TWI656512B - Image analysis system and method - Google Patents

Abstract

An image analysis system, the system includes a plurality of cameras for capturing images; at least one server, the server includes: a first acquisition module, configured to acquire a movement track of an object to be tracked; and a second acquisition mode a group, configured to acquire an image captured by a camera that the object to be tracked passes; and a filtering module, configured to filter, according to the specified image feature, the image to be tracked that includes the specified image feature An image of the object; and a storage module, configured to store the filtered image that includes the object to be tracked. The invention also provides an image analysis method.

Description

Image analysis system and method

The present invention relates to the field of image analysis, and more particularly to an image analysis system and method.

At present, it is necessary to analyze the type of action of the object to be tracked, and it is necessary to identify the object to be analyzed one by one from the images taken by each camera that the object to be tracked may pass, and the workload is large and easy to make a wrong judgment because the object to be tracked is similar to other object features.

In view of the above, it is necessary to provide an image analysis system and method that can solve the above problems.

An image analysis system, the image analysis system includes: a plurality of cameras for capturing images; at least one server, the server includes: a first acquisition module, configured to acquire a movement track of an object to be tracked; a acquiring module, configured to acquire, according to the moving trajectory, an image captured by a camera that is to be tracked by the camera; and a filtering module, configured to filter, according to the specified image feature, the included image from the acquired image An image of the object to be tracked of the specified image feature; and And a storage module, configured to store the filtered image that includes the object to be tracked.

An image analysis method, the method includes: acquiring a movement trajectory of a tracking object; acquiring an image captured by a camera through which the object to be tracked passes according to the movement trajectory; and acquiring the image according to the specified image feature An image of the object to be tracked including the specified image feature is filtered in the image; and the filtered image containing the object to be tracked is stored.

The system and method for analyzing an image according to a trajectory according to the present invention obtain an image including the object to be tracked according to the moving trajectory of the object to be tracked, thereby more accurately and efficiently analyzing the action type of the object to be tracked.

100‧‧‧Image Analysis System

10‧‧‧Server

20‧‧‧Camera

30‧‧‧ base station

101‧‧‧Setting module

102‧‧‧First acquisition module

103‧‧‧Second acquisition module

104‧‧‧Filter module

105‧‧‧Analysis module

106‧‧‧Judgement module

107‧‧‧Memory Module

200‧‧‧Electronic devices

1 is a system architecture diagram of a preferred embodiment of an image analysis system of the present invention.

2 is a functional block diagram of a preferred embodiment of the server of the present invention.

3 is a flow chart of a preferred embodiment of an image analysis method of the present invention.

The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

Referring to FIG. 1, a system architecture diagram of a preferred embodiment of the image analysis system 100 of the present invention is shown. The image analysis system 100 includes at least one server 10, a plurality of cameras 20, and a plurality of base stations 30. The server 10 can be a computer host. Each camera 20 is used to capture images with A network (not shown) is connected to the server 10. In the preferred embodiment, the base station 30 can be a base station or an access point (Bluetooth, WIFI, or ZigBee). The base station 30 connects to the server 10 via a network. The camera 20 can be installed indoors or outdoors, such as in a hospital, a supermarket, or a city road. The camera 20 located indoors is defined as an indoor camera, and the camera located outside is defined as an outdoor camera. The base station 30 is installed indoors, such as in a hospital or a supermarket.

In another embodiment, base station 30 and camera 20 in the same location may correspond to each other. The corresponding base station 30 and camera 20 can be combined into a single electronic device. That is, each base station 30 can include a corresponding one or more cameras 20, or each camera 20 can include a corresponding one or more base stations 30.

As shown in FIG. 2, the server 10 includes a setting module 101, a first obtaining module 102, a second obtaining module 103, a filtering module 104, an analyzing module 105, a determining module 106, and a storage module 107. . The module referred to in the present invention may be a program segment that performs a specific function.

In the preferred embodiment, the setting module 101 sets a target information for each indoor and outdoor camera 20 and each base station 30. The coordinate information includes position data of the camera 20 and the base station 30 in three axial directions of spatial positions X, Y, and Z. The coordinate information may also be location information from a satellite positioning system (eg, GPS: Global Positioning System).

In the preferred embodiment, the first obtaining module 102 is configured to acquire a moving track of an object to be tracked. The object to be tracked may be a person, a vehicle or other object. The movement trajectory includes an indoor movement trajectory and an outdoor movement trajectory.

The base station 30 is configured to acquire indoor location information of the object to be tracked and transmit the indoor location information to the server 10. The first acquiring module 102 obtains the indoor moving track of the object to be tracked according to the indoor location information received from the base station 30 and the corresponding receiving time. Specifically, the object to be tracked carries an electronic device 200, and the electronic device 200 transmits a wireless signal. The base station 30 detects the wireless signal, and further calculates the location information of the electronic device 200 according to the strength of the received wireless signal and the coordinate information of the base station 30 itself. The indoor position information is position data of the three axial directions of the object to be tracked in the space positions X, Y, and Z. During the moving of the object to be tracked, the spatial position data of the object to be tracked in the three axial directions of X, Y, and Z changes, that is, the spatial position data of the object to be tracked acquired by the base station 30 and Time related, changing over time. The server 10 arranges the indoor location information according to the indoor location information received from the base station 30 and in accordance with the order of receiving the indoor location information to obtain an indoor movement trajectory of the object to be tracked.

