METHOD AND DEVICE FOR ANALYZING SURROUNDING OBJECTS AND/OR SURROUNDING SCENES, SUCH AS FOR OBJECT AND SCENE CLASS SEGMENTING

• US 20110200230A1
• Filed: 09/30/2009
• Published: 08/18/2011
• Est. Priority Date: 10/10/2008
• Status: Active Grant

• Current Assignee: ADC GmbH (TE Connectivity Ltd. (United Kingdom))
• Original Assignee: ADC GmbH (TE Connectivity Ltd. (United Kingdom))
• Inventors: Wojek, Christian, Schiele, Bernt, Lüke, Stefan
• Granted Patent: US 8,934,666 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/295 Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06V 10/85 Markov-related models; Markov random fields
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

The invention relates to a method and an object detection device for analysing objects in the environment and/or scenes in the environment. The object detection device includes a data processing and/or evaluation device. In the data processing and/or evaluation device, image data (x^t) is evaluated on the basis of a Conditional Random Field (CRF) model and the CRF model provides additional object nodes (o^t_n) which take into account information from an object detector.

Claims

1-14. -14. (canceled)

15. A method for analysing objects in an environment and/or scenes in an environment with an evaluation unit, wherein in the evaluation unit image data (x^t) based on a conditional random field model is evaluated and the conditional random field model provides additional object nodes (o^t_n) which take into account information from an object detector.

17. The method according to claim 15, wherein within a scope of the analysis of objects in the environment and/or scenes in the environment, adjacent relationships (N₂, N₃) of nodes of the conditional random field model are modelled.

19. The method according to claim 17, wherein the adjacent relationships (N₂, N₃) are modelled using edge potentials.

21. The method according to claim 15, wherein within a scope of the analysis of objects in the environment and/or scenes in the environment, a support vector machine is also used for object detection and/or object classification.

23. The method according to claim 15, wherein on the basis of the conditional random field model within a scope of object detection and/or scene classification, moved cameras and/or moved objects (O) are modelled.

25. The method according to claim 15, wherein objects (O) and scenes are modelled in a shared segmentation stage, wherein the modelling is conducted at two different model layers with different information granularity and different segmentations in a dynamic conditional random field model.

27. The method according to claim 25, wherein at least one second model layer with reduced information granularity is used in order to represent object nodes (o^t_n) and to conduct the method on the basis of dynamic image sequences which contain objects (O) of any size.

29. The method according to claim 15, wherein a pixel-by-pixel object and/or scene class segmentation is conducted.

31. The method according to claim 15, wherein objects (O) of any size are integrated into a conditional random field model framework and an inference is conducted jointly for objects (O) and context and/or scene classes.

33. A method according to claim 15, wherein edge potentials are modelled by taking into account or evaluating a scale supplied by the object detector.

16. A method for analysing objects in an environment and/or scenes in an environment with an evaluation unit, wherein in the evaluation unit image data (x^t) based on a conditional random field model is evaluated, wherein a shared segmentation of object and scene classes is conducted and dynamic information is integrated within the scope of object detection and scene classification.

18. The method according to claim 16 wherein within a scope of the analysis of objects in the environment and/or scenes in the environment, adjacent relationships (N₂, N₃) of nodes of the conditional random field model are modelled.

20. The method according to claim 18, wherein the adjacent relationships (N₂, N₃) are modelled using edge potentials.

22. The method according to claim 16, wherein within a scope of the analysis of objects in the environment and/or scenes in the environment, a support vector machine is also used for object detection and/or object classification.

24. The method according to claim 16, wherein on the basis of the conditional random field model within a scope of object detection and/or scene classification, moved cameras and/or moved objects (O) are modelled.

26. The method according to claim 16, wherein objects (O) and scenes are modelled in a shared segmentation stage, wherein the modelling is conducted at two different model layers with different information granularity and different segmentations in a dynamic conditional random field model.

28. The method according to claim 26, wherein at least one second model layer with reduced information granularity is used in order to represent object nodes (o^t_n) and to conduct the method on the basis of dynamic image sequences which contain objects (O) of any size.

30. The method according to claim 16, wherein a pixel-by-pixel object and/or scene class segmentation is conducted.

32. The method according to claim 16, wherein objects (O) of any size are integrated into a conditional random field model framework and an inference is conducted jointly for objects (O) and context and/or scene classes.

34. A method according to claim 16, wherein edge potentials are modelled by taking into account or evaluating a scale supplied by an object detector.

35. An object detection device for analysing objects in an environment and/or scenes in an environment with a data processing and/or evaluation device, wherein in the data processing and/or evaluation device, image data (x^t) is evaluated on the basis of a conditional random field model and the conditional random field model provides additional object nodes (o^t_n) which take into account information from an object detector.

37. The device according to claim 35, wherein the object detection device is integrated into a camera device or into a sensor device.

36. A vehicle with an object detection device for analysing objects in an environment and/or scenes in an environment, with a data processing and/or evaluation device, wherein in the data processing and/or evaluation device, image data (x^t) is evaluated on the basis of a conditional random field model and the conditional random field model provides additional object nodes (o^t_n) which take into account information from an object detector (Ω

), with a data storage device for storing image data, which is connected in terms of data to the object detection device and/or to the data processing and/or evaluation device.

38. The vehicle according to claim 36, wherein the object detection device is integrated into a camera device or into a sensor device.