Abstract: At least one processor inputs trajectories of moving bodies in a tracking region. The at least one processor generates a score corresponding to each of the identification information, the score indicating a likelihood that the moving bodies corresponding to the identification information present in the area. The at least one processor determines an area with a high density of the moving bodies that a density of the moving bodies is a predetermined value or higher. The at least one processor associate, based on the score, a set of moving bodies and a set of identification information of the moving bodies. The at least one processor controls a display to display, for the area with the high density of the moving bodies, the set of moving bodies and the set of identification information in association with the score.

Abstract: Even when lacking an accurate association between the trajectory and identification of a moving body, the association between trajectory and identification of the moving body is estimated and the ambiguity quantified. An identification information association unit associates an individual trajectory link included in a trajectory link candidate with likely moving body identification information per trajectory link candidate. An association trend quantification unit quantifies a trend of the number of times when trajectory information is associated with moving body identification information per individual moving body identification information for individual trajectory information based on an association result between a trajectory link and moving body identification information.

Abstract: At least one processor inputs a trajectory of a moving body in a tracking region. The at least one processor acquires information of an attribute with user-designated. The at least one processor displays a map of the tracking region, the map indicating a possibility that a moving body having the user-designated attribute is present in each area of the tracking region.

Abstract: At least one processor inputs trajectories of moving bodies in a tracking region. The at least one processor generates a score corresponding to each of the identification information, the score indicating a likelihood that the moving bodies corresponding to the identification information present in the area. The at least one processor determines an area with a high density of the moving bodies that a density of the moving bodies is a predetermined value or higher. The at least one processor associate, based on the score, a set of moving bodies and a set of identification information of the moving bodies. The at least one processor controls a display to display, for the area with the high density of the moving bodies, the set of moving bodies and the set of identification information in association with the score.

Abstract: There is provided a flow line detection process data distribution system which can distribute data detected from a mobile body to precisely perform flow line detection when flow line detection is realized by distribution processing. An area processing means 92 calculates for each combination which is a combination of unit areas used as constituent units of divided areas upon determination of the divided areas obtained by dividing the predetermined area and which is obtained by combining two different unit areas a degree of correlation which indicates a degree that sensor data related to an identical mobile body is detected, and determines the divided areas obtained by dividing the predetermined area based on the calculated degree of correlation. A data distribution means 93 classifies the sensor data stored in the data storage means 91 depending on in which divided area the sensor data is detected, and outputs the classified sensor data to different flow line detection process units.

Abstract: There is provided a mobile body track identification system that determines which mobile body matches which detected track with a high precision irrespective of frequent interruption of tracks of a mobile body detected in a tracking area. Herein, hypotheses are generated by use of sets of track-coupling candidate/identification pairs, which combines track-coupling candidates, combining tracks of a mobile body detected in a predetermined time in the past, and identifications of the mobile body and which satisfies a predetermined condition. Next, identification likelihoods are calculated as likelihoods of detecting identifications in connection with tracks indicated by track-coupling candidates included in track-coupling candidate/identification pairs ascribed to each of the selected hypotheses. Identification likelihoods are integrated per each track-coupling candidate/identification pair, thus calculating an identification likelihood regarding the selected hypothesis.

Abstract: Even when lacking an accurate association between the trajectory and identification of a moving body, the association between trajectory and identification of the moving body is estimated and the ambiguity quantified. An identification information association unit associates an individual trajectory link included in a trajectory link candidate with likely moving body identification information per trajectory link candidate. An association trend quantification unit quantifies a trend of the number of times when trajectory information is associated with moving body identification information per individual moving body identification information for individual trajectory information based on an association result between a trajectory link and moving body identification information.

Abstract: A flow line specification unit selects, for each piece of mobile object identification information, position-score correspondence information that satisfies a criterion from among position-score correspondence information stored in state storage unit, as definite position-score correspondence information. The flow line specification unit repeatedly performs a process of reflecting the definite position-score correspondence information in position-score correspondence information of a time nearest a time corresponding to the definite position-score correspondence information and setting the position-score correspondence information of the nearest time as definite position-score correspondence information. And the flow line specification unit specifies a flow line of a mobile object from a score in position-score correspondence information of each time.

Abstract: There is provided a flow line detection process data distribution system which can distribute data detected from a mobile body to precisely perform flow line detection when flow line detection is realized by distribution processing. An area processing means 92 calculates for each combination which is a combination of unit areas used as constituent units of divided areas upon determination of the divided areas obtained by dividing the predetermined area and which is obtained by combining two different unit areas a degree of correlation which indicates a degree that sensor data related to an identical mobile body is detected, and determines the divided areas obtained by dividing the predetermined area based on the calculated degree of correlation. A data distribution means 93 classifies the sensor data stored in the data storage means 91 depending on in which divided area the sensor data is detected, and outputs the classified sensor data to different flow line detection process units.

Abstract: A flow line detection system capable of accurately determining a position of a mobile object of each piece of identification information and detecting a flow line even when there are frequent cases where a position or identification information of a mobile object cannot be detected is provided.

Abstract: There is provided a mobile body track identification system that determines which mobile body matches which detected track with a high precision irrespective of frequent interruption of tracks of a mobile body detected in a tracking area. Herein, hypotheses are generated by use of sets of track-coupling candidate/identification pairs, which combines track-coupling candidates, combining tracks of a mobile body detected in a predetermined time in the past, and identifications of the mobile body and which satisfies a predetermined condition. Next, identification likelihoods are calculated as likelihoods of detecting identifications in connection with tracks indicated by track-coupling candidates included in track-coupling candidate/identification pairs ascribed to each of the selected hypotheses. Identification likelihoods are integrated per each track-coupling candidate/identification pair, thus calculating an identification likelihood regarding the selected hypothesis.