In this embodiment, the electronic device 200 may be a device having a satellite positioning function (for example, a GPS positioning function) such as a mobile phone, a tablet computer, or a wearable electronic device. The electronic device 200 has an identification code. The plurality of base stations 30 and the electronic device 200 can be wirelessly connected by a short-range wireless communication protocol such as Bluetooth, WIFI or ZigBee.

When the base station 30 is configured to acquire the indoor location information of the object to be tracked, the electronic device 200 is similar to a mobile signal point broadcast device, and the base station 30 receives the wireless signal transmitted by the electronic device 200 to calculate the location of the electronic device 200. A wireless signal transmitting source (not shown) may be disposed inside the electronic device 200. The wireless signal transmitting source may transmit a wireless signal of a preset frequency, and the base station 30 is internally provided with a wireless signal receiver (not shown), which can receive The wireless signal transmitted by the electronic device 200.

The server 10 may obtain an outdoor movement trajectory of the object to be tracked according to the outdoor location information sent by the electronic device 200 of the object to be tracked. The outdoor location information includes coordinate position data of the three axial directions of the object to be tracked in the spatial positions X, Y, and Z. During the moving of the object to be tracked, the data of the space coordinate position of the object to be tracked in the three axial directions of X, Y, and Z changes, that is, the space coordinate position data is related to time, with time. Variety. The electronic device 200 obtains the outdoor location information of the object to be tracked by the satellite positioning system, and sends the outdoor location information of the object to be tracked to the first acquisition module 102 in chronological order, and the server 10 And the outdoor location information is arranged according to the outdoor location information, and the outdoor location information of the object to be tracked is obtained according to a sequence of receiving time of the outdoor location information.

In the preferred embodiment, the second acquisition module 103 acquires an image captured by the camera 20 through which the object to be tracked passes according to the indoor and outdoor movement trajectories. The second acquisition module 103 compares the movement trajectory of the object to be tracked acquired by the first acquisition module 102 with the coordinate information of each camera 20, determines the camera 20 whose coordinate information is on the movement trajectory, and acquires the camera 20 Image. The image captured by the camera 20 can be instantly uploaded to the server 10 and stored in the storage module 107. The second acquisition module 103 can acquire the image record of the camera 20 through which the object to be tracked passes from the storage module 107.

In the preferred embodiment, the filtering module 104 filters the image of the object to be tracked including the specified image feature from the acquired image according to the specified image feature. The image features are pre-stored in the server 10. In other embodiments, the image feature may be input to the server 10 by an input device (not shown) such as a keyboard, a mouse, a touch screen or a microphone, or may be connected to the server. 10 communication is connected to other electronic devices, such as mobile phones, computers, etc., transmitted. When the object to be tracked is a person, the image features include, but are not limited to, a person's appearance, body type, and the like. When the object to be tracked is a vehicle, the image features include, but are not limited to, the color of the vehicle, the license plate number, and the like.

The analysis module 105 analyzes the action type of the object to be tracked according to the filtered image containing the object to be tracked. The image including the object to be tracked is an image record of the camera 20. The image record can be set to be updated in real time or set to be updated every other preset time period, that is, the server 10 can be set to receive the images of the plurality of cameras 20 in an instant, or can be set to receive more every other preset time. The images of the cameras 20, for example, receive images of the plurality of cameras 20 every ten minutes. The action type may be some action that the object to be tracked is performing. when When the object to be tracked is a person, the action type may be coughing, eating, drawing blood, withdrawing money, and the like. When the object to be tracked is a vehicle, the action type may be parking, fueling, or the like.

The judging module 106 judges whether the action type of the object to be tracked needs to be notified, and outputs the notification information when it is judged that the notification is needed. For example, the object to be tracked is an infected patient, and when it is analyzed that the infected patient is coughing, the notification information is output, and the relevant person is notified to handle the problem. The notification information may be voice warning information or text information. The relevant person may be a person who is pre-stored and needs to be notified of the association. Such related personnel include, but are not limited to, police officers, doctors, and the like.

The storage module 107 stores the filtered image including the object to be tracked, and the storage module 107 is further configured to store information related to the object to be tracked. The information related to the object to be tracked includes, but is not limited to, an identifier of the object to be tracked, time, location, type of action, and the like. The time and location may be the time and location at which the object to be tracked appears in the image, or may be the time and location at which the object to be tracked performs the action type in the image. The time is included in the image recording of the camera 20. The position is the position at which the camera 20 of the object to be tracked is photographed. The type of action is obtained by analysis by the analysis module 105. The identification code of the object to be tracked is associated with an identification code of the electronic device 200.

