Event processing method, device, electronic device and storage medium

Abstract

The disclosed embodiments disclose an event processing method, apparatus, electronic device, and storage medium. The method comprises: receiving an event processing request; the event processing request includes the location of an event; controlling a target acquisition device at the event location to acquire first image data and recognize the first image data based on the event processing request; and returning the recognition result. This technical solution can proactively sense the actual event situation based on the event processing request and then return the recognition result. This process eliminates the need for manual call-up of acquisition devices to confirm the event, thus saving labor costs and improving event processing efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an event processing method, device, electronic device, and storage medium. Background Art

[0002] Currently, public video capture systems are deployed along major urban roads and in public areas, where computers replace human operators in identifying and tracking targets such as vehicles and people, as well as detecting unusual events. Computers primarily perform perception analysis based on deep learning algorithms based on the image data captured by these devices. However, traditional perception analysis methods employ a static model, where the system analyzes images frame by frame within a fixed field of view, and suspected events can only be confirmed manually. Summary of the Invention

[0003] Embodiments of the present disclosure provide an event processing method, device, electronic device, and computer-readable storage medium.

[0004] In a first aspect, an embodiment of the present disclosure provides an event processing method, including:

[0005] receiving an event processing request, wherein the event processing request includes an event occurrence location;

[0006] controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and identifying the first image data;

[0007] Returns the recognition result.

[0008] Furthermore, controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request and identifying the first image data includes:

[0009] A pre-deployed event processing interface is called so that the event processing interface mobilizes the target acquisition device to obtain the first image data and recognize the first image data according to the event processing request.

[0010] Furthermore, controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request includes:

[0011] Determine the collection information at the event occurrence location according to the event processing request; the collection information includes first indication information of the target collection device and second indication information of the target collection screen of the target collection device;

[0012] The first image data collected in the target acquisition screen of the target acquisition device is acquired.

[0013] Furthermore, determining the collected information at the location where the event occurred according to the event processing request includes:

[0014] The event occurrence location is mapped to a target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship.

[0015] Furthermore, the target acquisition device includes a device that reciprocates at multiple preset positions to capture images in sequence and / or at fixed time intervals, and the target area in the target acquisition screen includes the target area in the acquisition screen corresponding to at least one preset position of the target acquisition device.

[0016] Furthermore, it also includes:

[0017] When the target acquisition device is fixed at each preset position, acquiring second image data of the object from one end to the other end of the current acquisition screen from near to far or from far to near, and a position sequence of the object within the second image data;

[0018] The preset mapping relationship between the acquisition area and the position in the current acquisition picture is established according to the position sequence and the second image data.

[0019] Furthermore, it also includes:

[0020] Obtaining the acquisition area range of the target acquisition device in the acquisition picture corresponding to each preset position;

[0021] A preset interface of the navigation system is called to establish a preset mapping relationship between the position within the acquisition area and the acquisition area in the current acquisition picture.

[0022] Furthermore, determining the collected information at the location where the event occurred according to the event processing request includes:

[0023] Determining candidate areas involved in the location where the event occurred;

[0024] Determine a candidate acquisition device for acquiring image data in the candidate area and a candidate acquisition screen of the candidate acquisition device;

[0025] Acquire current image data captured in the candidate capture screen of the candidate capture device;

[0026] The target acquisition device and the target acquisition screen are determined by identifying the current image data.

[0027] Furthermore, obtaining the first image data collected in the target acquisition screen of the target acquisition device includes:

[0028] Determine the relative position of the event occurrence location in the target acquisition screen of the target acquisition device;

[0029] Dynamically adjust the acquisition mode of the target acquisition device according to the relative position;

[0030] The first image data acquired by the adjusted acquisition method is acquired.

[0031] Furthermore, obtaining the first image data collected in the target acquisition screen of the target acquisition device includes:

[0032] The current image data and the historical image data collected in the target acquisition screen of the target acquisition device are acquired.

[0033] Furthermore, the event processing request includes a suspected event reporting request from the navigation system, a manual reporting request from the terminal, and / or a reporting request generated by preliminarily identifying third image data at the location where the event occurred.

[0034] In a second aspect, an embodiment of the present invention provides an event processing method, including:

[0035] In response to the event reporting request, output a location input interface;

[0036] Obtaining the event location provided by the user through the location input interface;

[0037] calling a pre-deployed event processing interface so that the event processing interface mobilizes the target acquisition device to acquire the first image data according to the event occurrence location and identifies the first image data;

[0038] Output the recognition result returned by the server.

[0039] In a third aspect, an embodiment of the present invention provides an event processing device, including:

[0040] A receiving module configured to receive an event processing request; the event processing request includes an event occurrence location;

[0041] a control module configured to control a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and to identify the first image data;

[0042] The result returning module is configured to return the recognition result.

[0043] In a fourth aspect, an embodiment of the present invention provides an event processing device, including:

[0044] A first output module is configured to output a location input interface in response to an event reporting request;

[0045] An acquisition module configured to acquire the event occurrence location provided by the user through the location input interface;

[0046] a sending module configured to call a pre-deployed event processing interface so that the event processing interface mobilizes the target acquisition device to obtain the first image data according to the event occurrence location and recognizes the first image data;

[0047] The second output module is configured to output the recognition result returned by the server.

