Method and system for tracking moving objects in an occlusion-sensitive image sequence

Abstract

A computer-implemented method of tracking a moving object in a sequence of images, the method takes, as input data, a sequence of images and provides, as output data, the position of a moving object within the sequence of images.The method comprises the following steps:- detecting a moving object in a first image of the image sequence;- predicting the position of said moving object in at least one second image of the image sequence, the position being a bounding box;- calculating a community coefficient between the predicted bounding box corresponding to said moving object in the second image and the bounding box corresponding to a detected object in the second image;- validating the predicted position of the moving object if the value of the community coefficient is greater than a threshold value; in which the community coefficient CC is the ratio of the area of ​​the intersection between the predicted bounding box and the bounding box corresponding to a detected object to the area of ​​their union, the area of ​​each of the two bounding boxes being an area weighted according to a surface distribution law previously established for each of the images of the image sequence.

Description

Title of the invention: Method and system for tracking moving objects in a sequence of images sensitive to occultation Technical field

[0001] The invention relates to a method and a system for tracking moving objects in a sequence of images sensitive to occlusion. Technical background

[0002] The detection and tracking, also called tracking, of moving objects, such as people, animals or vehicles, in a sequence of images or a video are essential operations of computer vision. The applications are multiple. For example, these operations are the foundations of any analysis of the interactions between objects and their environment for the operation of so-called autonomous systems such as autonomous vehicles or robots, of the rational management of crowds or road traffic or of statistical studies of modeling and anticipation of the collective behavior of individuals. They are also used in railway and airport gates for the registration, identification and / or biometric authentication of travelers or vehicles in free flow.As part of prevention measures for civil security, police investigations or even the fight against crime, they also provide essential information for a better understanding and interpretation of scenes of daily life, offenses or crimes.

[0003] The tracking or tracking of moving objects in a sequence of images or a video generally relies on statistical learning methods such as artificial neural networks. These methods are configured to determine the trajectory of one or more objects through a sequence of images and consist, in general, of detecting one or more types of objects between successive images of a sequence of images, delimiting them and / or predicting their position using bounding boxes, then evaluating the rate of overlap of the bounding boxes between successive images.

[0004] It is common to evaluate the overlap rate between two bounding boxes using the Jaccard index, also called the "Jaccard coefficient" or "community coefficient" (loU, "Intersection over Union"). The Jaccard index is insensitive to scale effects. Its value is between 0 and 1. The value 0 means that the two sets A and B are perfectly disjoint, and the value 1 means that they perfectly overlap. It is defined as the ratio of the cardinality of the intersection between two sets A and B and the cardinality of the union between these two sets. J(4 B) = --

[0005] For two bounding boxes between two successive images, the Jaccard index corresponds to the ratio of the area of ​​the intersection between the two bounding boxes to the area of ​​their union. In the context of tracking moving objects in a sequence of images or in a video, two bounding boxes between two successive images are generally considered to relate to the same object when the Jaccard index is greater than a previously defined threshold value.

[0006] In practice, as long as the value of the Jaccard index of the bounding boxes between successive images of a sequence or video remains greater than this threshold value, the bounding boxes are assumed to represent the same object between each image. The object is then tracked in the image sequence or video. On the other hand, as soon as the value of the Jaccard index becomes lower than this threshold value, the two bounding boxes are assumed to concern two different moving objects. The tracking of the object is then terminated.

[0007] US 2020134837 Al [INTEL CORP [US]] 04 / 30 / 2020 describes, for example, a method for tracking moving objects in a video in which a Jaccard index is calculated between blobs and bounding boxes representing the objects detected by a convolutional neural network on successive images. If the value of the Jaccard index is lower than a threshold value, a new object detection is carried out by the convolutional neural network. This method makes it possible in particular to detect new moving objects entering a scene.

[0008] WO 2020 / 091749 Al [ARCUS HOLDING AS [DK]] 07.05.2020 describes a method for detecting moving objects in a video by simultaneously combining a deep learning approach in the form of a convolutional neural network and an approach by detecting changes in pixel values. The objects detected during these two approaches are delimited by bounding boxes. A Jaccard index is calculated between the bounding boxes of each of the two approaches and then compared to a threshold value.

