TWM566885U - A distributed object tracking system - Google Patents

Abstract

The present invention discloses a distributed object tracking system including a plurality of image analysis devices and a cluster management service device connected to the plurality of image analysis devices, wherein each image analysis device analyzes at least one object in at least one real-time video stream to generate an analysis result for tracking the at least one object, and the cluster management service device includes a tracking module to form a trajectory of each of the at least one object according to the analysis results of the plurality of image analysis devices.

Description

A distributed object tracking system

This creation is about object tracking systems, especially a distributed object tracking system.

Most of the current image analysis devices are image analysis for a single scene of a single camera. The analysis results of the respective image analysis devices are independent, and the analysis results of different cameras cannot be connected in series, thereby achieving object tracking across the camera. Therefore, the industry needs a distributed object tracking system that can serially analyze the results of different cameras to achieve object tracking across cameras.

One of the aims of the present invention is to provide a distributed object tracking system that can serially link object analysis results of multiple instant image streams of multiple image analysis devices to instantly track the trajectory of an object, wherein the resources of the image analysis device Points can be utilized to characterize objects to reduce system cost.

One of the purposes of the present invention is to provide a distributed object tracking system that can serially link object analysis results of multiple instant image streams across multiple image analysis devices across regions to instantly track object trajectories across regions. Provides services for post-event search and abnormal behavior alerts.

In an embodiment of the present disclosure, a distributed object tracking system is provided, comprising: a plurality of image analyzing devices, wherein each image analyzing device analyzes objects in at least one of the instant video streams received to generate traceable objects. An analysis result of the at least one object; and a cluster management service device connected to the plurality of image analysis devices, wherein the cluster management service device includes a tracking module to serially connect the plurality of image analysis devices Tracking the results of at least one object to track the trajectory of the objects.

In an embodiment, each image analysis device receives a plurality of real-time image streams, wherein each image analysis device includes a tracking module to cascade the feature analysis results of at least one of the plurality of instant image streams to Generating a secondary trajectory of the at least one object, wherein the tracking module of the cluster management service device serially connects the plurality of trajectories generated by the plurality of image analysis devices to track the trajectories of the objects.

In one embodiment, the at least one object comprises a person, and the analysis result includes facial features of the person.

In one embodiment, the at least one item comprises a luggage, and the analysis results include features of the luggage.

In an embodiment, the plurality of image analysis devices are distributed in a detection area, wherein at least one specific item in the detection area is predetermined not to be tracked.

In an embodiment, the detection area includes a station, and the station staff is scheduled not to be tracked.

In an embodiment, if a certain object in the detection area is not detected for more than a predetermined length of time, it is determined that the specific object has left the detection area, and is no longer The image analysis device performs real-time tracking.

In an embodiment, an abnormal stay event is issued if one of the detected areas continues to stay in a particular area of the detection area for more than a predetermined length of time.

An embodiment of the present invention provides a distributed object tracking system, including: a first plurality of image analysis devices, wherein each image analysis device analyzes objects in at least one of the instant image streams received to generate a first analysis result of one of the at least one object being tracked; a first cross-camera tracking device coupled to the first plurality of image analysis devices, wherein the first cross-camera tracking device includes a tracking module to serially connect a first analysis result of the at least one tracked object generated by the first plurality of image analysis devices to track a first track of the objects; a second plurality of image analysis devices, wherein each image analysis device analyzes The at least one object in the instant video stream is received to generate a second analysis result of at least one object that can be tracked; a second cross camera tracking device is coupled to the second plurality of image analysis devices, wherein the The second cross-camera tracking device includes a tracking module for concatenating the second of the at least one object that is generated by the second plurality of image analyzing devices Parsing the result to track a second track of the objects; and a cluster management service device coupled to the first cross-camera tracking device and the second cross-camera tracking device, wherein the cluster management service device includes a tracking module The first track and the second track are used to serially connect the objects.