[0048] The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions.

[0049] In one possible design, the apparatus includes a memory and a processor. The memory is configured to store one or more computer instructions that enable the apparatus to perform the corresponding method, and the processor is configured to execute the computer instructions stored in the memory. The apparatus may also include a communication interface for communicating with other devices or a communication network.

[0050] In a fifth aspect, an embodiment of the present disclosure provides an electronic device comprising a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method described in any one of the above aspects.

[0051] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by any of the above-mentioned devices, which includes computer instructions involved in executing the method described in any of the above-mentioned aspects.

[0052] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0053] After receiving an event processing request including the location where an event occurred, the embodiment of the present disclosure locates the target acquisition device at the location where the event occurred according to the event processing request, obtains the first image data at the location where the event occurred, and then obtains the recognition result by recognizing the first image data. The embodiment of the present disclosure proposes an active perception solution for events, which can actively perceive the actual situation of the event according to the event processing request, and then return the recognition result. During the process, there is no need to manually call the acquisition device to confirm the event, which can save labor costs and improve event processing efficiency.

[0054] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0056] Figure 1 A flowchart showing an event processing method according to an embodiment of the present disclosure is shown;

[0057] Figure 2 A schematic diagram of a captured image after dynamically adjusting the camera capture mode according to an embodiment of the present disclosure is shown;

[0058] Figure 3 A schematic diagram of a traffic accident handling process according to an embodiment of the present disclosure is shown;

[0059] Figure 4 A schematic diagram of a software implementation architecture for traffic incident processing according to an embodiment of the present disclosure is shown;

[0060] Figure 5 A flowchart showing an event processing method according to another embodiment of the present disclosure is shown;

[0061] Figure 6 An event processing device according to an embodiment of the present disclosure is shown;

[0062] Figure 7 An event processing device according to another embodiment of the present disclosure is shown;

[0063] Figure 8 It is a structural diagram of an electronic device suitable for implementing the event processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0064] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0065] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts, or combinations thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof exist or are added.

[0066] It should also be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0067] In actual application scenarios, the inventors of this disclosure have noticed that dome cameras have good maneuverability and considerable freedom in both field of view and sensing distance. In most cases, after receiving an alert about a suspected incident at a specific location, personnel need to manually verify the actual situation using a dome camera.

[0068] To this end, the embodiment of the present disclosure proposes an event processing method, which includes: receiving an event processing request; the event processing request includes the location where the event occurred; controlling the target acquisition device at the location where the event occurred to obtain first image data and identifying the first image data according to the event processing request; and returning the identification result. After receiving the event processing request including the location where the event occurred, the embodiment of the present disclosure locates the target acquisition device at the location where the event occurred according to the event processing request, obtains the first image data at the location where the event occurred, and then obtains the identification result by identifying the first image data. The embodiment of the present disclosure proposes an active perception scheme for events, which can actively perceive the actual situation of the event according to the event processing request and then return the identification result. In the process, there is no need to manually call the acquisition device to confirm the event, which can save labor costs and improve event processing efficiency.

[0069] The details of the embodiments of the present disclosure are described in detail below through specific examples.

[0070] Figure 1 FIG. 1 is a flow chart showing an event processing method according to an embodiment of the present disclosure. Figure 1 As shown, the event handling method includes the following steps:

[0071] In step S101, an event processing request is received; the event processing request includes an event occurrence location;

[0072] In step S102, according to the event processing request, a target acquisition device at the event occurrence location is controlled to acquire first image data and identify the first image data;

[0073] In step S103, the recognition result is returned.

[0074] In this embodiment, an event can be any event that occurs at a certain location, such as a traffic incident, a crowd gathering incident, a violent incident, and the like. An event processing request can be a confirmation request for a suspected event received from outside the system, or a confirmation request for a suspected event received from inside the system. For example, the current map navigation system will relatively promptly analyze that some locations may have abnormalities (such as a sudden congestion on a clear section of a highway), etc. Therefore, the map navigation system can report the above abnormal events to the execution system of the embodiment of the present disclosure to confirm the authenticity of the event, the cause of the event, the current status, and subsequent processing progress and other event information; relevant personnel or systems such as traffic police or traffic management systems can also report event processing requests based on the information they have, so that they can obtain further confirmation and then take corresponding measures; individuals can also report corresponding event processing requests through the terminal to confirm the cause of the event, the current status, and subsequent processing progress and other event information.

[0075] The location where the event occurred can be relatively precise location information, such as a GPS address, or it can be an approximate area range. After receiving the event processing request, the target acquisition device at the location where the event occurred can be located according to the event processing request. In some embodiments, the target acquisition device can include one or more, and any acquisition device that can acquire image data at the location where the event occurred can be considered a target acquisition device. Of course, it is understandable that when the acquisition images of multiple target acquisition devices overlap, one or more of them can be selected as the target acquisition device according to actual needs, and no specific restrictions are made here.

[0076] In some embodiments, the target acquisition device can be a 3D spherical camera. The disclosed embodiments can leverage the spherical camera's 3D positioning capabilities to zoom in on the area of ​​a suspected event, dynamically adjust the field of view for more refined event perception, and purposefully perceive event information based on received event processing requests. Event processing requires no human intervention, with the system automatically performing perception when triggered by the event processing request.