[0009] The effectiveness of approaches based on comparing the value of the Jaccard index to a threshold value is based on the assumption that a moving object is always visible in its entirety, or almost, from one image to the next. However, it is common, in a real environment, for a moving object to be partially obscured by other fixed or moving objects in its environment during its movements. For example, an individual initially visible in its entirety in a first image may be partially obscured in the following image by other individuals behind whom it is moves or by a vehicle moving in front of it. Similarly, a vehicle initially visible in its entirety in a first image may be partially obscured in the following image when it is overtaken by another vehicle or obscured by the movement of a crowd of pedestrians.

[0010] A first negative consequence is the untimely and wrongful interruption of the tracking of a moving object. During an occultation, the value of the Jaccard index can artificially become lower than the threshold value. The bounding boxes of two successive images are then no longer considered as representative of the same moving object, the tracking is interrupted.

[0011] A second negative consequence is the confusion between two moving objects resulting in the tracking of a moving object different from that of the object initially being tracked. When a first moving object is occluded by a second moving object of a similar nature and size, for example two vehicles, the bounding box corresponding to the second moving object may be wrongly assimilated to the bounding box of the first moving object. The value of the Jaccard index may artificially become greater than the threshold value, and tracking may wrongly continue on the basis of the second moving object.

[0012] To overcome these drawbacks, different strategies have been developed in which the Jaccard index is combined with several other indices, parameters, scores or information obtained using other image processing methods.

[0013] WO 2020 / 175818 Al [NAVER CORP [KR]] 03.09.2020 describes a method for tracking moving objects in an image sequence based on a classification type network configured to calculate a posture similarity index between the objects of successive images. This similarity index makes it possible to improve the detection and tracking of occluded objects. It comprises a displacement factor calculated on the basis of a Jaccard index and an appearance factor based on a measurement of correspondence between global patterns.

[0014] WO 2021 / 242445 Al [MICROSOFT TECHNOLOGY LICENSING LLC [US]] 02.12.2021 describes a method for tracking moving objects in a video capable of managing the partial or total occultation of the objects. The method implements a detection module and a tracking module simultaneously processing the images of a video stream. An association module makes it possible to associate the objects detected by the detection module and the objects tracked by the tracking module via a spatial affinity score based on the Jaccard index. The tracking module is further configured to anticipate the trajectory of a moving object from information provided by the detection module.

[0015] WO 2021 / 237749 Al [SIEMENS AG [DE]] 02.12.2021 describes a method for tracking moving objects, such as vehicles, in a sequence of images of a video. Based on the assumption that different objects have different sizes, it implements, in addition to the Jaccard index, a size change index between the bounding boxes of two consecutive images. If the size change index is lower than a given threshold value and the Jaccard index is higher than a given value alone, the bounding boxes of the two successive images are considered to represent the same object.

[0016] WO 2022 / 256150 Al [MICROSOFT TECHNOLOGY LICENSING LLC [US]] 08.12.2022 describes a method for tracking a plurality of moving objects, such as individuals, in a sequence of images of a video. The method is based on the postulate that the same object between two consecutive images retains its appearance and different objects have different sizes. The method implements a trained neural network to predict and estimate the position and size of the occlusion zones of the objects between them during their movement by anticipation of their trajectory. This predictor / estimator of the occlusion zones can be combined with a Jaccard index. Summary of the invention Technical problem

[0017] A major drawback of current methods for tracking moving objects capable of managing their temporary and / or partial occultation by other objects in a scene is the complexity of their implementation, in particular the need to implement other additional image processing methods and to combine them with a Jaccard index calculation, which, consequently, requires additional computing resources.

[0018] Another disadvantage of these methods is that by seeking to overcome only the inherent pitfalls of the Jaccard index with regard to the detection of partially or totally occulted moving objects, they still remain dependent on it. In other words, they remain based on an index which, as defined and used therein, is inappropriate for dealing with the phenomena of occultation of moving objects which may occur in a sequence of images of a real scene.