In one embodiment, the distributed object tracking system tracks the target based on a particular target image.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the first detection area and the first At least one specific item in the second detection area is scheduled not to be tracked.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the cluster management service device If a specific object in all the detection areas is not detected for more than a predetermined length of time, it is determined that the specific object has left all the detection areas of the cluster management service device, and is no longer the first The plurality of image analysis devices and the second plurality of image analysis devices perform real-time tracking.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the object being tracked continues to stay An abnormal stay event is issued when the cluster manages a specific area within the detection area of the service device and exceeds a predetermined length of time.

The foregoing and other technical features, features, and advantages of the present invention will be apparent from the following description of the preferred embodiments. However, it should be noted that the following embodiments are not intended to limit the present invention.

In an embodiment of the present work, a distributed object tracking system is proposed. Referring to FIG. 1, the distributed object tracking system includes: a plurality of image analyzing devices 105 and 106, wherein each of the image analyzing devices 105 and 106 respectively analyzes the instant image strings captured by the corresponding camera devices 101 and 102. An object in the stream to generate an analysis result of the object that can be tracked; and a cluster management service device 110 connected to the plurality of image analysis devices 105, 106, wherein the cluster management service device 110 includes a tracking module 110a The analysis result of the tracked object generated by the plurality of image analyzing devices 105, 106 is followed to track the trajectory of the object.

In one embodiment, the at least one object comprises a person, and the analysis result includes facial features of the person.

In one embodiment, the at least one item comprises a luggage, and the analysis results include features of the luggage.

In an embodiment, the plurality of image analysis devices are distributed in a detection area, wherein at least one specific item in the detection area is predetermined not to be tracked.

In an embodiment, the detection area includes a station, and the station staff is scheduled not to be tracked.

In an embodiment of the present work, a distributed object tracking system is proposed. Referring to FIG. 2, the distributed object tracking system includes: a plurality of image analyzing devices 205, 206, wherein each of the image analyzing devices 205, 206 has a corresponding plurality of image analyzing modules 205a, 205b, 206a, 206b to analyze the objects in the instant video stream captured by the corresponding plurality of photographic devices 201, 202, 203, 204 to generate an analysis result of the object that can be tracked; and a cluster management service device 210 connected to the a plurality of image analysis devices 205, 206, wherein the cluster management service device 210 includes a tracking module 210a for serially analyzing the analysis results of the tracked objects generated by the plurality of image analysis devices 205, 206 to track the object. Track.

In an embodiment of the present work, a distributed object tracking system is proposed. Referring to FIG. 3, the distributed object tracking system includes: a plurality of image analyzing devices 310 and 311, wherein each of the image analyzing devices 310 and 311 has a corresponding plurality of image analyzing modules 310a, 310b, and 311a, respectively. 311b to analyze the objects in the instant video stream captured by the corresponding plurality of photographic devices 201, 202, 203, 204 to generate an analysis result of the object that can be tracked, wherein each image analysis device 310, 311 includes a corresponding tracking module 310c, 311c to cascade the analysis results of the objects of the plurality of instant image streams to generate a secondary track of the objects; and a cluster management service device 320 connected to the plurality of image analysis The device 310, 311, wherein the cluster management service device 320 includes a tracking module 320a to cascade the plurality of trajectories generated by the plurality of image analyzing devices 310, 311 to track the trajectories of the objects.

In an embodiment, the distributed object tracking system of the present invention can be divided into multiple detection areas, and each image analysis device can perform face detection on the instant image stream captured by the camera in a single detection area. Or other non-human object detection to obtain facial features and other identifiable features to track the person or other non-human object in the single detection area. In an embodiment, each image analysis device can perform face detection or other non-human object detection for a plurality of instant image streams captured by a plurality of cameras from different locations in a single detection area. Face features and other identifiable features to track the person or other non-human object in the single detection area. In an embodiment, after preliminary face recognition or object recognition, objects that do not need to be tracked can be excluded. For example, at a station, the station personnel who have logged in do not need to be tracked; or specify that only special items need to be tracked, such as a suitcase. If there is an object to be tracked, the analysis result of the object to be tracked is recorded as a follow-up cross-detection area tracking, and the analysis result may include the object features to be tracked. The tracking module of the cluster management service device can cascade the analysis results of each detection area to track the trajectories of the objects in all the detection areas.