[0077] After determining the target acquisition device, the target acquisition device can be activated to capture first image data, and then the actual event conditions at the event location can be identified based on the first image data. The first image data can be an image sequence, that is, a sequence of image frames in video data captured by the target acquisition device. If there are multiple target acquisition devices, the first image data can include multiple image sequences. The specific setting depends on actual circumstances and is not specifically limited here.

[0078] The recognition process for the first image data can vary depending on the event. For example, for a traffic incident, the vehicle and vehicle behavior in the first image data can be identified; for a violent incident, the person and person behavior in the first image data can be identified. In some embodiments, a pre-trained machine model can be used to recognize the first image data. This machine model can be trained using a deep learning algorithm.

[0079] Taking a traffic incident as an example, an identification process of the first image data is schematically illustrated: the first image data collected by the target acquisition device in the target acquisition screen is obtained, the first image data is decoded and processed, and then according to the area of ​​the event location in the first image data, it is determined whether it is necessary to call the target acquisition device to obtain clearer image data through the zoom function. After obtaining clearer image data of the incident location, the vehicles involved in the incident can be detected and tracked from the first image data through pre-trained target detection and tracking models, and the event recognition algorithm can also be used to obtain event recognition results.

[0080] In some embodiments, the recognition results may include, but are not limited to, the authenticity of the event, the location of the event, the time of the event, the cause of the event, the type of event, the progress of the event (e.g., whether it has been reported to the relevant department for processing), the location of the event, and the objects involved in the event (e.g., vehicles, people, surrounding information, etc.). After obtaining the recognition results, the recognition results can be returned to the requester of the event processing request, the preset processing party corresponding to the event type (e.g., the transportation department, the security department), etc.

[0081] After receiving an event processing request including the location where an event occurred, the embodiment of the present disclosure locates the target acquisition device at the location where the event occurred according to the event processing request, obtains the first image data at the location where the event occurred, and then obtains the recognition result by recognizing the first image data. The embodiment of the present disclosure proposes an active perception solution for events, which can actively perceive the actual situation of the event according to the event processing request, and then return the recognition result. During the process, there is no need to manually call the acquisition device to confirm the event, which can save labor costs and improve event processing efficiency.

[0082] In an optional implementation of this embodiment, step S102, i.e., the step of controlling the target acquisition device at the event occurrence location to acquire first image data and identifying the first image data according to the event processing request, further includes the following steps:

[0083] A pre-deployed event processing interface is called so that the event processing interface mobilizes the target acquisition device to obtain the first image data and recognize the first image data according to the event processing request.

[0084] In this optional implementation, the event processing interface can be deployed locally or in the cloud. The navigation system, relevant departments, individuals (if authorized), etc. can trigger the event processing interface by sending an event processing request when needed, so that the event processing interface can locate the target acquisition device at the location where the event occurred from a large number of acquisition devices according to the event processing request, and when the target acquisition device is a dynamic cruise acquisition device, it can further determine which acquisition screen of the target acquisition device the event location is in, and then automatically identify the event occurring at the location where the event occurred based on the image data collected by the acquisition screen. In this way, the event processing interface can be provided to individuals, departments, enterprises and other parties in need under the premise of compliance, and provide all parties with high-efficiency and high-accuracy event identification results.

[0085] In some embodiments, when a user requests to report an event processing request through a terminal, a user interface for receiving event processing requests can be displayed on the terminal. The user interface can provide an interface for inputting the location where the event occurred or an option for selecting the location where the event occurred. The user can directly input the location where the event occurred or select the location where the event occurred through the options provided by the user interface; the user interface can also provide event type options so that the user can select the type of event currently being reported.

[0086] After the event processing interface obtains the recognition result based on the event reporting request, it can return the recognition result to the terminal and display it on the user interface. The recognition result may include but is not limited to the authenticity of the event, the location of the event, the time of the event, the cause of the event, the event type, the progress of the event processing (such as whether it has been reported to the relevant department for processing, etc.), the event location, and the objects involved in the event (such as vehicles, people, surrounding information, etc.); in addition, the event processing interface can also return representative image data (including static images and dynamic image sequences) to the terminal. Afterwards, the progress of the event processing can be pushed to the terminal until the event is resolved.

[0087] In an optional implementation of this embodiment, step S102, i.e., controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, further includes the following steps:

[0088] Determine the collection information at the event occurrence location according to the event processing request; the collection information includes first indication information of the target collection device and second indication information of the target collection screen of the target collection device;

[0089] The first image data collected in the target acquisition screen of the target acquisition device is acquired.

[0090] In this optional implementation, after receiving an event processing request, a target acquisition device can be located from multiple data acquisition devices based on the event location included in the event processing request. For example, the areas covered by the acquisition screens of the multiple data acquisition devices can be pre-marked. After receiving the event processing request, the event location provided in the event processing request can be matched with the coverage areas of the acquisition devices, and the successfully matched device can be determined as the target acquisition device. It is understood that because the coverage areas of multiple acquisition devices may overlap or the event location spans multiple coverage areas, the target acquisition device ultimately determined may include multiple devices. The first indication information may include acquisition device identification information for identifying the target acquisition device. For image acquisition devices with automatic cruise control, such as spherical cameras, they automatically and continuously capture images between multiple preset points at time intervals. Therefore, after determining the target acquisition device, it is also possible to determine which preset point of the target acquisition device corresponds to the acquisition screen where the event location occurs. Therefore, the second indication information may include acquisition screen identification information for identifying the target acquisition screen in the target acquisition device. Of course, it is understood that for static image acquisition devices, there is only one acquisition screen, so the second indication information may be the identification information of that acquisition screen.

