System and method for detecting potential drive-up drug deal activity via trajectory-based analysis

1. A computer-implemented method for automatically detecting an occurrence of an interaction event of at least one person and at least one vehicle concurrently present in a surveilled area using a video camera directed towards the surveilled area, the method comprising:

a) acquiring a video stream from the video camera, the video stream including a temporal sequence of video frames including the surveilled area within a FOV (field-of-view) associated with the video camera;

b) detecting and tracking at least one person and at least one vehicle within a common temporal sequence of video framers included in the video stream, and generating a trajectory of each person and vehicle tracked within the first common temporal sequence of video frames;

c) processing the trajectories of the tracked people and vehicles to extract one or more trajectory interaction features (TIFs) associated with the trajectories of the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames; and

d) applying predefined heuristics to the extracted TIFs to detect an interaction event associated with the predefined heuristics has occurred between the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames,

wherein the TIFs include one or more of a position, a velocity, and a relative distance associated with the at least one person and the at least one vehicle within the first common temporal sequence of video frames, and

wherein the predefined heuristics applied in step d) include the calculation of an evidence vector state, the evidence vector state calculated as a function of a velocity threshold and a proximity threshold associated with the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames.

2. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 1 ,

wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction event has occurred between the at least one person and the at least one vehicle tracked within the second common temporal sequence of video frames.

3. The computer-implemented method for automatically detecting the interaction of at least one person and at least one vehicle according to claim 2 , further comprising:

e) collecting evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with the each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

4. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 3 , further comprising:

f) communicating an alert to an operatively associated central system, the alert indicating one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

5. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 1 , wherein the interaction event is an illegal drug deal between at least one person and at least one vehicle.

6. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 5 , wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction event has occurred between at least one person and at least one vehicle of the at least one person and the at least one vehicle tracked within the second common temporal sequence of video frames.

7. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 6 , further comprising:

e) collecting evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with the each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

8. The computer-implemented method for automatically detecting the interaction event of at least one person and at least one vehicle according to claim 7 , further comprising:

f) communicating an alert to an operatively associated central system, the alert indicating one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

9. A video system for automatically detecting an occurrence of an interaction event of at least one person and at least one vehicle concurrently present in a surveilled area comprising:

a video camera with an associated FOV (field-of-view) directed towards the surveilled area; and

a video processing system operatively connected to the video camera, the video processing system configured to:

a) acquire a video stream from the video camera, the video stream including a temporal sequence of video frames including the surveilled area within the FOV associated with the video camera;

b) detect and track at least one person and at least one vehicle within a first common temporal sequence of video frames included in the video stream, and generate a trajectory of each person and each vehicle tracked within the first common temporal sequence of video frames;

c) process the trajectories of the tracked people and vehicles to extract one or more trajectory interaction features (TIFs) associated with the trajectories of the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames; and

d) apply predefined heuristics to the extracted TIFs to detect an interaction event has occurred between the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames,

wherein the TIFs include one or more of a position, a velocity, and a relative distance associated with the at least one person and the at least one vehicle within the first common temporal sequence of video frames, and

wherein the predefined heuristics applied in step d) include the calculation of an evidence vector state, the evidence vector state calculated as a function of a velocity threshold and a proximity threshold associated with the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames.

10. The video system for automatically detecting the occurrence of an interaction event according to claim 9 , wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction event has occurred between at least one person and at least one vehicle of the at least one person and the at least one vehicle tracked within the second common temporal sequence of video frames.

11. The video system for automatically detecting the occurrence of an interaction event according to claim 10 , further comprising the video processing system configured to:

e) collect evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with the each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

12. The video system for automatically detecting the occurrence of an interaction event according to claim 11 , further comprising the video processing system configured to:

f) communicate an alert to an operatively associated central system, the alert indicating one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

13. The video system for automatically detecting the occurrence of an interaction event according to claim 9 , wherein the interaction event is an illegal drug deal between at least one person and at least one vehicle.

14. The video system for automatically detecting the occurrence of an interaction event according to claim 13 , wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction event has occurred between at least one person and at least one vehicle of the at least one person and the at least one vehicle tracked within the second common temporal sequence of video frames.

15. The video system for automatically detecting the occurrence of an interaction event according to claim 14 , further comprising the video processing system configured to:

e) collect evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with the each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

16. The video system for automatically detecting the occurrence of an interaction event according to claim 15 , further comprising the video system configured to:

f) communicate an alert to an operatively associated central system, the alert indicating one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each person of the at least one person and each vehicle of the at least one vehicle detected within the first and second common temporal sequence of video frames.

17. A video system for automatically detecting an occurrence of an interaction event of two or more objects concurrently present in a surveilled area, the interaction event associated with an illegal drug deal between the two or more objects, comprising:

a video camera with an associated FOV (field-of-view) directed towards the surveilled area; and

a video processing system operatively connected to the video camera, the video processing system configured to:

a) acquire a video stream from the video camera, the video stream including a temporal sequence of video frames including the surveilled area within the FOV associated with the video camera;

b) detect and track the two or more objects within a first common temporal sequence of video frames included in the video stream, and generate a trajectory of each object tracked within the first common temporal sequence of video frames;

c) process the trajectories of the tracked objects to extract one or more trajectory interaction features (TIFs) associated with the trajectories of the two or more objects tracked within the first common temporal sequence of video frames, the TIFs including one or more of a position, a velocity, and a relative distance associated with the two or more objects within the first common temporal sequence of video frames; and

d) apply predefined heuristics to the extracted TIFs to detect an interaction event has occurred between at least two objects of the two or more objects tracked within the first common temporal sequence of video frames, the predefined heuristics including a velocity threshold and a proximity threshold associated with the two or more objects tracked within the first common temporal sequence of video frames,

wherein the TIFs include one or more of a position, a velocity, and a relative distance associated with the at least one person and the at least one vehicle within the first common temporal sequence of video frames,

wherein the predefined heuristics applied in step d) include the calculation of an evidence vector state, the evidence vector state calculated as a function of a velocity threshold and a proximity threshold associated with the at least one person and the at least one vehicle tracked within the first common temporal sequence of video frames, and

wherein steps b)-d) are repeated for a second common temporal sequence of video frames, distinct from the first common temporal sequence of video frames, to determine if the interaction even has occurred between at least two objects of the two or more objects tracked within the second common temporal sequence of video frames.

18. A video system for automatically detecting an occurrence of an interaction event according to claim 17 , further comprising the video system configured to:

e) collect evidence of the detected interaction events in step d), the evidence including one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each of the two or more objects detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each of the two or more objects detected within the first and second common temporal sequence of video frames.

19. A video system for automatically detecting an occurrence of an interaction event according to claim 18 , further comprising:

a central processing system operatively associated with the video processing system, wherein the video processing system is configured to:

f) communicate an alert to an operatively associated central system, the alert indicating one or more of the number of occurrences of the detected interaction event, the number of occurrences of the detected interaction event associated with each of the two or more objects detected within the first and second common temporal sequence of video frames, a time duration and start/end time associated with each detected interaction event, a calculated probability of the occurrence of the interaction event, and an indication of static or dynamic movement associated with each of the two or more objects detected within the first and second common temporal sequence of video frames.