In an embodiment, each image analysis device can perform face detection or other non-human object detection for a plurality of instant image streams captured by a plurality of cameras from different locations in a single detection area. a face feature and other identifiable features, wherein each image analysis device includes a tracking module to cascade the analysis results of at least one of the plurality of instant image streams to generate a secondary trajectory of the at least one object. The tracking module of the cluster management service device serially connects the plurality of trajectories generated by the plurality of image analysis devices to track the trajectories of the objects.

In an embodiment, if a certain object in the detection area is not detected for more than a predetermined length of time, it is determined that the specific object has left the detection area, and is no longer The image analysis device performs real-time tracking.

In an embodiment, the object features are aligned for a predetermined length of time. If an object feature reaches a certain score (this score can be dynamically adjusted according to the scene learning), the object is marked as an item to be continuously tracked.

In an embodiment, an abnormal stay event is issued if one of the detected areas continues to stay in a particular area of the detection area for more than a predetermined length of time.

In an embodiment of the present work, a distributed object tracking system is proposed. Referring to FIG. 4, the distributed object tracking system includes: a first plurality of image analyzing devices 411, 412, wherein each of the image analyzing devices 411, 412 respectively analyzes a plurality of corresponding image capturing devices 401, 402 Acquiring an object in the live video stream to generate a first analysis result of one of the at least one object that can be tracked; a first cross camera tracking device 431 connected to the first plurality of image analysis devices 411, 412, wherein The first cross-camera tracking device 431 includes a tracking module 431a for serially connecting the first analysis results of the at least one tracked object generated by the first plurality of image analyzing devices 411, 412 to track the objects. a first trajectory; a second plurality of image analyzing devices 421, 422, wherein each of the image analyzing devices 421, 422 analyzes objects in the instant video stream captured by the corresponding plurality of photographic devices 403, 404 to generate a second analysis result of one of at least one object that can be tracked; a second cross-camera tracking device 432 coupled to the second plurality of image analysis devices 421, 422, wherein the second cross-camera tracking device 432 includes a tracking module 432a for concatenating the second analysis results of the at least one tracked object generated by the second plurality of image analysis devices 421, 422 to track a second track of the objects; A cluster management service device 440 is coupled to the first cross-camera tracking device 431 and the second cross-camera tracking device 432, wherein the cluster management service device 440 includes a tracking module 440a for serially connecting the objects The first track and the second track.

Please note that each of the image analyzing devices 411, 412, 421, and 422 in FIG. 4 may be the image analyzing device in FIG. 1, or the image analyzing device in FIG. 2, or the image analyzing device in FIG.

In one embodiment, the distributed object tracking system tracks the target based on a particular target image.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the first detection area and the first At least one specific item in the second detection area is scheduled not to be tracked.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the cluster management service device If a specific object in all the detection areas is not detected for more than a predetermined length of time, it is determined that the specific object has left all the detection areas of the cluster management service device, and is no longer the first The plurality of image analysis devices and the second plurality of image analysis devices perform real-time tracking.

In an embodiment, the first plurality of image analysis devices are distributed in a first detection area, and the second plurality of image analysis devices are distributed in a second detection area, wherein the object being tracked continues to stay An abnormal stay event is issued when the cluster manages a specific area within the detection area of the service device and exceeds a predetermined length of time.

The cluster management device of the present invention can communicate with the plurality of image analysis devices via the Internet, the cluster management device can have an internet address, and the plurality of image analysis devices pass the fixed internet address and the The cluster management device is coupled to cause the cluster management device to include the plurality of image analysis devices in its management scope. The cluster management device and the plurality of image analysis devices can communicate with each other using a communication protocol (Protocol). The cluster management device may have a management interface for the user to manage the plurality of image analysis devices. For example, the management interface may display a location distribution map of the plurality of image analysis devices, or input a target image through the management interface. To track the target.