[0091] After the target acquisition device and the target acquisition screen are determined, the first image data acquired by the target acquisition device in the target acquisition screen can be obtained, and then the event recognition result can be obtained by analyzing and identifying the first image data.

[0092] In an optional implementation of this embodiment, determining the collected information at the event occurrence location according to the event processing request further includes the following steps:

[0093] The event occurrence location is mapped to a target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship.

[0094] In this optional implementation, a mapping relationship can be pre-established, comprising a mapping relationship between each region in the target acquisition image and the GPS location within the geographic area corresponding to the image actually captured by the target acquisition image. Each region can be a region within the image data captured by the target acquisition image, for example, a target acquisition image can capture image data for a few hundred meters ahead of a road, and each region can be obtained by dividing the image data within the few hundred meters of road. After receiving an event processing request, the event location carried in the event processing request can be located on the target region in the target acquisition image. For example, using a road traffic camera as an example, the camera's capture image at a preset position can cover an area several hundred meters ahead of a road, and the preset mapping relationship can include a correspondence between the region within the image of the road several hundred meters ahead and the GPS location. In this way, the specific area of ​​the target acquisition image where the event occurred can be located, and if necessary, the target acquisition device can be mobilized to change the acquisition method, for example, to expand the field of view to capture images from a farther distance.

[0095] In an optional implementation of this embodiment, the target acquisition device includes a device that reciprocates at multiple preset positions to capture images in sequence and / or at fixed time intervals, and the target area in the target acquisition screen includes the target area in the acquisition screen corresponding to at least one preset position of the target acquisition device.

[0096] In this optional implementation, the target acquisition device can be an acquisition device with an automatic cruise function, for example, it can be an acquisition device installed on a pan-tilt head, and its acquisition lens can reciprocate at various preset positions along with the pan-tilt head. The sequence relationship of multiple preset positions can be preset so that the target acquisition device reciprocates sequentially at the multiple preset positions and collects image data in real time; in addition, the target acquisition device can move to the multiple preset positions at fixed time intervals and collect image data. The target acquisition device can be, for example, a 3D spherical camera. By reciprocating at multiple preset positions in sequence and at fixed time intervals to collect images, it can obtain all-round image data and can also accurately locate and collect the first image data corresponding to the location where the event occurred.

[0097] In an optional implementation of this embodiment, the method further includes:

[0098] When the target acquisition device is fixed at each preset position, acquiring second image data of the object from one end to the other end of the current acquisition screen from near to far or from far to near, and a position sequence of the object within the second image data;

[0099] The preset mapping relationship between the acquisition area and the position in the current acquisition picture is established according to the position sequence and the second image data.

[0100] In this optional implementation, a preset mapping relationship corresponding to each acquisition device can be pre-established, and the position sequence can be a real geographic location sequence, such as a GPS position sequence. The preset mapping relationship can be established in a variety of ways. One way is that for an automatic cruise acquisition device with multiple preset positions, after the acquisition device is fixed at one of the preset positions, a collection vehicle carrying a GPS system can be driven from one end of the acquisition screen corresponding to the preset position to the other end, and then the acquisition device collects its complete driving video. Based on the second image data in the driving video and the GPS position collected by the GPS system, a pixel-level mapping relationship between the GPS position and the area in the acquisition screen is established through the association of time sequence information. For example, it can include but is not limited to the GPS position range covered by the acquisition screen and the relative position of the collected GPS position sequence within the area covered by the acquisition screen. For example, when the acquisition vehicle drives from near to far from the acquisition screen, the area covered by the acquisition screen is determined based on the GPS position obtained at the nearest end and the GPS position obtained at the farthest end, and the relative position of each GPS position relative to the acquisition screen is determined based on the time sequence information of the GPS position in the video data.

[0101] In an optional implementation of this embodiment, the method further includes:

[0102] Obtaining the acquisition area range of the target acquisition device in the acquisition picture corresponding to each preset position;

[0103] A preset interface of the navigation system is called to establish a preset mapping relationship between the position within the acquisition area and the acquisition area in the current acquisition picture.

[0104] In this optional implementation, another way to establish a preset mapping relationship is to first obtain the acquisition area range of the image data collected by each acquisition device in the acquisition picture corresponding to each preset position. For example, for a camera set up for road traffic, the road area range in the acquisition picture of the camera when it is preset can be obtained. In some embodiments, it can be obtained by manual drawing, and in other embodiments, it can also be obtained by acquiring images and identifying roads. Some navigation systems, such as AutoNavi Maps, usually provide an interface for binding GPS addresses. After obtaining the acquisition area range, the interface of the navigation system can be called to establish a mapping relationship between the acquisition area range and the GPS address within the acquisition area range. The mapping relationship can, for example, include but is not limited to the GPS position range covered by the acquisition area range, and the relative position of each GPS position within the acquisition area range.