[0019] There therefore remains a need for a simple and robust method of tracking mobile objects capable of managing their temporary and / or partial occultation. Technical solution

[0020] According to a first aspect of the invention, there is provided a computer-implemented method of tracking a moving object in a sequence of images, the method takes, as input data, a sequence of images and provides, as output data, the position of a moving object among the sequence of images, the method comprises the following steps: - detecting a moving object in a first image of the image sequence; - predicting the position of said moving object in at least a second image of the image sequence, the position being a bounding box; - calculating a community coefficient between the predicted bounding box corresponding to said moving object in the second image and the bounding box corresponding to an object detected in the second image; - validate the predicted position of the moving object if the community coefficient value is greater than a threshold value; in which the community coefficient is the ratio of the area of ​​the intersection between the predicted bounding box and the bounding box corresponding to a detected object to the area of ​​their union, the area of ​​each of the two bounding boxes being an area weighted according to a surface distribution law previously established for each of the images in the image sequence.

[0021] Advantageous embodiments are described below.

[0022] According to a second aspect of the invention, there is provided a data processing device comprising means for implementing the method of any one of the embodiments of the first aspect of the invention.

[0023] According to a third aspect of the invention, there is provided a computer program comprising instructions which, when the program is executed by a computer, cause the computer to implement the method according to any one of the embodiments of the first aspect of the invention.

[0024] According to a fourth aspect of the invention, there is provided a storage medium comprising instructions which, when executed by a computer, cause the computer to implement the method according to any one of the embodiments of the first aspect of the invention.

[0025] According to a fifth aspect of the invention, there is provided a system of Brief description of the drawings

[0026] [Fig. 1] is a schematic representation of a first image and a second image of a scene in which a moving object is visible in its entirety and then partially obscured during its movement.

[0027] [Fig.2] is a flowchart of a method according to the first aspect of the invention.

[0028] [Fig.3] is a schematic representation of a surface distribution law for the second image of the scene of [Fig.l]

[0029] [Fig.4] is a schematic representation of a data processing device according to the second aspect of the invention. Detailed description of the embodiments

[0030] In [Fig.l] is shown an example of a sequence of two images II, 12 of a scene in which two individuals 1001, 1002 move. The two individuals 1001, 1002 are respectively represented by the bounding boxes B1-1001 and B1-1002 on the first image II and by the bounding boxes B2-1001 and B2-1002 on the second image 12. These bounding boxes can be obtained by any type of image analysis method capable of detecting objects, in particular convolutional neural networks.

[0031] In the first image II, the two mobile individuals 1001, 1002 are far from each other and their bounding boxes Bl-1001, Bl-1002 do not intersect. The overlap rate, calculated using a Jaccard index, between the two bounding boxes Bl-1001, Bl-1002 is therefore zero.

[0032] In the second image 12, the two individuals 1001, 1002 intersect and the bounding boxes B2-1001, B2-1002 overlap. The overlap rate, calculated using a Jaccard index, between the two bounding boxes B2-1001, B2-1002 is higher than in the case of the first image II. If this rate is higher than a threshold value, there may be a risk of confusion between the two individuals by a conventional tracking system. The system may consider that the two individuals 1001, 1002 represent the same individual, for example individual 1002, and interrupt the tracking of individual 1001.

[0033] In addition to detecting moving objects and delimiting them using bounding boxes, a moving object tracking system may be configured to predict the position of a moving object as it moves in one or more images of an image sequence. This prediction may be established by extrapolation from a displacement field whose measurement is based on an analysis of the different positions of the object and / or one or more distinctive characteristics of this moving object from one or more previous images.

