KR-20260064504-A - controlling a list of inactive tracks used for re-identification in an object tracking system

KR20260064504AKR 20260064504 AKR20260064504 AKR 20260064504AKR-20260064504-A

Abstract

The present disclosure relates to a method (600), a system, and software for controlling a list of inactive tracks in an object tracking system. The described technique includes the step (s604) of obtaining a false positive rate (fpr) of a re-identification model using a judgment threshold and the step (s606) of obtaining an acceptable fpr of the tracking system. The re-identification model is used to match new detections with inactive tracks. The technique includes the step (s608) of determining one or more termination conditions for deleting inactive tracks based on the acceptable fpr and the model fpr. If a first inactive track satisfies the termination condition, the first inactive track is deleted from the list (s610).

Inventors

크리스티안 콜리안더
에마뉴엘 에스 해셀버그
조나탄 에릭손
니클라스 다니엘슨
니클라스 로셀
리차드 알레백
사라 라로스

Assignees

엑시스 에이비

Dates

Publication Date: 20260507
Application Date: 20250909
Priority Date: 20241030

Claims (15)

A method (600, 700, 800) for controlling a list (110) of inactive tracks (302, 304, 306, 308) used for re-identification in an object tracking system (100) that includes an object detector (102) and tracks an object in a scene, wherein the object tracking system includes a re-identification model (112) used when attempting to associate object detection data (106) received from the object detector with an inactive track from the list, and wherein the re-identification model is a metric learning model learned on the object detection data. A step (S602) of obtaining the false positive rate of a re-identification model using the decision threshold (206) of the re-identification model; Step of obtaining an acceptable false positive rate of the object tracking system (S604); A step (S606) of determining one or more termination conditions for deleting inactive tracks from the list using the acceptable false positive rate of the object tracking system and the false positive rate of the re-identification model; A step (S608) of determining that the first inactive track satisfies one of the one or more termination conditions; and A method comprising the step (S610) of deleting the inactive track from the list.
In paragraph 1, Each inactive track in the above list is associated with a counter (303, 305, 307, 309) indicating the number of associated failure attempts for the corresponding inactive track, and The above method additionally, A step (S702) of determining a threshold number of association attempts for each inactive track in the list using the acceptable false positive rate of the object tracking system and the false positive rate of the re-identification model, wherein the first termination condition among the one or more termination conditions includes the counter exceeding the threshold number of association attempts; A step of obtaining first object detection data from the object detector (S704); and A method comprising a step (S706) of evaluating whether the first object detection data is associated with a first inactive track from the list, wherein if the object detection data is not associated with a first inactive track from the list, the step of increasing the counter associated with the first inactive track.
In paragraph 2, The above method additionally, A step of obtaining multiple object detection data associated with the same image frame of a video stream illustrating the above scene from the object detector; For each of the plurality of object detection data, a step of evaluating whether the object detection data is associated with a first inactive track from the list, wherein if the object detection data is not associated with a first inactive track from the list, a step of increasing a counter associated with the first inactive track; and A method comprising the step of determining whether the first inactive track satisfies the first termination condition among the one or more termination conditions after the evaluation of all object detection data of the plurality of object detection data is completed.
In paragraph 2, A method for deleting the first inactive track from the list when the first object detection data is associated with the first inactive track from the list.
In paragraph 2, The above threshold number is a mathematical formula It is determined by solving, In the above mathematical formula represents the true positive rate of the above re-identification model, and represents the value obtained by subtracting the acceptable false positive rate of the object tracking system from 1, and A method in which the above threshold number is determined using N.
In paragraph 2, Each inactive track in the above list is associated with location data representing a location within a scene where the inactive track is determined to be inactive by the object tracking system, and the method additionally, A step of determining first position data from the acquired object detection data; A step of selecting a subset of inactive tracks from the list based on location data from the first object detection data and location data associated with each inactive track in the list; and A method comprising, for each inactive track within a subset of the inactive tracks, evaluating whether the object detection data is associated with the inactive track, and if the object detection data is not associated with the inactive track, increasing a counter associated with the inactive track.
In paragraph 2, The above method additionally, A step of obtaining the maximum number of inactive tracks within the above list; A step of sorting the list of the above inactive tracks according to a counter associated with each; and A method comprising the step of cutting the list such that the list includes the maximum number of inactive tracks.
In paragraph 1, Each inactive track in the above list is associated with a timer (502, 504, 506, 508) indicating a time interval since the inactive track was added to the list, and the method additionally, Step of determining the current number of objects p in the scene (S802); A step (S804) of estimating r, which is the number of times an attempt to associate object detection data received from the object detector with an inactive track from the list is performed by the object tracking system per inactive track and per time unit; and A method comprising the step (S806) of determining a threshold time interval expressed in time units using p, r, the acceptable false positive rate of an object tracking system and the false positive rate of a re-identification model, wherein the second termination condition among the one or more termination conditions includes the step of the time interval of an inactive track exceeding the threshold time interval.
In paragraph 8, The critical time interval t expressed in time units is a mathematical formula It is decided by solving, or The critical time interval t expressed in time units is a mathematical formula The method is determined by solving for, where R corresponds to the total number of association attempts performed by the object tracking system per unit of time and is a function of p.
In paragraph 8, The above method additionally, It includes a step of estimating the amount of change p′ in the number of objects in a scene per time unit using historical data in which p and the number of objects in a scene are recorded at multiple points in time, and The critical time interval t expressed in time units is a mathematical formula The method is determined by solving for, where R corresponds to the total number of association attempts performed by the object tracking system per unit of time and is a function of p′.
In paragraph 8, The above method additionally, A step of obtaining the maximum number of inactive tracks within the above list; A step of sorting the list of inactive tracks according to the time interval indicated by a timer associated with each; and A method comprising the step of cutting the list such that the list includes the maximum number of inactive tracks.
In paragraph 1, The above method additionally, A step of obtaining an updated acceptable false positive rate of the object tracking system from a user of the object detection system; and A method comprising the step of updating at least one of a threshold number of association attempts and a threshold time interval using the updated acceptable false positive rate of the object tracking system.
A non-transient computer-readable storage medium storing instructions for implementing the method according to claim 1 when executed on a device having one or more processing capabilities.
As an object tracking system that includes an object detector and tracks objects within a scene, The object tracking system includes a re-identification model used when attempting to associate object detection data received from the object detector with an inactive track from a list, the re-identification model is a metric learning model learned on the object detection data, the object tracking system is configured to control a list of inactive tracks used for re-identification, and the object tracking system: Obtain the false positive rate of the re-identification model using the decision threshold of the re-identification model; Obtaining an acceptable false positive rate of the above object tracking system; Using the acceptable false positive rate of the object tracking system and the false positive rate of the re-identification model, one or more termination conditions for deleting inactive tracks from the list are determined; Determining that the first inactive track satisfies one of the one or more termination conditions; and An object tracking system configured to delete the inactive track from the above list.
In Paragraph 14, An object tracking system connected to a camera that captures a video stream representing a scene.