[0105] In an optional implementation of this embodiment, the step of determining the collected information at the event occurrence location according to the event processing request further includes the following steps:

[0106] Determining candidate areas involved in the location where the event occurred;

[0107] Determine a candidate acquisition device for acquiring image data in the candidate area and a candidate acquisition screen of the candidate acquisition device;

[0108] Acquire current image data captured in the candidate capture screen of the candidate capture device;

[0109] The target acquisition device and the target acquisition screen are determined by identifying the current image data.

[0110] In this optional implementation, the location where the incident occurred can be a rough geographical range. For example, when an individual or a relevant department learns that a suspected incident may have occurred at a certain location, but is not sure of the GPS location coordinates of the location, a rough geographical range of the location can be given in the event handling request, such as location information of a certain section of a highway. In this case, the candidate acquisition device can be located according to the rough geographical range, and the positioning method can be based on a pre-established mapping relationship, which can include a mapping relationship between the acquisition device, the acquisition screen, and the geographical range covered by the image data collected by the acquisition screen. The candidate area is determined by the location where the incident occurred, that is, the geographical range involved in the location where the incident occurred, and then the candidate area is matched with the above-mentioned mapping relationship to obtain the candidate acquisition device and the candidate acquisition screen. If the geographical range given by the location where the incident occurred is large, multiple candidate acquisition devices and multiple candidate acquisition screens of the multiple candidate acquisition devices may be located. In order to accurately locate the target acquisition device and the target acquisition screen, the image data acquired by the multiple candidate acquisition screens of the multiple candidate acquisition devices can be obtained, and then the image data can be preliminarily identified using a pre-set algorithm. The preliminary identification can be a relatively rough identification process, which mainly identifies whether there is an abnormality from the image data. If an abnormality is identified, it can be considered that the location of the event is the location of the abnormality. Therefore, the candidate acquisition device and candidate acquisition screen corresponding to the image data with the identified abnormality can be determined as the target acquisition device and target acquisition screen. In this way, the party reporting the event processing request does not need to give the precise location of the event, but can give a rough geographical range, which can improve the scope of scenarios for the application of the embodiment of the present disclosure.

[0111] In an optional implementation of this embodiment, the step of acquiring the first image data captured in the target capture screen of the target capture device further includes the following steps:

[0112] Determine the relative position of the event occurrence location in the target acquisition image of the target acquisition device;

[0113] Dynamically adjust the acquisition mode of the target acquisition device according to the relative position;

[0114] The first image data acquired by the adjusted acquisition method is acquired.

[0115] In this optional implementation, after determining the target acquisition device and the target acquisition screen, since a single acquisition screen can capture image data hundreds of meters away, when the event location is located farther away from the field of view, it may not be possible to accurately identify relevant information from the image data captured in the current acquisition screen. Therefore, the acquisition method of the target acquisition device can be dynamically adjusted based on the relative position of the event location in the target acquisition screen. This acquisition method can be a zoom method. For example, when the event location is farther away from the target acquisition device, more accurate first image data at the event location can be obtained by magnifying the acquisition magnification, and then accurate recognition results can be obtained by recognizing this first image data.

[0116] Figure 2 FIG. 1 shows a schematic diagram of a captured image after dynamically adjusting the camera capture mode according to an embodiment of the present disclosure. Figure 2 As shown, in the image captured by the spherical camera, the initial perception field of view is short and does not capture information about the target vehicle. However, after determining the acquisition method using the method of the disclosed embodiment, the 3D spherical camera's zoom function can be used to adjust the perception field of view to the dynamic perception field of view shown in the figure, making the target vehicle appear in the spherical camera's capture image. In this way, the target vehicle's position can be dynamically perceived, and then its image data can be acquired and then identified, resulting in more accurate recognition results.

[0117] In an optional implementation of this embodiment, the step of acquiring the first image data captured in the target capture screen of the target capture device further includes the following steps:

[0118] The current image data and the historical image data collected in the target acquisition screen of the target acquisition device are acquired.

[0119] In this optional implementation, after the target acquisition device and the target acquisition screen are determined, the image frame sequence continuously captured by the target acquisition device in the target acquisition screen can be obtained and analyzed in real time. At the same time, if necessary, the historical image data captured by the target acquisition device and the target acquisition screen before and after receiving the event processing request can also be obtained. By analyzing and identifying the historical image data and the real-time image data, more accurate event recognition results can be obtained.

[0120] In an optional implementation of this embodiment, the event processing request includes a suspected event reporting request from the navigation system, a manual reporting request from the terminal and / or a reporting request generated by preliminarily identifying third image data at the location where the event occurred.

[0121] In this optional implementation, after receiving a suspected event such as a road congestion reported by a user, the navigation system reports an event processing request to the system so that the system can execute the event processing method proposed in the embodiment of the present disclosure to identify the true situation of the event. Individuals or relevant departments can also report event processing requests for suspected events to the system through the terminal. For example, after encountering a traffic congestion, a vehicle occupant reports an event processing request to the system in order to understand the situation of the accident ahead, so as to understand the current traffic congestion event situation and the subsequent processing progress, so as to decide whether to change lanes. The traffic department can also determine the cause of the traffic incident, the vehicle involved, and other related information by reporting the event processing request. In addition, the system can also set up a special processing module for performing simple recognition processing on the video data collected in real time by the acquisition device. When a suspected event such as vehicle congestion or highway parking is initially identified in the current video data, an event processing request can be reported based on the acquisition location of the current video data so that further event details can be obtained through the method of the embodiment of the present disclosure. After obtaining the recognition result, an alarm can be issued.