[0034] By way of example, with reference to [Fig. 1], the tracking system can predict the position of the first individual 1001 from a displacement field measured by analyzing the different positions of his head and / or the upper part of his body such as his bust, possibly combined with an analysis of his build and / or his posture. In the first image II, the first individual 1001 being visible in his entirety, the predicted box PI-1001 representing the predicted position corresponds more or less to the bounding box Bl-1001. On the other hand, in the second image 12, the predicted position is represented by a box P2-1001 centered only on a visible part of the individual 1001, in this case the upper part of his bust including his head. The predicted box P2-1001 overlaps the bounding box B2-1001 of the first character 1001 as well as part of the bounding box B2-1002 of the second character 1002.

[0035] For tracking systems which are wholly or partly based on the Jaccard index, the predicted position is validated as soon as the value of said index between the predicted box and the bounding box of the moving object is greater than a threshold value, for example 0.7. In image II, this condition is met: the Jaccard index between the predicted box Pl-1001 and the bounding box Bl-1001 is greater than 70%. In image 12, the value of the Jaccard index between the predicted box P2-1001 and the bounding box B2-1002 representing the individual 1002 is less than 70%. The condition is not met, individual 1001 is not confused with individual 1002. However, in image 12, the value of the Jaccard index between the predicted box P2-1001 and the bounding box B2-1001 of individual 1001 is also less than 70%, the condition is also not met for the first individual 1001 and the predicted position P2-1001 is not validated for individual 1001. However, this predicted position P2-1001 does indeed correspond to the first individual 1001.Tracking systems that are wholly or partly based on the Jaccard index therefore fail in tracking moving objects that may be obscured.

[0036] According to a first aspect of the invention, with reference to [Fig.l] to 3, there is provided a computer-implemented method 2000 for tracking a moving object 1001 in a sequence of images II, 12. The method 2000 takes, as input data, a sequence of images II, 12 and provides, as output data, the position P1-1001, P2-1001 of a moving object 1001 among the sequence of images II, 12. The method 2000 comprises the following steps: - detecting 2001 a moving object 1001 in a first image II of the sequence of images II, 12; - predicting 2002 the position P2-1001 of said mobile object 1001 in at least one second image 12 of the sequence of images II, 12, the position P2-1001 being a bounding box; - calculate 2003 a community coefficient CC between the predicted bounding box P2-1001 corresponding to said moving object 1001 in the second image 12 and the bounding box Bl-1001, B2-1002 corresponding to a detected object 1001, 1002 in the second image 12; - validate 2004 the predicted position P2-1001 of the mobile object 1001 if the value of the community coefficient CC is greater than a threshold value VS; in which the community coefficient CC is the ratio of the area of ​​the intersection between the predicted bounding box P2-1001 and the bounding box Bl-1001, B2-1002 corresponding to a detected object 1001, 1002 to the area of ​​their union, the area of ​​each of the two bounding boxes being an area weighted according to a surface distribution law G previously established for each of the images II, 12 of the sequence of images II, 12.

[0037] The community coefficient is defined as the ratio of the area of ​​the intersection between the predicted bounding box P2-1001 and bounding box Bl-1001, B2-1002 corresponding to a detected object 1001, 1002 on the area of ​​their union, Making each of the two bounding boxes being an area weighted according to a surface distribution law G previously established for each of the images II, 12 of the sequence of images II, 12.

[0038] A fundamental difference between the community coefficient according to the invention and the Jaccard index (loU, "Intersection over Union") is the weighting of the areas of the bounding boxes according to a surface distribution law. The function of this weighting is to ensure a differentiated contribution of the regions of the image contained in the bounding boxes according to their relevance to the characteristics of the moving object that they represent.In other words, the regions of the image representing relevant or discriminating characteristics of the moving object, such as, for example, the head or the upper part of the bust in the case of an individual, are favored in their contribution to the value of the area of ​​the bounding box in which they are contained. A remarkable advantage of the community coefficient according to the invention is therefore better discrimination of moving objects, in particular with regard to the characteristics to be taken into account to differentiate them during occultation phenomena.