The object tracking of this creation can be referenced, such as facial features, or humanoid features such as clothing, body shape, etc., or the location of the device that detects the object to exclude unreasonable motion trajectories.

The "cross-camera tracking device" in one embodiment of the present invention can increase hierarchical superposition, thus dispersing computing resources, and also expanding the entire detection area to track objects.

The “Immediate Cross-Camera Object Tracking” of this creation enables instant event search and where to go when objects go there. The “Immediate Cross-Camera Object Tracking” of this creation can also provide anomalous behavioral alerts to proactively inform the relevant units of suspicious objects. This creation can also instantly aggregate a large number of events into objects, streamline event presentation/storage, and speed up post-search.

In one embodiment, the image analysis device of the present invention can control the lens of the PTZ camera to follow the target object, and the PTZ indicates that the lens of the camera can be rotated left and right (Pan), up and down (Tile) and zoomed (Zoom). Features.

In one embodiment, the cluster management device has the capability of image analysis, and the cluster management device can perform the at least part of the work.

In one embodiment, the cluster management device of the present invention can be combined with the image analysis device, that is, the cluster management device can also have the function of the image analysis device of the present invention to reduce the cost of the system.

In one embodiment, the cluster management device of the present invention does not have the capability of image analysis.

In one embodiment, the tracking module of the image analysis device of the present invention includes at least one central processing unit (CPU).

In one embodiment, the tracking module of the image analysis device of the present invention includes at least one central processing unit (CPU) and at least one image processing unit (GPU) or an image processing hardware accelerator.

In one embodiment, the tracking module of the image analysis device of the present invention includes at least one central processing unit (CPU) and at least one image processing hardware accelerator.

Although the present invention has been described above with reference to the preferred embodiments thereof, it is not intended to limit the present invention, and anyone skilled in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of patent protection of the creation shall be subject to the definition of the scope of the patent application attached to this specification.

101‧‧‧Photographing device

102‧‧‧Photographing device

105‧‧‧Image analysis device

105a‧‧‧Image Analysis Module

106‧‧‧Image analysis device

106a‧‧‧Image Analysis Module

110‧‧‧Cluster Management Service Unit

110a‧‧‧Tracking module

201‧‧‧Photographing device

202‧‧‧Photographing device

203‧‧‧Photographing device

204‧‧‧Photographing device

205‧‧‧Image analysis device

205a‧‧‧Image Analysis Module

205b‧‧‧Image Analysis Module

206‧‧‧Image analysis device

206a‧‧‧Image Analysis Module

206b‧‧‧Image Analysis Module

210‧‧‧Cluster Management Service Unit

210a‧‧‧Tracking module

301‧‧‧Photographing device

302‧‧‧Photographing device

303‧‧‧Photographing device

304‧‧‧Photographing device

310‧‧‧Image analysis device

310a‧‧‧Image Analysis Module

310b‧‧‧Image Analysis Module

310c‧‧‧ Tracking Module

311‧‧‧Image analysis device

311a‧‧‧Image Analysis Module

311b‧‧‧Image Analysis Module

311c‧‧‧ Tracking Module

320‧‧‧Cluster Management Service Unit

320a‧‧‧ Tracking Module

401‧‧‧Photographing device

402‧‧‧Photographing device

403‧‧‧Photographing device

404‧‧‧Photographing device

411‧‧‧Image analysis device

412‧‧‧Image analysis device

421‧‧‧Image Analysis Device

422‧‧‧Image analysis device

431‧‧‧cross camera tracking device

431a‧‧‧Tracking Module

432‧‧‧cross camera tracking device

432a‧‧‧Tracking module

440‧‧‧Cluster Management Service Unit

440 a‧‧‧Tracking module

1 illustrates a schematic diagram of a distributed object tracking system in an embodiment of the present author. 2 illustrates a schematic diagram of a distributed object tracking system in an embodiment of the present author. 3 illustrates a schematic diagram of a distributed object tracking system in an embodiment of the present author. 4 illustrates a schematic diagram of a distributed object tracking system in an embodiment of the present author.

