Partially occluded object detection using context and depth ordering

Patent metadata

Field	Value
Publication number	US-9805274-B2
Application number	US-201615015033-A
Country	US
Kind code	B2
Filing date	Feb 3, 2016
Priority date	Feb 3, 2016
Publication date	Oct 31, 2017
Grant date	Oct 31, 2017

Abstract

A system and method for verifying detection of partially occluded objects (e.g., pedestrians) in the vicinity of a vehicle. An image input device captures an image and/or video of surroundings. An object detector detects partially occluded pedestrians and other objects in received image information. The detection of a partially occluded pedestrian is verified when a detection window of the partially occluded pedestrian overlaps with a detection window of an occluding object, and the occluding object window is closer to the image input device than the partially occluded object window. Optionally, a range-finding sensor, such as a LIDAR device, determines a range to objects located in the direction of the partially occluded object. The detection of the partially occluded object is verified when the range of one of the other objects located in the direction of the partially occluded object is less than that of the partially occluded object.

First claim

What is claimed is:

1. A method for verifying detection of a first object partially occluded by a second object relative to a vehicle, the method comprising:
receiving image information via an image input device;
determining a first detection window bounding a first image in the image information corresponding to the first object;
determining a second detection window bounding a second image in the image information corresponding to the second object;
determining whether the first window and the second window overlap;
determining a first distance to the first detection window and a second distance to the second detection window;
comparing the first distance to the second distance, and
if the first distance is greater than the second distance, verifying that the first object is partially occluded by the second object.

2. The method of claim 1 , wherein verifying that the first object is partially occluded by the second object further includes:
receiving an input from a depth sensor, the depth sensor input corresponding to a measured distance between the depth sensor and the second object;
comparing the first distance to the measured distance; and
verifying that the first distance is greater than the measured distance.

3. The method of claim 1 , wherein the first object is a human.

4. The method of claim 1 , wherein the first object is selected from a group consisting of a human, a bicycle, a motorcycle, and an animal.

5. The method of claim 1 , wherein the image input device is a camera.

6. The method of claim 5 , wherein the camera is mounted on the vehicle.

7. The method of claim 1 , wherein determining whether the first window and the second window overlap includes:
determining whether the first image is a partial image.

8. The method of claim 7 , wherein the first image is a human, and wherein determining whether the first image is a partial image includes:
applying human recognition to at least a portion of the first image.

9. The method of claim 2 , wherein the depth sensor is selected from a group consisting of a LIDAR device, a RADAR device, and a stereo camera system.

10. A method for verifying detection of a first object partially occluded by a second object relative to a vehicle, the method comprising:
receiving image information via an image input device;
determining a first detection window bounding a first image in the image information corresponding to the first object;
determining a second detection window bounding a second image in the image information corresponding to the second object;
determining whether the first window and the second window overlap;
determining a first distance to the first detection window;
receiving an input from a depth sensor, the depth sensor input corresponding to a measured distance between the depth sensor and the second object;
comparing the first distance to the measured distance; and
if the first distance is greater than the measured distance, verifying that the first object is partially occluded by the second object.

11. A system for verifying detection of a first object partially occluded by a second object relative to a vehicle, the system comprising:
an image input device for receiving image information;
an object detector to determine a first detection window bounding a first image in the image information corresponding to the first object, and a second detection window bounding a second image in the image information corresponding to the second object; and
a processor operatively connected for computer communication to the image input device and the object detector, the processor being configured to:
determine whether the first detection window and the second detection window overlap;
if the first and second detection windows overlap, determine a first distance to the first object and determine a second distance to the second object; and
if the first distance is greater than the second distance, verify that the first object is partially occluded.

12. The system of claim 11 , wherein the processor being configured to determine a first distance to the first object and determine a second distance to the second object includes:
determining a first distance to the first object using the received image information and location information for the first detection window.

13. The system of claim 12 , wherein the processor being configured to determine a first distance to the first object and determine a second distance to the second object includes:
determining a second distance to the second object using the received image information and location information for the second detection window.

14. The system of claim 12 , further comprising:
a depth sensor;
wherein the processor being configured to determine a first distance to the first object and determine a second distance to the second object includes:
receiving a depth sensor input corresponding to the distance between the depth sensor and the second object as the second distance.

15. The system of claim 11 , wherein the first object is a human.

16. The system of claim 11 , wherein the image input device is a camera.

17. The system of claim 16 , wherein the camera is mounted on the vehicle.

18. The system of claim 11 , wherein determining whether the first window and the second window overlap includes:
determining whether the first image is a partial image.

19. The system of claim 18 , wherein the first image is a human, and wherein determining whether the first image is a partial image includes:
applying human recognition to at least a portion of the first image.

20. The system of claim 14 , wherein the depth sensor is selected from a group consisting of a LIDAR device, a RADAR device, and a stereo camera system.

Assignees

• Honda Motor Co Ltd

Inventors

• Ayvaci Alper
• Heisele Bernd
• Zheng Jingjing

Classifications

• G06V10/75

  Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries · CPC title

• G06V40/10 Primary

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06V10/42

  Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation · CPC title