Method for detecting a person in a space

• US 7,295,123 B2
• Filed: 02/14/2003
• Issued: 11/13/2007
• Est. Priority Date: 06/13/2002
• Status: Expired due to Fees

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Abraham, Steffen, Freienstein, Heiko, Trinh, Hoang, Bothe, Hans-Dieter, Engelberg, Thomas
• Primary Examiner(s): TRIEU, VAN THANH
• Application Number:
  US10/517,746
• Publication Number:
  US 20060062472A1
• Time in Patent Office: 1,733 Days
• Field of Search: 340/575, 340/576, 340/545.1, 340/545.2, 340/573.1, 382/117, 382/118, 382/104, 382/106, 701/45, 701/46, 701/49, 348/143, 348/148
• US Class Current: 340/576
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

A method for detecting a person in a space includes at least one depth sensor producing spatial data about the space to be monitored, at least one sub-model, which is sub-dividable into further sub-models being used for at least one selected body part of a human, the spatial data being used to adapt the sub-models, the adaptation being checked by position parameters between the sub-models of different body parts, and the person being recognized using a complete model made up of the checked sub-models.

Claims

1. A method for detecting a person in a space, comprising:

producing spatial data about the space to be monitored via at least one depth sensor;

using at least one sub-model which is subdividable into further sub-models for at least one selected body part of a human, wherein the at least one sub-model is selected from a hierarchically-structured model data set including different sub-models for the at least one selected body part;

adapting the sub-models using the spatial data, wherein the adaptation is checked by position parameters between the sub-models of different body parts; and

recognizing the person using a complete model made up of checked sub-models.

2. The method of claim 1, wherein the complete model is adapted to track the persons over time by further adapting the sub-models using the data at predetermined intervals.

3. The method of claim 1, wherein the at least one selected body part is the head of a human.

4. The method of claim 1, wherein the at least one selected body part is the shoulder.

5. The method of claim 1, wherein intensity information from the spatial data is used.

6. The method of claim 1, wherein at least part of the complete model is transmitted for occupant classification to a restraint system in a vehicle in which a person is located.

7. The method of claim 1, wherein the complete model is used in an anti-pinch protection.

8. The method of claim 1, wherein the depth sensor has at least one image pickup.

9. The method of claim 8, wherein the at least one image pickup includes a video sensor.

10. The method of claim 1, further comprising:

controlling convenience features in a vehicle.