[0122] Figure 3 FIG. 1 shows a flow chart of a traffic accident handling process according to an embodiment of the present disclosure. Figure 3 As shown, after learning that a traffic accident occurred at position B of road A, the requester 301 reports an event processing request to the event processing server 302, and the event processing request includes the location where the accident occurred, that is, the information of position B of road A; after receiving the event processing request, the event processing server 302 locates the target camera 304 used to collect image data at position B of road A from a large number of traffic road cameras based on the pre-established mapping relationship between the position and the acquisition screen covered by the camera, and obtains the current image data of position B of road A collected by the target camera 304 from the camera management server 303 that manages the cameras, as well as the historical image data of position B of road A collected before and after receiving the event processing request. The event processing server 302 uses the pre-trained deep learning machine model to recognize the obtained image data, and returns the obtained recognition result to the requester 301.

[0123] Figure 4 FIG. 1 is a schematic diagram showing a software implementation architecture for traffic incident processing according to an embodiment of the present disclosure. Figure 4As shown, the software implementation architecture includes an input layer, a processing layer, and an output layer. The input layer includes real-time video stream data obtained from the camera. The processing layer includes a cruise control part and a video analysis part. The cruise control part is mainly designed to implement the event processing method of the embodiment of the present disclosure. The cruise control part includes a geographic location mapping module, an event monitoring module, and an ROI (location of interest) region positioning module. The geographic location mapping module is used to manage the mapping relationship between the geographic location and the region in the captured image. It is also used to map the event location carried in the event processing request to the target region in the target acquisition image of the target acquisition device after receiving the event processing request. The event monitoring module is used to monitor the event processing request reported by the requesting party, such as a navigation system. The ROI region positioning module can find the target object of interest, such as a target vehicle, from the target region in the target acquisition image of the target acquisition device by dynamically adjusting the camera's image acquisition method, and then collect image data based on the region where the target object is located. The video analysis part can integrate modules of traditional traffic event management systems, such as video decoding modules, vehicle detection modules, and vehicle tracking modules. Among them, the video analysis part can also include a 3D Zoom / ROI module and an event recognition algorithm module. The functions that can be realized by the 3D Zoom / ROI module include being designed for 3D spherical cameras to control the 3D spherical camera to locate the location of the event through the zoom function, thereby accurately collecting video data at the location of the event; the event recognition algorithm module is used to automatically identify event information based on the collected video data, without the need for human eyes to recognize events.

[0124] Figure 5 FIG. 1 is a flow chart showing an event processing method according to another embodiment of the present disclosure. Figure 5 As shown, the event handling method includes the following steps:

[0125] In step S501, in response to the event reporting request, a location input interface is output;

[0126] In step S502, the event location provided by the user through the location input interface is obtained;

[0127] In step S503, a pre-deployed event processing interface is called, so that the event processing interface mobilizes the target acquisition device to obtain the first image data according to the event occurrence location, and recognizes the first image data;

[0128] In step S504, the recognition result returned by the event processing interface is output.

[0129] In this embodiment, the event may be any event occurring at a certain location, such as a traffic incident, a crowd gathering incident, a violent incident, etc. The event processing method in this embodiment may be executed on a user terminal.

[0130] The embodiment of the present disclosure can deploy an event processing interface on a user terminal or a cloud server. When necessary, relevant personnel can send the location of the event through the event reporting interface provided on the user terminal to trigger the event processing interface, and the event processing interface can locate the target acquisition device at the location of the event from among a large number of acquisition devices. When the target acquisition device is a dynamic cruise acquisition device, it can further determine in which acquisition screen of the target acquisition device the event location is located, and then automatically identify the event occurring at the event location based on the image data collected by the acquisition screen.

[0131] The user opens the event reporting interface through the user terminal. The event reporting interface can provide a location input interface for the event location. The user can manually enter the event location or automatically locate the location near the user by clicking on the map provided by the interface, and the user clicks on the event location. After the user provides the event location through the location input interface, the event location is provided to the user terminal by clicking the corresponding button. The user terminal calls the locally deployed event processing interface or sends an event processing request including the event location to the remote server. After receiving the event processing request, the cloud server can call the event processing interface; the event processing interface can perform event recognition based on the received event location. The specific recognition process can be found in the above Figure 1 The descriptions in the illustrated embodiment and related embodiments will not be repeated here.

[0132] The event processing interface returns the recognition results to the user terminal. The recognition results may include but are not limited to the authenticity of the event, the location of the event, the time of the event, the cause of the event, the event type, the progress of the event processing (such as whether it has been reported to the relevant department for processing), the event location, and the objects involved in the event (such as vehicles, people, surrounding information, etc.). In addition, the event processing interface can also return representative image data (including static images and dynamic image sequences) to the user terminal. Afterwards, the progress of the event processing can be pushed to the user terminal until the event is resolved.