Description

Controlling a list of inactive tracks used for re-identification in an object tracking system The present invention relates to object tracking, and more particularly to a method, system, and software for controlling an inactive track list used for re-identification in an object tracking system. Object tracking systems play a key role in applications requiring continuous monitoring of objects within a scene, such as surveillance and autonomous vehicles. These systems utilize video feeds and algorithms to track objects across multiple frames, thereby forming a so-called "object track." This object track is constructed from a series of associated detection results for the same object. However, tracking may be interrupted due to reasons such as occlusion, the object moving out of sight, or missing detection. In such cases, the object track becomes inactive, and these inactive tracks are stored in memory or an “inactive track gallery.” When the object reappears, it can be re-identified using the inactive track gallery, thereby preventing duplicate tracks from being created for the same object. Generally, “re-identification (ReID)” refers to the process of accurately identifying and associating a previously detected object with a new detection result for the same object. Using re-identification, a new detection result can be matched with an inactive track representing a previously detected object; this is accomplished by comparing feature vectors that represent the appearance or visual characteristics of the detected object. These feature vectors are typically generated by a convolutional neural network (CNN) trained to output similar vectors for images containing the same object and different vectors for images containing different objects. A decision model evaluates the feature similarity between the new detection result and the inactive track by comparing the feature vector associated with the new detection result with the feature vector associated with the inactive track. At this stage, a similarity score (e.g., Euclidean distance or cosine similarity) may be calculated, and this similarity score can be used to determine whether to match the new detection result with the inactive track. However, as the number of inactive tracks increases, the accuracy of the decision model decreases. For example, a CNN may have an accuracy of about 70% in matching a single detection result in a gallery containing 100 inactive tracks, but the accuracy can be improved to 90% when there are only 5 inactive tracks. To manage this, a method can be used to keep the size of the inactive track gallery small and maintain accuracy by discarding inactive tracks that have remained inactive for a predetermined time limit (e.g., 5 seconds). This method works effectively in scenes with medium object density, as the number of inactive tracks is maintained at a manageable level. However, in scenes with very few objects, the aforementioned time limit may be unnecessarily strict, and maintaining inactive tracks for a longer period can improve the probability of successful re-identification without overloading the system. Conversely, in scenes with many objects, it may be necessary to discard inactive tracks more quickly to prevent the inactive track gallery from becoming excessively large, otherwise the accuracy of the decision model may be degraded. Therefore, improvement is required in this context. The foregoing and additional purposes, features, and advantages will be more clearly understood through the following exemplary and non-limiting detailed description of embodiments of the present disclosure with reference to the accompanying drawings, wherein like reference numerals indicate similar elements, FIG. 1 illustrates an object tracking system according to examples; FIG. 2 illustrates the distribution of matches and non-matches in a metric learning model used for re-identification in object tracking according to examples; FIG. 3 illustrates a tracked scene and a list of inactive tracks used for re-identification, wherein each inactive track is associated with a counter indicating the number of association failure attempts for the corresponding inactive track; FIG. 4 illustrates a list of inactive tracks used for tracking scenes and re-identification of FIG. 3, wherein each inactive track is additionally associated with location data; FIG. 5 illustrates a list of inactive tracks used for tracking scenes and re-identification according to examples, wherein each inactive track is associated with a timer representing the time interval since the inactive track was added to the list; and FIGS. 6 to 8 each illustrate a flowchart of a method for controlling an inactive track list used for re-identification in an object tracking system according to examples. Object tracking systems are essential in applications such as surveillance and autonomous driving, forming “object tracks” by continuously monitoring objects within a scene through video feed