As shown in FIG. 3, a flow chart of a preferred embodiment of the method for analyzing images according to a trajectory according to the present invention is shown. The image analysis method includes the following steps:

Step S301, the setting module 101 sets a label information for each camera and each base station.

Step S302, the first acquiring module 102 acquires a moving track of the object to be tracked. The movement trajectory may be a continuous trajectory formed by coordinate positions of the object to be tracked at different times.

In step S303, the second obtaining module 103 acquires an image captured by the camera 20 through which the object to be tracked passes according to the moving track.

Step S304, the filtering module 104 filters, according to the specified image feature, the image of the object to be tracked including the specified image feature from the acquired image. The filtering module 104 filters the image of the object to be tracked that matches the pre-stored image feature according to the acquired image of the camera 20 on the moving track.

In step S305, the analysis module 105 analyzes the action type of the object to be tracked according to the filtered image containing the object to be tracked.

Step S306, the determining module 106 determines whether the action type of the object to be tracked needs to be notified, and outputs the notification information when it is determined that the notification needs to be notified. If it is determined that the action type of the object to be tracked does not need to be notified, the process proceeds to step S307.

Step S307, the storage module 107 stores the filtered image including the object to be tracked and information related to the object to be tracked.

In step S308, it is determined whether to continue tracking the object to be tracked, and when it is necessary to continue tracking, the process returns to step S302, and if it is determined that the tracking is not required to continue, the process ends.

In another embodiment, steps S305, S306 may be omitted to simplify the method of analyzing images from trajectories.

The image analysis system and method of the present invention obtains an image including the object to be tracked according to the indoor and outdoor movement trajectories of the object to be tracked, thereby more accurately and efficiently analyzing the action type of the object to be tracked.

In summary, the creation meets the requirements of the invention patent, and the patent application is filed according to law. However, the above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiments, and those skilled in the art will be equivalently modified or changed according to the spirit of the present invention. It should be covered by the following patent application.

Claims (10)

An image analysis system, the system comprising: a plurality of cameras for capturing images; at least one server, the server comprising: a setting module, configured to set a label information for each of the cameras; a module for acquiring a moving track of an object to be tracked; a second acquiring module, configured to compare the moving track with coordinate information of each camera, and acquire a camera captured by the camera with the coordinate information on the moving track And a filtering module, configured to filter, according to the specified image feature, an image of the object to be tracked that includes the specified image feature from the acquired image; and a storage module configured to store the filtered content An image of the object to be tracked; and an analysis module, configured to analyze, according to the filtered image of the object to be tracked, an action type of the object to be tracked; wherein the storage module is further configured to store Information related to the object to be tracked, the information related to the object to be tracked includes time and location of the object to be tracked, the time and location The execution time of the object to be tracked and the location of the mobile type in the image. The image analysis system of claim 1, wherein: the moving track comprises an indoor moving track, the image analyzing system further comprising: a plurality of base stations, wherein the base station is configured to acquire the indoor object to be tracked The first acquisition module obtains the indoor movement trajectory of the object to be tracked according to the indoor location information and the receiving time of the object to be tracked received from the base station. The image analysis system of claim 1, wherein: the movement track comprises an outdoor movement track, and the first acquisition module is further configured to receive and receive the outdoor position information according to the received object to be tracked. Time to get the outdoor moving track of the object to be tracked Trace, the outdoor location information is obtained by a satellite positioning system. The image analysis system of claim 1, wherein the server further comprises: a determining module, configured to determine whether the action type of the object to be tracked needs to be notified, and output when the device needs to be notified Notify the information. The image analysis system of claim 1, wherein the information related to the object to be tracked further includes an identification code of the object to be tracked and an action type. An image analysis method, the method comprising the steps of: setting a target information for each camera; acquiring a moving track of the object to be tracked; comparing the moving track with coordinate information of each camera, and acquiring coordinate information in the moving An image captured by the camera on the track; filtering, according to the specified image feature, an image of the object to be tracked including the specified image feature from the acquired image; and storing the filtered image to include the to-be-tracked The image analysis method further includes the steps of: analyzing the action type of the object to be tracked according to the filtered image including the object to be tracked; and storing information related to the object to be tracked The information related to the object to be tracked includes the time and location of the object to be tracked, and the time and location is the time and location at which the object to be tracked performs the action type in the image. The image analysis method of claim 6, wherein the image analysis method further comprises the step of: determining whether the action type of the object to be tracked needs to be notified. The image analysis method of claim 7, wherein the image analysis method further comprises the step of: outputting if the action type of the object to be tracked needs to be notified Notify the information. The image analysis method of claim 7, wherein the information related to the object to be tracked further includes an identification code of the object to be tracked and an action type. The image analysis method of claim 6, wherein the moving track comprises an indoor moving track and an outdoor moving track.