Claims (13)

A distributed object tracking system includes: a plurality of image analysis devices, wherein each image analysis device is coupled to at least one camera device to analyze an object in the at least one live image stream transmitted by the at least one camera device to generate a And a cluster management service device connected to the plurality of image analysis devices, wherein the cluster management service device is serially connected to each of the plurality of image analysis devices The analysis result of the at least one object being tracked to generate a trajectory of the at least one object being tracked. The distributed object tracking system of claim 1, wherein each image analyzing device is connected to a plurality of photographic devices to analyze objects in the plurality of instant image streams transmitted by the plurality of photographic devices to generate the a secondary trajectory of at least one object being tracked, wherein the cluster management service device cascades the trajectory generated by each of the plurality of image analysis devices to generate a trajectory of the at least one object being tracked. The distributed object tracking system of claim 1, wherein the at least one object comprises a person, and the analysis result includes the facial features of the person. The distributed item tracking system of claim 1, wherein the at least one item comprises a luggage, and the analysis result includes characteristics of the luggage. The distributed object tracking system of claim 1, wherein the plurality of image analysis devices are distributed in a detection area, wherein at least one specific item in the detection area is predetermined not to be tracked. The distributed object tracking system of claim 5, wherein the detection area comprises a station, and the station staff is scheduled not to be tracked. For example, in the distributed object tracking system described in claim 5, if a specific object in the detection area is not detected for more than a predetermined length of time, it is determined that the specific object has left the Detective. The area is known and will not be tracked by the multiple image analysis devices. The distributed object tracking system of claim 5, wherein if one of the detected areas continues to stay in a specific area of the detection area for more than a predetermined length of time, An abnormal stay event is issued. A distributed object tracking system includes: a first plurality of image analyzing devices, wherein each image analyzing device is coupled to at least one first photographing device to analyze at least one first instant transmitted by the at least one first photographing device An object in the image stream to generate a first analysis result of the at least one object being tracked; a first cross-camera tracking device coupled to the first plurality of image analysis devices, wherein the first cross-camera tracking device is connected in series a first analysis result of the tracked at least one object generated by each of the first plurality of image analysis devices to generate a first trajectory of the at least one object being tracked; An image analysis device, wherein each image analysis device analyzes and connects to the at least one second camera device to analyze the object in the at least one second live image stream transmitted by the at least one second camera device to generate the tracked at least a second analysis result of an object; a second cross-camera tracking device coupled to the second plurality of image analysis devices, wherein the second cross-photography The tracking device serially connects the second analysis result of the tracked at least one object generated by each of the second plurality of image analysis devices to generate a second track of the tracked at least one object; as well as a cluster management service device coupled to the first cross camera tracking device and the second cross camera tracking device to serially connect the first track and the second track of the at least one object. The distributed object tracking system of claim 9, wherein the distributed object tracking system tracks the target based on an image of the target. The distributed object tracking system of claim 9, wherein the first plurality of image analyzing devices are distributed in a first detecting area, and the second plurality of image analyzing devices are distributed in a second detecting The area is known, wherein at least one specific item in the first detection area and the second detection area is predetermined not to be tracked. The distributed object tracking system of claim 9, wherein the first plurality of image analyzing devices are distributed in a first detecting area, and the second plurality of image analyzing devices are distributed in a second detecting a region in which, if a specific object in all of the detection areas of the cluster management service device is not detected for more than a predetermined length of time, it is determined that the specific object has left the cluster management service device All the detection areas are no longer tracked by the first plurality of image analysis devices and the second plurality of image analysis devices. The distributed object tracking system of claim 9, wherein the first plurality of image analyzing devices are distributed in a first detecting area, and the second plurality of image analyzing devices are distributed in a second detecting An area in which an abnormal stay event is issued if a tracked item continues to stay in a particular area within all of the detected areas of the cluster management service device for more than a predetermined length of time.