[0133] The user terminal can output the received recognition results to the user. For example, the event recognition results can be displayed in a visual manner on the display interface of the user terminal, and the event recognition results can also be output to the user through voice broadcast or information push.

[0134] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein.

[0135] Figure 6 FIG. 1 shows an event processing device according to an embodiment of the present disclosure. Figure 6 As shown, the device can be implemented as part or all of the electronic device through software, hardware or a combination of both. The event processing device includes:

[0136] The receiving module 601 is configured to receive an event processing request; the event processing request includes an event occurrence location;

[0137] The control module 602 is configured to control the target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and identify the first image data;

[0138] The result returning module 603 is configured to return the recognition result.

[0139] In this embodiment, an event can be any event that occurs at a certain location, such as a traffic incident, a crowd gathering incident, a violent incident, and the like. An event processing request can be a confirmation request for a suspected event received from outside the system, or a confirmation request for a suspected event received from inside the system. For example, the current map navigation system will relatively promptly analyze that some locations may have abnormalities (such as a sudden congestion on a clear section of a highway), etc. Therefore, the map navigation system can report the above abnormal events to the execution system of the embodiment of the present disclosure to confirm the authenticity of the event, the cause of the event, the current status, and subsequent processing progress and other event information; relevant personnel or systems such as traffic police or traffic management systems can also report event processing requests based on the information they have, so that they can obtain further confirmation and then take corresponding measures; individuals can also report corresponding event processing requests through the terminal to confirm the cause of the event, the current status, and subsequent processing progress and other event information.

[0140] The location where the event occurred can be relatively precise location information, such as a GPS address, or it can be an approximate area range. After receiving the event processing request, the target acquisition device at the location where the event occurred can be located according to the event processing request. In some embodiments, the target acquisition device can include one or more, and any acquisition device that can acquire image data at the location where the event occurred can be considered a target acquisition device. Of course, it is understandable that when the acquisition images of multiple target acquisition devices overlap, one or more of them can be selected as the target acquisition device according to actual needs, and no specific restrictions are made here.

[0141] In some embodiments, the target acquisition device can be a 3D spherical camera. The disclosed embodiments can leverage the spherical camera's 3D positioning capabilities to zoom in on the area of ​​a suspected event, dynamically adjust the field of view for more refined event perception, and purposefully perceive event information based on received event processing requests. Event processing requires no human intervention, with the system automatically performing perception when triggered by the event processing request.

[0142] After determining the target acquisition device, the target acquisition device can be activated to capture first image data, and then the actual event conditions at the event location can be identified based on the first image data. The first image data can be an image sequence, that is, a sequence of image frames in video data captured by the target acquisition device. If there are multiple target acquisition devices, the first image data can include multiple image sequences. The specific setting depends on actual circumstances and is not specifically limited here.

[0143] The recognition process for the first image data can vary depending on the event. For example, for a traffic incident, the vehicle and vehicle behavior in the first image data can be identified; for a violent incident, the person and person behavior in the first image data can be identified. In some embodiments, a pre-trained machine model can be used to recognize the first image data. This machine model can be trained using a deep learning algorithm.

[0144] Taking a traffic incident as an example, an identification process of the first image data is schematically illustrated: the first image data collected by the target acquisition device in the target acquisition screen is obtained, the first image data is decoded and processed, and then according to the area of ​​the event location in the first image data, it is determined whether it is necessary to call the target acquisition device to obtain clearer image data through the zoom function. After obtaining clearer image data of the incident location, the vehicles involved in the incident can be detected and tracked from the first image data through pre-trained target detection and tracking models, and the event recognition algorithm can also be used to obtain event recognition results.

[0145] In some embodiments, the recognition results may include, but are not limited to, the authenticity of the event, the location of the event, the time of the event, the cause of the event, the type of event, the progress of the event (e.g., whether it has been reported to the relevant department for processing), the location of the event, and the objects involved in the event (e.g., vehicles, people, surrounding information, etc.). After obtaining the recognition results, the recognition results can be returned to the requester of the event processing request, the preset processing party corresponding to the event type (e.g., the transportation department, the security department), etc.

[0146] After receiving an event processing request including the location where an event occurred, the embodiment of the present disclosure locates the target acquisition device at the location where the event occurred according to the event processing request, obtains the first image data at the location where the event occurred, and then obtains the recognition result by recognizing the first image data. The embodiment of the present disclosure proposes an active perception solution for events, which can actively perceive the actual situation of the event according to the event processing request, and then return the recognition result. During the process, there is no need to manually call the acquisition device to confirm the event, which can save labor costs and improve event processing efficiency.

[0147] In an optional implementation of this embodiment, the control module 602 includes:

[0148] The calling submodule is configured to call a pre-deployed event processing interface so that the event processing interface mobilizes the target acquisition device to obtain the first image data according to the event processing request and recognize the first image data.

[0149] In an optional implementation of this embodiment, the control module 602 includes:

[0150] A first determining submodule is configured to determine, according to the event processing request, the collection information at the location where the event occurs; the collection information includes first indication information of the target collection device and second indication information of the target collection screen of the target collection device;

[0151] The first acquisition submodule is configured to acquire the first image data captured in the target acquisition screen of the target acquisition device.

