System and Method for Tracking and Annotating Multiple Objects in a 3D Model

Abstract

system and method for tracking and annotating objects in a 3D model is disclosed. The method includes receiving a signal feed from a group of sensors including at least one depth sensor, determining a reference signal feed from the signal feed, determining a volumetric representation of at least one object not present in the reference signal feed, assigning a unique volumetric profile to at least one object, and/or storing the unique volumetric profile in an object database. The signal feed may include at least one 3D area of interest. Also, the unique volumetric profile may include a unique volumetric id obtained from a group of attributes. The unique volumetric profile may include at least a unique volumetric position and a unique volumetric centroid. The group of sensors may further include video cameras, thermal, and chemical sensors.

Claims

1. A computing system comprising: a plurality of capture servers, each of the plurality of capture servers located in a distinct physical site, comprising a processor and a memory storing instructions that, when executed by the processor, configure the servers to execute the steps of: receiving a signal feed from a plurality of sensors, said signal feed comprising at least one area of interest, said plurality of sensors comprising at least one depth sensor, determining a reference signal feed from the signal feed, determining a volumetric representation of at least one object not part of the reference signal feed, assigning a unique volumetric profile to the at least one object, storing the unique volumetric profile in an object database, and sending the unique volumetric profile to at least one analytics server, wherein the unique volumetric profile comprises a unique volumetric id obtained from a plurality of volumetric attributes comprising at least a unique volumetric position and a unique volumetric centroid; the analytics server comprising a processor and a memory storing instructions that, when executed by the processor, configure the apparatus to a processor execute the steps of: receiving the unique volumetric profile from the plurality of capture servers, wherein the analytics server processes an aggregated data based on the received unique volumetric profile; and a web server comprising a processor and a memory storing instructions that, when executed by the processor, configure the apparatus to a processor execute the steps of: providing access to a user to the aggregated data.

2. The computing system of claim 1, wherein the unique volumetric attributes further comprise a total volume, height, and weight.

3. The computing system of claim 1, wherein the plurality of sensors further comprises at least one video sensor and the unique volumetric attributes further comprise color.

3. The computing system of claim 1, wherein the plurality of sensors further comprises at least one thermal sensor and the unique volumetric attributes further comprise temperature.

4. The computing system of claim 1, wherein the aggregated data comprises number of customers in a queue, time spent in the queue, and productivity of employees in a customer service area.

5. A method comprising: receiving, by a capture server, a signal feed from a plurality of sensors, said signal feed comprising at least one area of interest, said plurality of sensors comprising at least one depth sensor, determining a reference signal feed from the signal feed, determining a volumetric representation of at least one object not part of the reference signal feed, assigning a unique volumetric profile to the at least one object, storing the unique volumetric profile in an object database, wherein the unique volumetric profile comprises a unique volumetric id obtained from a plurality of volumetric attributes comprising at least a unique volumetric position and a unique volumetric centroid.

6. The method of claim 5, further comprising processing an aggregated data based on a plurality of unique volumetric profiles stored in the object database.

7. The method of claim 5, wherein the unique volumetric attributes further comprise a total volume, height, and weight.

8. The method of claim 5, wherein the plurality of sensors further comprises at least one video sensor and the unique volumetric attributes further comprise color.

9. The method of claim 5, wherein the plurality of sensors further comprises at least one thermal sensor and the unique volumetric attributes further comprise temperature.

10. The method of claim 6, wherein the aggregated data comprises number of customers in a queue, time spent in the queue, and productivity of employees in a customer service area.

11. A computing apparatus, the computing apparatus comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to a processor execute the steps of: receive a signal feed from a volumetric sensor, calculate a reference signal feed from the signal feed, define a queue entry point, a queue exit point and a queue path in the reference signal feed, detect the presence of an object in the reference signal feed, assign a unique volumetric profile to the object, said unique volumetric profile comprising a unique volumetric id and a unique volumetric position in the queue path, store the unique volumetric profile in an object database, and retrieve the unique volumetric profile from the object database, wherein the unique volumetric position in the queue path is determined with respect to the queue entry point and the queue exit point.

12. The computing system of claim 11, wherein the unique volumetric profile further comprises a total volume, height, and weight.

13. The computing system of claim 11, wherein the plurality of sensors further comprises at least one video sensor and the unique volumetric profile further comprises color.

14. The computing system of claim 11, wherein the plurality of sensors further comprises at least one thermal sensor and the unique volumetric profile further comprises temperature.

15. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to a processor execute the steps of: receive a signal feed from a volumetric sensor, calculate a reference signal feed from the signal feed, define a queue entry point, a queue exit point and a queue path in the reference signal feed, detect the presence of an object in the reference signal feed, assign a unique volumetric profile to the object, said unique volumetric profile comprising a unique volumetric id and a unique volumetric position in the queue path, store the unique volumetric profile in an object database, and retrieve the unique volumetric profile from the object database, wherein the unique volumetric position in the queue path is determined with respect to the queue entry point and the queue exit point.

16. The computing system of claim 15, wherein the unique volumetric profile further comprises a total volume, height, and weight.

17. The computing system of claim 15, wherein the plurality of sensors further comprises at least one video sensor and the unique volumetric profile further comprises color.

18. The computing system of claim 15, wherein the plurality of sensors further comprises at least one thermal sensor and the unique volumetric profile further comprises temperature.

Description

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0010] To easily identify the discussion of any particular element or act, the most significant digit or digits in a reference number refer to the figure number in which that element is first introduced.

[0011] FIG. 1 illustrates an exemplary infrastructure for the object tracking system.

[0012] FIG. 2 illustrates a site managed by the tracking system.

[0013] FIG. 3 illustrates a routine for obtaining a unique volumetric profile of an object in a reference signal feed in accordance with one embodiment.

[0014] FIG. 4 illustrates a routine for managing a queue in a reference signal feed in accordance with one embodiment.

[0015] FIG. 5 illustrates a routine for tracking an area of interest in a reference signal feed in accordance with one embodiment.

DETAILED DESCRIPTION

[0016] According to FIG. 1, tracking system 100 includes a capture server 104 operationally connected to a plurality of sensors 106 in a physical site. The plurality of sensors 106 includes at least one depth sensor 102. The plurality of sensors 106 may include any suitable type of sensor such as a video camera, a microphone, or other sensors. The data captured by the capture server 104 is filtered and processed to obtain a volumetric representation of a moving object captured by the plurality of sensors 106. These volumetric representations are further processed to obtain a unique volumetric id and a unique volumetric profile for each moving object. The unique volumetric profile may include metadata such as the unique volumetric centroid and the unique volumetric position of the moving object.

[0017] After processing the captured data, the capture server 104 generates and sends data packet to the analytics server 108. As discussed, said data packet contains metadata information about the moving objects captured by the plurality of sensors 106. Communication between the capture server 104 and the analytics server 108 may be initiated in any suitable fashion such as a remote procedure call or an API. In some embodiments, the communication is performed in JSON, YAML, XML, or any similar format. In some embodiments, communication is performed by way of database or storage replication.

[0018] The analytics server 108 further processes the data from the capture server 104. For instance, the analytics server 108 may aggregate data from a plurality of capture servers. According to some embodiments, the analytics server 108 applies techniques to determine aggregated information from a plurality of physical sites. After analytics server 108 processes the data, it places the result in a format suitable for display in a web server 110. The web server 110 provides access to a user 112 to the processed data in analytics server 108.

[0019] The capture server 104, analytics server 108 and web server 110 each include at least one processor, RAM memory, storage medium, and a connection to the Internet.

[0020] FIG. 2 shows an exemplary site tracked by a plurality of sensors 106, including at least one depth sensor 102 (shown in FIG. 1). In one embodiment, the reference signal feed includes a queue entry point 204, a queue exit point 206, and a queue path 208.

[0021] Queue entry point 204 marks the place where the users enter the queue. In most sites, this marker is placed visibly with signs. Similarly, queue path 208 is the path that customers follow to get to queue exit point 206. In most sites, the queue path 208 will also be marked visibly with crowd control products such as retractable belt barriers. Once a customer representative is available, the customer gets out of the queue through queue exit point 206 and approaches customer service area 210. The plurality of sensors 106 may also track the interaction of customers with watched object 212, for example, for marketing or security measures.

[0022] The tracking system 100 allows site managers to measure, for example, the number of customers in the queue, the time they spent waiting in queue, and/or the productivity of employees at customer service area 210.

[0023] As shown in the picture, the plurality of sensors 106 may be mounted on the ceiling. However, it will be apparent to a person skilled in the art that the sensors may be wall-mounted, attached to furniture, or installed in other ways known by persons skilled in the art.

[0024] Referring to FIG. 3, in block 302, routine 300 receiving a signal feed from a plurality of sensors. The plurality of sensors include at least one depth sensor 102. Other types of sensors, such as thermal sensors and video cameras, may be suitable for obtaining and annotating volumetric representations of objects.

[0025] In block 304, routine 300 determines a reference signal feed from the signal feed. The reference signal feed is obtained by detecting non-movable objects in the signal feed. Other filters may also be applied, such as ignoring all objects outside (above or below) of a height threshold. This may be useful, for example, to ignore objects such as plants, crowd control devices, lamps, and other undesired objects.

