SURVEILLANCE SYSTEM AND OPERATION METHOD THEREOF

• US 20170353699A1
• Filed: 05/30/2017
• Published: 12/07/2017
• Est. Priority Date: 06/01/2016
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: PixArt Imaging Incorporated
• Inventors: WANG, GUO-ZHEN
• Granted Patent: US 10,757,377 B2
• Time in Patent Office: Days
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19695 Arrangements wherein non-video detectors start video recording or forwarding but do not generate an alarm themselves
• CPC Class Codes: H04N 23/651 for reducing power consumption by affecting camera operations, e.g. sleep mode, hibernation mode or power off of selective parts of the camera
• CPC Class Codes: H04N 23/667 Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

The disclosure is related to a surveillance system and an operation method thereof. The surveillance system includes an auxiliary sensor module that is in full-time operation, and a main sensor module that is in a power-saving mode at a normal state. The main sensor is in operation only if the signals generated by the auxiliary sensor module meet a criterion of surveillance. The surveillance system can reduce power consumption since the more powerful main sensor module stays in the power-saving mode without actuation. The surveillance system can process the surveillance data generated by the auxiliary sensor module since it adopts the steps of ROI detection, feature extraction, and object recognition in an early stage of a whole surveillance process.

Claims

1. A surveillance system, comprising:

an auxiliary sensor module that is in full-time operation and that outputs sensed signals from a scene;

a motion-detection engine that detects a movement in the scene based on the sensed signals;

an object-detection engine that detects an object in the scene based on the movement to be detected by the motion-detection engine; and

a main sensor module that is in a power-saving mode when there is no object to be detected in the scene, and that is activated to perform a surveillance function when the object is detected by the object-detection engine.

2. The system as recited in claim 1, wherein the auxiliary sensor module includes a motion detector and/or an image sensor, and an auxiliary processor.

3. The system as recited in claim 2, wherein the image sensor of the auxiliary sensor module is a low-resolution image sensor.

4. The system as recited in claim 1, wherein the motion-detection engine or the object-detection engine is implemented by hardware or a series of software instructions executed by a processor of the surveillance system.

5. The system as recited in claim 4, wherein the motion-detection engine is to initially detect whether or not any object enters the scene;

and the object-detection engine is to find a moving object in the scene based on the movement information generated by the motion-detection engine.

6. The system as recited in claim 4, wherein the object-detection engine includes:

an ROI detector, used to determine an ROI based on images captured by an image sensor of the auxiliary sensor module;

a feature extractor, used to extract features in the ROI based on the images; and

an object recognizer, used to recognize the object in the scene according to the features extracted from the images;

wherein, via an output, the object-detection engine outputs the recognized object in the scene for activating the main sensor module.

7. The system as recited in claim 1, wherein the main sensor module includes a main sensor and a main processor.

8. The system as recited in claim 7, wherein the main sensor is a high-resolution image sensor;

and the main processor is an image processor.

9. An operation method of a surveillance system, comprising:

detecting a movement in a scene based on signals sensed by an auxiliary sensor module which is in full-time operation;

detecting an object in the scene based on the movement to be detected; and

activating a main sensor module from a power-saving mode for performing surveillance function when the object is detected, in which the main sensor module is in the power-saving mode when there is no object to be detected in the scene.

10. The method as recited in claim 9, wherein the auxiliary sensor module includes a low-resolution image sensor that captures low-resolution images of the scene.

11. The method as recited in claim 10, wherein the auxiliary sensor module enters a power-saving mode when the main sensor module has been activated.

12. The method as recited in claim 10, wherein the step of detecting the object in the scene further includes:

determining an ROI based on the low-resolution images;

extracting features in the ROI based on the images;

recognizing the object in the scene according to the features extracted from images; and

outputting the recognized object in the scene for activating the main sensor module.

13. The method as recited in claim 12, wherein the ROI is determined according to a determination of a location of the object.

14. The method as recited in claim 13, wherein a size and/or coverage of the ROI is determined based on image information related to the object.

15. The method as recited in claim 14, wherein the ROI is an upper-half region of the scene if the object is a distant object;

and the ROI is a lower-half region of the scene if the object is a near object.

16. The method as recited in claim 9, wherein the step for detecting the movement in the scene is implemented by hardware or a series of software instructions executed by a processor of the surveillance system, and is to detect whether or not any object enters the scene and to find a moving object in the scene.

17. The method as recited in claim 9, wherein the main sensor module includes a high-resolution image sensor that captures high-resolution images of the scene.