Detecting and localizing multiple objects in images using probabilistic inference

Patent metadata

Field	Value
Publication number	US-8953888-B2
Application number	US-201113024933-A
Country	US
Kind code	B2
Filing date	Feb 10, 2011
Priority date	Feb 10, 2011
Publication date	Feb 10, 2015
Grant date	Feb 10, 2015

Abstract

An object detection system is disclosed herein. The object detection system allows detection of one or more objects of interest using a probabilistic model. The probabilistic model may include voting elements usable to determine which hypotheses for locations of objects are probabilistically valid. The object detection system may apply an optimization algorithm such as a simple greedy algorithm to find hypotheses that optimize or maximize a posterior probability or log-posterior of the probabilistic model or a hypothesis receiving a maximal probabilistic vote from the voting elements in a respective iteration of the algorithm. Locations of detected objects may then be ascertained based on the found hypotheses.

First claim

What is claimed is:

1. A computer-implemented method comprising:
under control of one or more processors configured with executable instructions:
receiving an image including an unknown number of objects to be detected;
obtaining a plurality of voting elements from the image, the plurality of voting elements placing votes on one or more hypotheses to determine one or more locations of one or more objects in the image;
deriving a probabilistic model based at least on the plurality of voting elements; and
ascertaining locations of a plurality of objects in the image based at least in part on the probabilistic model, the probabilistic model including a penalty factor to discourage hallucinated object detection by penalizing a number of hypotheses used to explain the unknown number of objects in the image, wherein the penalty factor increases as the number of hypotheses used to explain the unknown number of objects in the image increases.

2. The computer-implemented method as recited in claim 1 , wherein the plurality of voting elements include a plurality of descriptors, the plurality of descriptors usable in determining votes on a plurality of hypotheses for the locations of the plurality of objects.

3. The computer-implemented method as recited in claim 2 , wherein the plurality of descriptors include local image appearances and/or geometric positions of the plurality of voting elements.

4. The computer-implemented method as recited in claim 1 , wherein the plurality of voting elements include a plurality of descriptors, and ascertaining the locations of the plurality of objects further include traversing the plurality of voting elements through a Hough forest including a plurality of trees based on the plurality of descriptors.

5. The computer-implemented method as recited in claim 4 , wherein traversing the plurality of voting elements includes traversing the plurality of voting elements to one or more leaf nodes of the plurality of trees, each leaf node including one or more class labels and one or more offset vectors defining positions of class objects corresponding to the one or more class labels.

6. The computer-implemented method as recited in claim 4 , wherein ascertaining the locations of the plurality of objects further includes obtaining probabilistic votes from one or more leaf nodes of the plurality of trees reached by the plurality of voting elements.

7. The computer-implemented method as recited in claim 4 , wherein ascertaining the locations of the plurality of objects in the image is further based on a greedy algorithm that maximizes a joint probability of a plurality of hypotheses for the locations of the plurality of objects, the greedy algorithm iteratively increasing a total probability that is based on probabilistic votes obtained from one or more leaf nodes of the plurality of trees for the plurality of hypotheses for the locations of the plurality of objects.

8. The computer-implemented method as recited in claim 1 , wherein obtaining the plurality of voting elements includes dividing the image into a predetermined number of image segments and assigning information of each image segment to each voting element.

9. The computer-implemented method as recited in claim 8 , wherein the image segments include edge pixels, interest points, image patches and/or image regions.

10. The computer-implemented method as recited in claim 1 , wherein ascertaining the locations of the plurality of objects in the image is further based on a greedy algorithm that maximizes a joint probability of a plurality of hypotheses for the locations of the plurality of objects, and the plurality of hypotheses for the locations of the plurality of objects minimize likelihoods of the plurality of voting elements from voting on a hypothesis for a location of an object other than the plurality of objects.

11. The computer-implemented method as recited in claim 1 , wherein the penalty factor includes an Occam razor or a Minimum Description Length (MDL) penalty factor.

12. One or more computer storage media storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:
receiving an image including an unknown number of objects to be detected;
obtaining a plurality of voting elements from the image, the plurality of voting elements placing votes on one or more hypotheses to determine one or more locations of one or more objects in the image;
deriving a probabilistic model based at least on the plurality of voting elements; and
ascertaining locations of a plurality of objects in the image based at least in part on the probabilistic model, the probabilistic model including a penalty factor to discourage hallucinated object detection by penalizing a number of hypotheses used to explain the unknown number of objects in the image, wherein the penalty factor increases as the number of hypotheses used to explain the unknown number of objects in the image increases.

13. The one or more computer storage media as recited in claim 12 , wherein the plurality of voting elements include a plurality of descriptors, the plurality of descriptors usable in determining votes on a plurality of hypotheses for the locations of the plurality of objects.

14. The one or more computer storage media as recited in claim 13 , wherein the plurality of descriptors include local image appearances and/or geometric positions of the plurality of voting elements.

15. The one or more computer storage media as recited in claim 12 , wherein the plurality of voting elements include a plurality of descriptors, and ascertaining the locations of the plurality of objects further include traversing the plurality of voting elements through a Hough forest including a plurality of trees based on the plurality of descriptors.

16. The one or more computer storage media as recited in claim 12 , wherein obtaining the plurality of voting elements includes dividing the image into a predetermined number of image segments and assigning information of each image segment to each voting element.

17. A system comprising:
one or more processors;
memory storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
receiving an image including an unknown number of objects to be detected;
obtaining a plurality of voting elements from the image, the plurality of voting elements placing votes on one or more hypotheses to determine one or more locations of one or more objects in the image;
deriving a probabilistic model based at least on the plurality of voting elements; and
ascertaining locations of a plurality of objects in the image based at least in part on the probabilistic model, the probabilistic model including a penalty factor to discourage hallucinated object detection by penalizing a number of hypotheses used to explain the unknown number of objects in the image, wherein the penalty factor increases as the number of hypotheses used to explain the unknown number of objects in the image increases.

18. The system as recited in claim 17 , wherein the plurality of voting elements include a plurality of descriptors, the plurality of descriptors usable in determining votes on a plurality of hypotheses for the locations of the plurality of objects.

19. The system as recited in claim 18 , wherein the plurality of descriptors include local image appearances and/or geometric positions of the plurality of voting elements.

20. The system as

Assignees

• Kohli Pushmeet
• Lempitsky Victor
• Barinova Olga
• Microsoft Corp

Inventors

• Kohli Pushmeet
• Lempitsky Victor
• Barinova Olga

Classifications

• G06V10/757

  Matching configurations of points or features · CPC title

• G06K9/6211

  Physics · mapped topic

• G06K9/00369 Primary

  Physics · mapped topic

• G06V40/103 Primary

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title