[0039] In [Fig. 3] is shown a schematic and purely illustrative example of a surface distribution law in the form of a pattern G in gradient of points for the second image 12 of [Fig. 1]. The three bounding boxes P2-1001, Bl-1001 and B2-1002 are also shown in this figure. The pattern G in gradient of points consists of three zones Gl, G2, G3 whose density of points decreases from the top of the image towards the bottom of the image.These three zones Gl, G2, G3 represent a surface distribution law corresponding to decreasing weightings of the pixels from the top of the image to the bottom of the image when calculating the areas of the three bounding boxes P2-1001, Bl-1001 and B2-1002: during this calculation, the pixels of the bounding boxes located in the first zone Gl are weighted by a weighting coefficient higher than those of the second zone G2, themselves being weighted by a weighting coefficient higher than those of the third zone G3.

[0040] Thanks to this surface distribution law, the pixels “have” different weights when calculating the area of ​​the bounding boxes depending on their location in the image. By analogy, in the example illustrated in [Fig.3], the “barycenters” of the predicted bounding box P2-1001 and of the bounding box Bl-1001 are respectively shifted to the area of ​​the distribution in which the weighting of the pixels is the highest, in this case the first zone Gl; the pixels located in the first zone Gl have “more importance” than those located in the second zone G2.

[0041] When calculating the areas of the predicted bounding box P2-1001 and the bounding box Bl-1001 corresponding to individual 1001, the pixels of the first zone Gl are weighted by a coefficient higher than those of the second zone G2. The value of the community coefficient according to the invention between the predicted bounding box P2-1001 and the bounding box B1-1001, being more representative of this weighting, becomes higher than that of a Jaccard index, and, unlike the latter, during the occultation of individual 1001 by individual 1002, remains higher than the threshold value VS. The predicted position for individual 1001 is validated; the tracking of individual 1001 continues correctly despite the occultation.

[0042] In the example of [Fig. 3], the surface distribution law is deliberately simplified for purely illustrative purposes. Also, instead of being discontinuous, in particular organized into regions of different density, it is preferably continuous over the entire image. Similarly, the variations in the weighting along the image may be different from that shown in [Fig. 3] which is decreasing from the top to the bottom of the image. For example, it may be decreasing or increasing from one lateral side of the image to another, or from the edges of the image towards its center. Generally speaking, the continuous or discontinuous nature of the surface distribution law as well as its variations along the image depend on the type of moving objects likely to be tracked, the way in which they move and the environment in which they move.For example, they may be different depending on whether the moving object is an individual or a vehicle. The surface distribution law may be different for each of the images in the image sequence. When the nature of the scene in which the moving objects are tracked does not change substantially during tracking, the surface distribution law is generally identical for each of the images in the image sequence.

[0043] The surface distribution law is of any suitable type. It can be in the form of a table of values ​​in which each value is a weighting coefficient associated with a region comprising one or more pixels of the images of the image sequence. It can also be in the form of a mathematical function whose value varies according to the location of the pixels of the images of the image sequence.

[0044] According to certain preferred embodiments, the surface distribution law G is an exponential distribution law. An exponential distribution is advantageous in that it makes it possible to ensure a differentiated weighting granting a significantly high contribution to certain most relevant regions of an image while considerably reducing the contribution of less relevant regions in the calculation of the community coefficient according to the invention. Such a distribution is particularly suitable for tracking individuals in a scene.

[0045] According to one example, for an exponential distribution law decreasing from the top to the bottom of the image, the area A of a bounding box can be calculated using the following formula, where 1 is the width, expressed in pixels, of the bounding box, y

[0046]

[0047] the coordinate of the upper left corner of the box, h the height, expressed in pixels, of the bounding box and T a fixed parameter. A = r eiT = er?7^ An exponential or similar distribution law is likely to make the community coefficient according to the invention sensitive to scale effects such as enlargement or shrinkage of the images in the image sequence. Since such operations are likely to be performed on the images, this sensitivity can be a source of artifacts which can manifest themselves as aberrant values ​​of the sensitivity coefficient.

[0048] Also, according to certain advantageous embodiments, the exponential distribution law may further comprise, as a parameter, a normalization factor with respect to at least one dimension of the images of the image sequence. This normalization factor has the function of removing sensitivity to scale effects. The normalization may be carried out with respect to the width of the image, the height of the image or those of the dimensions.

