network before classifying the foreground patch.
9. A computer-readable storage medium containing a program which, when executed by a processor, performs an operation for discovering object type clusters for image data captured by a video camera, the operation comprising:
receiving a micro-feature vector including multiple micro-feature values, each micro-feature value based on at least one pixel-level characteristic of a foreground patch that depicts a foreground object;
processing the micro-feature vector by a self-organizing map adaptive resonance theory (SOM-ART) network to discover the object type clusters for the image data;
classifying the foreground object as depicting a first object type corresponding to a first object type cluster of the object type clusters when the micro-feature vector matches the first object type cluster; and
indicating that no match is found when the micro-feature vector does not correspond to any of the object type clusters for the image data.
10. The computer-readable storage medium of claim 9 , wherein the operation further comprises:
receiving additional micro-feature vectors; and
updating the SOM-ART network when a predetermined number of the additional micro-feature vectors is received to produce an updated SOM-ART network.
11. The computer-readable storage medium of claim 10 , wherein the operation further comprises:
determining that a micro-feature value is invalid; and
excluding the invalid micro-feature value from the updating of the SOM-ART network.
12. The computer-readable storage medium of claim 9 , wherein the operation further comprises estimating a topology for the SOM-ART network based on the number of input micro-feature vectors.
13. The computer-readable storage medium of claim 9 , wherein the operation further comprises:
receiving additional micro-feature vectors; and
processing the additional micro-feature vectors to produce a mature SOM-ART network before classifying the foreground patch.
14. A system, comprising:
a video input source configured to provide image data;
a processor; and
a memory containing a program, which, when executed on the processor is configured to perform an operation discovering object type clusters for the image data captured by the video input source, the operation comprising:
receiving a micro-feature vector including multiple micro-feature values, each micro-feature value based on at least one pixel-level characteristic of a foreground patch that depicts a foreground object;
processing the micro-feature vector by a self-organizing map adaptive resonance theory (SOM-ART) network to discover the object type clusters for the image data;
classifying the foreground object as depicting a first object type corresponding to a first object type cluster of the object type clusters when the micro-feature vector matches the first object type cluster; and
indicating that no match is found when the micro-feature vector does not correspond to any of the object type clusters for the image data.
15. The system of claim 14 , wherein the operation further comprises:
receiving additional micro-feature vectors; and
updating the SOM-ART network when a predetermined number of the additional micro-feature vectors is received to produce an updated SOM-ART network.
16. The system of claim 15 , wherein the operation further comprises:
determining that a micro-feature value is invalid; and
excluding the invalid micro-feature value from the updating of the SOM-ART network.
17. The system of claim 14 , wherein the operation further comprises comprises estimating a topology for the SOM-ART network based on the number of input micro-feature vectors.
18. The system of claim 14 , wherein the operation further comprises:
receiving additional micro-feature vectors; and
processing the additional micro-feature vectors to produce a mature SOM-ART network before classifying the foreground patch.
19. The system of claim 14 , wherein the operation further comprises:
receiving additional micro-feature vectors; and
removing the first object type cluster when none of the additional micro-feature vectors match the first object type cluster.
20. The system of claim 14 , wherein the operation further comprises adding a new object type cluster when the micro-feature vector does not correspond to any of the object type clusters for the image data.