System and method for identification and suppression of time varying background objects
A system and method for identification and suppression of time varying background objects is disclosed. A proposed surveillance security system includes an image analytics system and at least one surveillance camera. The image analytics system identifies objects within image data of a scene captured by the surveillance camera, and then analyzes the objects to determine whether each object is a foreground object or a dynamic background object. In examples, the image analytics system determines whether an object is a foreground object or a dynamic background object based upon movement and/or an appearance of the object. The surveillance security system does not send alerts to users of the system for objects determined to be dynamic background objects. When users request objects of interest, the dynamic background objects are also excluded from lists of objects sent in reply messages to the users.
1. A surveillance security system, comprising:
a plurality of surveillance cameras for generating image data of a scene; and
an image analytics system comprising an object tracking system for identifying objects within the image data and an object analysis system for analyzing the objects to determine whether the objects are dynamic background objects or foreground objects based upon appearances of each of the objects by matching color and edge information for each of the objects against that of static portions of the scene.
2. The system of claim 1 , wherein the image analytics system determines whether the objects are dynamic background objects or foreground objects based upon movement of each of the objects.
3. The system of claim 1 , wherein the image analytics system initially classifies the objects as dynamic background objects, and reclassifies the dynamic background objects as foreground objects upon determining that the objects are foreground objects.
4. The system of claim 1 , wherein in response to requests from user devices for the objects, the analytics system excludes the dynamic background objects from lists of objects sent in reply messages to the user devices.
5. The system of claim 1 , wherein the image analytics system includes an object tracking system that creates bounding boxes for the objects, the objects including both dynamic background objects and foreground objects.
6. The system of claim 1 , wherein the image analytics system determines whether the objects are dynamic background objects or foreground objects by:
tracking positions of the objects within the scene over time and storing position observations for the positions of the objects; and
for each of the objects, concluding that the objects are dynamic background objects when a count of the position observations has not met a threshold number of position observations.
7. The system of claim 1 , wherein the image analytics system determines whether the objects are dynamic background objects or foreground objects by:
tracking positions of the objects within the scene over time and storing position observations for the positions of the objects; and
for each of the objects, determining distances between position observations and concluding whether the objects are dynamic background objects or foreground objects based on the distances.
8. The system of claim 1 , wherein the image analytics system is included within the plurality of surveillance cameras.
9. The system of claim 1 , wherein the image analytics system determines whether the objects are foreground objects based upon appearances of each of the objects by:
comparing an appearance of the objects relative to static portions of the scene, and storing appearance match results for the appearances of the objects; and
for each of the objects, comparing time intervals between the appearance match results and concluding whether the objects are dynamic background objects or foreground objects based on the time intervals.
10. A method for a surveillance security system, the method comprising:
a plurality of surveillance cameras generating image data of a scene; and
an object tracking system of an image analytics system identifying objects within the image data; and
an object analysis system of the image analytics system analyzing the objects to determine whether the objects are dynamic background objects or foreground objects based upon appearances of each of the objects by matching color and edge information for each of the objects against that of static portions of the scene.
11. The method of claim 10 , further comprising the image analytics system determining whether the objects are dynamic background objects or foreground objects based upon movement of each of the objects.
12. The method of claim 10 , further comprising the image analytics system initially classifying the objects as dynamic background objects, and reclassifying the dynamic background objects as foreground objects upon determining that the objects are foreground objects.
13. The method of claim 10 , further comprising the analytics system excluding the dynamic background objects from lists of objects sent in reply messages to the user devices, in response to receiving requests from user devices for the objects.
14. The method of claim 10 , further comprising creating bounding boxes for the objects, the objects including both dynamic background objects and foreground objects.
15. The method of claim 10 , further comprising the image analytics system determining whether the objects are dynamic background objects or foreground objects by:
tracking positions of the objects within the scene over time and storing position observations for the positions of the objects; and
for each of the objects, concluding whether the objects are dynamic background objects when a count of the position observations has not met a threshold number of position observations.
16. The method of claim 10 , further comprising the image analytics system determining whether the objects are dynamic background objects or foreground objects by:
tracking positions of the objects within the scene over time and storing position observations for the positions of the objects; and
for each of the objects, determining distances between position observations and concluding whether the objects are dynamic background objects or foreground objects based on the distances.
17. The method of claim 10 , further comprising the image analytics system determining whether the objects are foreground objects based upon appearances of each of the objects by
comparing an appearance of the objects relative to static portions of the scene, and storing appearance match results for the appearances of the objects; and
for each of the objects, comparing time intervals between the appearance match results and concluding whether the objects are dynamic background objects or foreground objects based on the time intervals.