[0026] In block 306, routine 300 determines a volumetric representation of at least one object not part of the reference signal feed. When the object is detected, the contour of said object is obtained. According to one embodiment, the contour is then placed inside of a rectangle in order to use less computing resources when following said object.

[0027] In block 308, routine 300 assigns a unique volumetric profile to the at least one object. The unique volumetric profile contains all metadata obtained from the object. In one embodiment, the unique volumetric profile contains metadata from a plurality of sensors, such as video cameras, thermal sensors, microphones, and others. In some embodiments, the unique volumetric profile includes at least a unique volumetric id and a unique volumetric centroid.

[0028] In block 310, routine 300 stores the unique volumetric profile in an object database. The object database may be any kind of suitable storage such as a structured database, a column-based database or a text file in a format such as JSON or YAML. This may be needed, for example, to compare the unique volumetric profile with a new object detected in the reference signal feed.

[0029] In block 312, routine 300 obtains a unique volumetric id from a plurality of volumetric attributes. Assigning a unique volumetric id may be performed by finding unique features of an object based on the object's metadata and additional indirect calculations, such as its total volume, height, position, weight, color and others. In one embodiment, these unique features are simply based on the location of the object. In other embodiments, statistical and machine learning techniques may be used to train the system and later identify a volumetric representation once it reappears on screen after leaving the reference signal feed. In “DONE” block 314, routine 300 ends.

[0030] FIG. 4 shows an example embodiment of a queue tracking system. Such an embodiment is useful, for example, to determine how many customers are in a queue and how much time are they waiting to be served.

[0031] In block 402, routine 400 receives a signal feed from a volumetric sensor.

[0032] In block 404, routine 400 calculates a reference signal feed from the signal feed. As in FIG. 3, the reference signal feed is obtained by detecting non-movable objects in the signal feed. Other filters may also be applied, such as ignoring all objects outside (above or below) of a height threshold.

[0033] In block 406, routine 400 defines a queue entry point and a queue exit point and a queue path. The queue entry point is the section where customers enter the queue and the queue exit point is the section where customers exit the queue. The queue path may be optionally established to detect whether an object has left the queue even though it may still be visible in the reference signal feed.

[0034] In block 408, routine 400 detects the presence of an object in the signal feed. When an object is detected, the routine 400 detects the object's contour and calculates the volumetric representation from said contour and assigns an entry time timestamp. In block 410, routine 400 assigns a unique volumetric profile to the object. In block 412, routine 400 adds metadata from the object to the unique volumetric profile. The unique volumetric profile contains metadata about the object such as pixel colors obtained from video cameras, sounds obtained from microphones, position in the queue, time and height variation at each position (gait), and others.

[0035] In block 414, routine 400 stores the unique volumetric profile in an object database. In block 416, routine 400 retrieves the unique volumetric profile from the object database. Storage and retrieval of the unique volumetric profile may be used, for example, to compare the unique volumetric profile with a new object detected in the reference signal feed. In “DONE” block 418, routine 400 ends.

[0036] FIG. 5 shows an example embodiment of an area of interest tracking system. Such an embodiment is useful, for example, to determine how much time customers spend in an area of interest or to detect when a customer engages with a watched object (i.e. determining whether the customer picked up an object).

[0037] In block 502, routine 500 receives a signal feed from a volumetric sensor, such as a thermal sensor or a depth sensor.

[0038] In block 504, routine 500 calculates a reference signal feed from the signal feed. As in FIG. 4, the reference signal feed is obtained by detecting non-movable objects in the signal feed. Other filters may also be applied, such as ignoring all objects outside (above or below) of a height threshold.

[0039] In block 506, routine 500 defines a 3D area of interest. A 3D area of interest i s any area, such as a product display or a cash register, where the behavior of a moving object is measured. In one embodiment, the 3D area of interest may be useful, for example, to detect how much time a customer is engaged with a customer representative. Another embodiment may be used to determine whether a customer picked up an object contained in the 3D area of interest.

[0040] In block 508, routine 500 detects the presence of an object in the signal feed. When an object is detected, the routine 500 detects the object's contour and calculates the volumetric representation from said contour. In block 510, routine 500 generated a unique volumetric profile and adds metadata from the object to said unique volumetric profile. The unique volumetric profile contains metadata about the object such as time spent in the 3D area of interest or how many objects the customer has picked up, among others.

[0041] In block 512, routine 500 stores the unique volumetric profile in an object database. In block 514, routine 500 retrieves the unique volumetric profile from the object database. This may be needed, for example, to compare the unique volumetric profile with a new object detected in the reference signal feed. In done block 516, routine 500 ends.

[0042] While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the true spirit and scope of the invention. In addition, many modifications may be made without departing from the essential teachings of the invention.