Video surveillance system in which trajectory hypothesis spawning allows for trajectory splitting and/or merging

• US 7,148,912 B2
• Filed: 08/12/2004
• Issued: 12/12/2006
• Est. Priority Date: 11/17/2003
• Status: Active Grant

• Current Assignee: Axis AB (Canon Inc.)
• Original Assignee: Vidient Systems, Inc. (Agilence Incorporated)
• Inventors: Gong, Yihong, Han, Mei, Tao, Hai
• Primary Examiner(s): Dastouri, Mehrdad
• Assistant Examiner(s): CZEKAJ, DAVID J
• Application Number:
  US10/917,201
• Publication Number:
  US 20050104961A1
• Time in Patent Office: 852 Days
• Field of Search: 348/143, 348/135, 348/155
• US Class Current: 348/143
• CPC Class Codes: G08B 13/19604 involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19615 wherein said pattern is defined by the user
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Abstract

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

Claims

1. A method for use in a video surveillance system, the method comprising

generating first and second extended hypotheses comprising respective different sets of hypothesized trajectories of particular objects hypothesized to have been moving through an area under surveillance at a previous time, the first and second extended hypotheses being at least one of a) an hypothesis with a merge and an hypothesis without the merge and b) an hypothesis with a split and an hypothesis without the split, the merge comprising at least two trajectories extended to the same one object and the split comprising a trajectory extended to at least two objects,

generating a first further extended hypothesis comprising a first set of hypothesized trajectories of objects hypothesized to have been moving through the area under surveillance at a present time that is subsequent to the previous time, the trajectories of the first further extended hypothesis comprising 1) at least ones of the trajectories of the first extended hypothesis, 2) one or more of the objects hypothesized to have been moving through the area under surveillance at the present time, and 3) a particular set of connections extending at least ones of the trajectories of the first extended hypothesis to at least ones of the objects hypothesized to have been moving through an area under surveillance at the present time,

generating a second further extended hypothesis comprising a second set of hypothesized trajectories of the objects hypothesized to have been moving through the area under surveillance at the present time, the trajectories of the second further extended hypothesis comprising 1) at least ones of the trajectories of the second extended hypothesis, 2) one or more of the objects hypothesized to have been moving through the area under surveillance at the present time, and 3) a particular set of connections extending at least ones of the trajectories of the second extended hypothesis to at least ones of the objects hypothesized to have been moving through the area under surveillance at the present time,

generating a third further extended hypothesis comprising a third set of hypothesized trajectories of objects hypothesized to have been moving through the area under surveillance at the present time, the trajectories of the third further extended hypothesis comprising 1) at least ones of the trajectories of the first extended hypothesis, 2) one or more of the objects hypothesized to have been moving through the area under surveillance at the present time, and 3) a particular set of connections extending at least ones of the trajectories of the first extended hypothesis to at least ones of the objects hypothesized to have been moving through an area under surveillance at the present time, the third further extended hypothesis being different from the first further extended hypothesis, and

generating a fourth further extended hypothesis comprising a fourth set of hypothesized trajectories of respective ones of the objects hypothesized to have been moving through the area under surveillance at the present time, the trajectories of the fourth further extended hypothesis comprising 1) at least ones of the trajectories of the second extended hypothesis, 2) one or more of the objects hypothesized to have been moving through the area under surveillance at the present time, and 3) a particular set of connections extending at least ones of the trajectories of the second extended hypothesis to at least ones of the objects hypothesized to have been moving through the area under surveillance at the present time, the fourth further extended hypothesis being different from the second further extended hypothesis.

2. The invention of claim 1 further comprising identifying one of the first, second, third and fourth further extended hypotheses as being more likely than the others to represent the actual trajectories of the actual objects moving through the area under surveillance at the present time.

3. The method of claim 2 wherein the identifying includes computing likelihoods each associated with a respective one of the first, second, third and fourth further extended hypotheses, each likelihood being a function of connection probabilities each associated with a respective trajectory of the associated further extended hypothesis, each connection probability being a measure of the probability that an object that terminates the associated trajectory is, in fact, an object in the area under surveillance that is on that trajectory.

4. The method of claim 3 wherein said one of the first, second, third and fourth further extended hypotheses has a larger associated likelihood than the others.

5. A video surveillance system adapted to carry out the method of claim 1.

6. A computer-readable medium on which are stored computer programs that are executable by a computer to carry out the method of claim 1.

7. A video surveillance system adapted to carry out the method of claim 2.

8. A computer-readable medium on which are stored computer programs that are executable by a computer to carry out the method of claim 2.