Method, device, and computer-readable medium of object detection

• US 8,401,232 B2
• Filed: 04/27/2011
• Issued: 03/19/2013
• Est. Priority Date: 05/07/2010
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Yi, Hong, Deng, Yu, Wang, Xin, Fan, Shengyin
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): Azima, Shaghayegh
• Application Number:
  US13/095,128
• Publication Number:
  US 20110274315A1
• Time in Patent Office: 692 Days
• Field of Search: 382/103, 600/458, 600/407, 348/354, 348/169
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/215 Motion-based segmentation
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

Disclosed are an object detection method and an object detection device. The object detection method comprises a step of obtaining plural detection results of a current frame according to plural object detection methods; a step of setting initial probabilities of the plural detection results of the current frame; a step of calculating a movement frequency distribution diagram representing movement frequencies of respective pixels in the current frame; a step of obtaining detection results of a previous frame; a step of updating the probabilities of the plural detection results of the current frame; and a step of determining a final list of detected objects based on the updated probabilities of the plural detection results of the current frame.

Claims

1. An object detection method of detecting one or more predetermined objects in a video, comprising:

a step of obtaining plural kinds of detection results acquired by detecting the entireties or parts of the predetermined objects in a current frame according to plural kinds of object detection methods;

a step of setting, based on predetermined detection accuracies corresponding to the plural kinds of object detection methods, initial probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods;

a step of calculating, based on detection results of one or more moving objects in plural frames including the current frame, a movement frequency distribution diagram representing movement frequencies of respective pixels in the current frame;

a step of filtering objects detected in a previous frame of the current frame based on the movement frequency distribution diagram so as to obtain filtered detection results of the previous frame;

a step of updating, based on overlaps of the plural kinds of detection results of the current frame and the filtered detection results of the previous frame, the probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods; and

a step of determining a final list of detected objects based on the updated probabilities of the plural kinds of detection results of the current frame.

2. The object detection method according to claim 1, further comprising:

a step of updating the probabilities of the plural kinds of detection results of the current frame based on overlaps of the plural kinds of detection results themselves of the current frame.

3. The object detection method according to claim 2, wherein:

the step, of updating the probabilities of the plural kinds of detection results of the current frame based on overlaps of the plural kinds of detection results of the current frame, includes;

a step of determining whether a predetermined number of detection results overlap by comparing an overlap ratio of regions corresponding to the predetermined number of detection results with a predetermined threshold value, wherein, if the predetermined number of detection results overlap, then a probability of each of the predetermined number of detection results is updated based on a predetermined detection accuracy corresponding to the overlap of the predetermined number of detection results.

4. The object detection method according to claim 1, further comprising:

a step of removing at least one object causing noise in the plural kinds of detection results of the current frame or the final list of detected objects based on a noise removing rule defined according to an application.

5. The object detection method according to claim 1, wherein:

the predetermined detection accuracies corresponding to the plural detection methods, predetermined detection accuracies corresponding to overlaps of the plural detection results of the plural detection methods and the detection results of the previous frame are stored in a knowledge database in advance, and the knowledge database is obtained by statistics calculation.

6. The object detection method according to claim 1, wherein:

the step of calculating, based on detection results of one or more moving objects in plural frames including the current frame, a movement frequency distribution diagram representing movement frequencies of respective pixels in the current frame includes;

a step of calculating, based on the detection results of the moving objects in the plural frames, the number of times of the respective pixels belonging to the moving objects in a predetermined continuous time period until a current time point, and then obtaining the movement frequency distribution diagram by dividing the number of times of the respective pixels belonging to the moving objects by the number of the plural frames.

7. The object detection method according to claim 6, wherein:

the step, of filtering objects detected in a previous frame of the current frame based on the movement frequency distribution diagram so as to obtain filtered detection results of the previous frame, includes;

a step of calculating the sum of movement frequencies of a region of an object detected in the previous frame;

a step of normalizing the sum of movement frequencies of the region of the object; and

a step of retaining the object if the normalized sum is less than or equal to a predetermined threshold value, otherwise removing the object from the objects detected from the previous frame.

8. The object detection method according to claim 1, wherein:

the step of updating, based on overlaps of the plural kinds of detection results of the current frame and the filtered detection results of the previous frame, the probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods includes;

a step of determining whether there are overlaps between respective detection results of a kind of detection result and the filtered detection results of the previous frame, wherein, if overlaps exist, then the probabilities of the respective detection results of this kind of detection result is updated based on a predetermined detection accuracy corresponding to the overlap.

9. The object detection method according to claim 1, wherein:

the step, of determining a final list of detected objects based on the updated probabilities of the plural kinds of detection results of the current frame, includes;

a step of generating a random number in a range of 0 to 1 by a random number generating unit;

a step of comparing the probability of each detection result of the plural kinds of detection results with the random number, a predetermined first threshold value, and a predetermined second threshold value less than the predetermined first threshold value; and

a step of retaining the detection result if the probability of the detection result is greater than the predetermined first threshold value, or is greater than the second threshold value and the random number, otherwise removing the detection result.

10. An object detection device for detecting one or more predetermined objects in a video, comprising:

a detection result obtaining device for obtaining plural kinds of detection results acquired by detecting the entireties or parts of the predetermined objects in a current frame according to plural kinds of object detection methods;

an initial probability setting device for setting, based on predetermined detection accuracies corresponding to the plural kinds of object detection methods, initial probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods;

a movement frequency distribution diagram calculating device for calculating, based on detection results of one or more moving objects in plural frames including the current frame, a movement frequency distribution diagram representing movement frequencies of respective pixels in the current frame;

a previous detection result filtering device for filtering objects detected in a previous frame of the current frame based on the movement frequency distribution diagram so as to obtain filtered detection results of the previous frame;

a probability updating device for updating, based on overlaps of the plural kinds of detection results of the current frame and the filtered detection results of the previous frame, the probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods; and

an object list determining device for determining a final list of detected objects based on the updated probabilities of the plural kinds of detection results of the current frame.

11. A non-transitory computer-readable medium having machine-executable instructions for execution by a processing system, wherein, the machine-executable instructions are used for carrying out an object detection method of detecting one or more predetermined objects in a video, and the machine-executable instructions, when executed, cause the processing system to carry out:

a step of obtaining plural kinds of detection results acquired by detecting the entireties or parts of the predetermined objects in a current frame according to plural kinds of object detection methods;

a step of setting, based on predetermined detection accuracies corresponding to the plural kinds of object detection methods, initial probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods;

a step of calculating, based on detection results of one or more moving objects in plural frames including the current frame, a movement frequency distribution diagram representing movement frequencies of respective pixels in the current frame;

a step of filtering objects detected in a previous frame of the current frame based on the movement frequency distribution diagram so as to obtain filtered detection results of the previous frame;

a step of updating, based on overlaps of the plural kinds of detection results of the current frame and the filtered detection results of the previous frame, the probabilities of the plural kinds of detection results of the current frame corresponding to the plural kinds of object detection methods; and

a step of determining a final list of detected objects based on the updated probabilities of the plural kinds of detection results of the current frame.