[0049] From the formula of the previous example, the fixed parameter T can include a normalization factor expressed in the following manner, with U the height of the image expressed in pixels: 100501

[0051] In the previous formula, the normalization factor corresponds to the coefficient 1 / U.

[0052] The parameter T here has the function of an empirically defined optimization parameter. It can be a fixed or variable number, preferably fixed. It has been found that values ​​between 0 (not included) and 30 (inclusive) for the parameter T constitute an optimal range of values ​​for tracking individuals in a sequence of images in which they are likely to be hidden.

[0053] Generally speaking, the distribution law can advantageously include an optimization factor, of which the preceding parameter T is an example. This parameter can be a fixed or variable value, preferably a fixed value. Its value can be adjusted according to a purely empirical approach or using any suitable optimization method.

[0054] According to certain preferred embodiments, the surface distribution law G comprises, as a parameter, an optimization factor, the optimization factor being previously defined by minimizing the difference between the community coefficient and a Jaccard index for non-occulted mobile objects. An optimization factor obtained by minimizing the difference between the community coefficient and a Jaccard index for non-occulted mobile objects. community according to the invention and a Jaccard index for non-occulted mobile objects is particularly advantageous in that it makes it possible to obtain, during its implementation, a community coefficient preserving the continuity of the tracking of a mobile object when it is occulted and retaining a behavior close to that of a Jaccard index when the object is no longer occulted.

[0055] The method according to the invention is particularly advantageous for tracking moving objects such as individuals or vehicles in a sequence of images. Thus, according to preferred embodiments, the moving object is an individual in a substantially vertical position and the surface distribution law G is a distribution decreasing vertically from the head to the feet of vertical people. According to other embodiments, the moving object is a vehicle and the surface distribution law G is a distribution decreasing horizontally in the direction of movement of the vehicles.

[0056] The method according to the first aspect of the invention is implemented by computer. With reference to [Fig.4], in a second aspect of the invention, there is provided a data processing device 4000 comprising means for implementing a method 2000 according to any one of the embodiments of the first aspect of the invention.

[0057] An example of a device may be a device responsible for automatically executing sequences of arithmetic or logical operations to perform tasks or actions. This device, also called a computer, may comprise one or more central processing units (CPUs) and / or one or more graphics processors (GPUs) 4001 as well as at least one control device adapted to the execution of these operations. It may also comprise other electronic components such as input / output interfaces 4002, non-volatile or volatile storage devices 4003, and communication buses for transferring data between internal components of the device or with external components. One of the input / output devices 4002 may be a user interface for human-machine interaction, for example a graphical user interface for displaying human-understandable information.

[0058] According to a third aspect of the invention, there is provided a computer program 14003 comprising instructions which, when the program is executed by a computer, cause the computer to implement a method 2000 according to any one of the embodiments of the first aspect of the invention.

[0059] Any type of programming language, compiled or interpreted, can be used to implement the steps of the method of the invention. The computer program can be part of a software solution, i.e. a collection of executable instructions, codes, scripts or others and / or databases.

[0060] According to a fourth aspect of the invention, there is provided a computer-readable recording medium 4003 comprising instructions which, when executed by a computer, cause the computer to implement a method 2000 according to any one of the embodiments of the first aspect of the invention.

[0061] The computer-readable storage medium 4003 is preferably a non-volatile memory, for example a hard disk or a solid-state drive. It may be a removable storage medium or a non-removable storage medium forming part of a computer.

[0062] The computer-readable recording medium 4003 may also be volatile memory within a removable medium. This may facilitate deployment of the invention in many production sites.

[0063] The computer-readable recording medium 4003 may be part of a computer used as a server from which executable instructions may be downloaded and, when executed by a computer, cause the computer to execute a method according to one of the embodiments described herein.

[0064] The computer program 14003 and the medium 4003 on which it is recorded may be implemented in a distributed computing environment, for example cloud computing. The instructions may be executed on a server to which one or more client computers may connect and provide encoded data as input data to a method according to any of the embodiments of the first aspect of the invention. Once the data has been processed, the result may be downloaded and decoded to the client computer or sent directly, for example, in the form of instructions.

[0065] According to a fifth embodiment, there is provided a system for tracking a moving object in a sequence of images. The system comprises - an image acquisition device; - a data processing device according to the second aspect of the invention, said data processing device being configured to receive and process a sequence of images acquired by the image acquisition device. References Patent literature

[0066] US 2020134837 Al [INTEL CORP [US]] 04.30.2020.

[0067] WO 2020 / 091749 Al [ARCUS HOLDING AS [DK]] 07.05.2020.

[0068] WO 2020 / 175818 Al [NAVER CORP [KR]] 03.09.2020.

[0069] WO 2021 / 242445 Al [MICROSOFT TECHNOLOGY LICENSING LLC [US]] 02.12.2021.

[0070] WO 2021 / 237749 Al [SIEMENS AG [DE]] 02.12.2021.

[0071] WO 2022 / 256150 Al [MICROSOFT TECHNOLOGY LICENSING LLC [US]] 08.12.2022.

Claims

Claims

1. A computer-implemented method (2000) for tracking a moving object (1001) in a sequence of images (II, 12), the method (2000) takes, as input data, a sequence of images (II, 12) and provides, as output data, the position (P1-1001, P2-1001) of a moving object (1001) among the sequence of images (II, 12), the method (2000) comprises the following steps: - detecting (2001) a moving object (1001) in a first image (II) of the sequence of images (II, 12); - predicting (2002) the position (P2-1001) of said moving object (1001) in at least one second image (12) of the image sequence (II, 12), the position (P2-1001) being a bounding box; - calculating (2003) a community coefficient CC between the predicted bounding box (P2-1001) corresponding to said moving object (1001) in the second image (12) and the bounding box (B 1-1001, B2-1002) corresponding to a detected object (1001, 1002) in the second image (12);- validate (2004) the predicted position (P2-1001) of the mobile object (1001) if the value of the community coefficient CC is greater than a threshold value VS; in which the community coefficient CC is the ratio of the area of ​​the intersection between the predicted bounding box (P2-1001) and the bounding box (Bl-1001, B2-1002) corresponding to a detected object (1001, 1002) to the area of ​​their union, the area of ​​each of the two bounding boxes being an area weighted according to a surface distribution law G previously established for each of the images (II, 12) of the sequence of images (II, 12).;

2. Method (2000) according to claim 1, such that the surface distribution law G is an exponential distribution law.

3. Method (2000) according to claim 2, such that the exponential distribution law comprises, as a parameter, a normalization factor with respect to at least one dimension of the images of the sequence of images.

4. Method (2000) according to any one of claims 2 to 3, such that the distribution law comprises, as a parameter, an optimization factor, the optimization factor being previously defined by minimizing the difference between the community coefficient and a Jaccard index for non-occulted moving objects.

5. Method (2000) according to any one of claims 1 to 4, such that the mobile object is an individual in a substantially vertical position and the surface distribution law G is a distribution decreasing vertically from the head to the feet of vertical persons.

6. Method (2000) according to any one of claims 1 to 4, such that the moving object is a vehicle and the surface distribution law G is a horizontally decreasing distribution in the direction of movement of the vehicles.

7. Data processing device (4000) comprising means for implementing the method (2000) according to any one of claims 1 to 6.

8. A computer program (14003) comprising instructions which, when the program is executed by a computer, cause the computer to implement the method of any one of claims 1 to 4, wherein the computer is executed by a computer.

9. 1 dO. A computer-readable recording medium (4003) comprising instructions which, when executed by a computer, cause the computer to implement the method of any one of claims 1 to 6.

10. System for tracking a moving object in a sequence of images, said system comprises: - an image acquisition device; - a data processing device (4000) according to claim 7, said data processing device (4000) being configured to receive and process a sequence of images acquired by the image acquisition device.

Images