[0152] In this optional implementation, after receiving an event processing request, a target acquisition device can be located from multiple data acquisition devices based on the event location included in the event processing request. For example, the areas covered by the acquisition screens of the multiple data acquisition devices can be pre-marked. After receiving the event processing request, the event location provided in the event processing request can be matched with the coverage areas of the acquisition devices, and the successfully matched device can be determined as the target acquisition device. It is understood that because the coverage areas of multiple acquisition devices may overlap or the event location spans multiple coverage areas, the target acquisition device ultimately determined may include multiple devices. The first indication information may include acquisition device identification information for identifying the target acquisition device. For image acquisition devices with automatic cruise control, such as spherical cameras, they automatically and continuously capture images between multiple preset points at time intervals. Therefore, after determining the target acquisition device, it is also possible to determine which preset point of the target acquisition device corresponds to the acquisition screen where the event location occurs. Therefore, the second indication information may include acquisition screen identification information for identifying the target acquisition screen in the target acquisition device. Of course, it is understood that for static image acquisition devices, there is only one acquisition screen, so the second indication information may be the identification information of that acquisition screen.

[0153] After the target acquisition device and the target acquisition screen are determined, the first image data acquired by the target acquisition device in the target acquisition screen can be obtained, and then the event recognition result can be obtained by analyzing and identifying the first image data.

[0154] In an optional implementation of this embodiment, the first determining submodule includes:

[0155] The mapping submodule is configured to map the event occurrence location to a target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship.

[0156] In this optional implementation, a mapping relationship can be pre-established, comprising a mapping relationship between each region in the target acquisition image and the GPS location within the geographic area corresponding to the image actually captured by the target acquisition image. Each region can be a region within the image data captured by the target acquisition image, for example, a target acquisition image can capture image data for a few hundred meters ahead of a road, and each region can be obtained by dividing the image data within the few hundred meters of road. After receiving an event processing request, the event location carried in the event processing request can be located on the target region in the target acquisition image. For example, using a road traffic camera as an example, the camera's capture image at a preset position can cover an area several hundred meters ahead of a road, and the preset mapping relationship can include a correspondence between the region within the image of the road several hundred meters ahead and the GPS location. In this way, the specific area of ​​the target acquisition image where the event occurred can be located, and if necessary, the target acquisition device can be mobilized to change the acquisition method, for example, to expand the field of view to capture images from a farther distance.

[0157] In an optional implementation of this embodiment, the target acquisition device includes a device that reciprocates at multiple preset positions to capture images in sequence and / or at fixed time intervals, and the target area in the target acquisition screen includes the target area in the acquisition screen corresponding to at least one preset position of the target acquisition device.

[0158] In this optional implementation, the target acquisition device can be an acquisition device with an automatic cruise function, for example, it can be an acquisition device installed on a pan-tilt head, and its acquisition lens can reciprocate at various preset positions along with the pan-tilt head. The sequence relationship of multiple preset positions can be preset so that the target acquisition device reciprocates sequentially at the multiple preset positions and collects image data in real time; in addition, the target acquisition device can move to the multiple preset positions at fixed time intervals and collect image data. The target acquisition device can be, for example, a 3D spherical camera. By reciprocating at multiple preset positions in sequence and at fixed time intervals to collect images, it can obtain all-round image data and can also accurately locate and collect the first image data corresponding to the location where the event occurred.

[0159] In an optional implementation of this embodiment, the apparatus further includes:

[0160] a first acquisition module configured to acquire, when the target acquisition device is fixed at each preset position, second image data of the object from one end to the other end of the current acquisition screen from near to far or from far to near, and a position sequence of the object within the second image data;

[0161] The first establishing module is configured to establish the preset mapping relationship between the acquisition area and the position in the current acquisition picture according to the position sequence and the second image data.

[0162] In this optional implementation, a preset mapping relationship corresponding to each acquisition device can be pre-established, and the position sequence can be a real geographic location sequence, such as a GPS position sequence. The preset mapping relationship can be established in a variety of ways. One way is that for an automatic cruise acquisition device with multiple preset positions, after the acquisition device is fixed at one of the preset positions, a collection vehicle carrying a GPS system can be driven from one end of the acquisition screen corresponding to the preset position to the other end, and then the acquisition device collects its complete driving video. Based on the second image data in the driving video and the GPS position collected by the GPS system, a pixel-level mapping relationship between the GPS position and the area in the acquisition screen is established through the association of time sequence information. For example, it can include but is not limited to the GPS position range covered by the acquisition screen and the relative position of the collected GPS position sequence within the area covered by the acquisition screen. For example, when the acquisition vehicle drives from near to far from the acquisition screen, the area covered by the acquisition screen is determined based on the GPS position obtained at the nearest end and the GPS position obtained at the farthest end, and the relative position of each GPS position relative to the acquisition screen is determined based on the time sequence information of the GPS position in the video data.

[0163] In an optional implementation of this embodiment, the apparatus further includes:

[0164] The second acquisition module is configured to obtain the acquisition area range of the target acquisition device in the acquisition picture corresponding to each preset position;

[0165] The second establishing module is configured to call a preset interface of the navigation system to establish a preset mapping relationship between the position within the acquisition area and the acquisition area in the current acquisition picture.

[0166] In this optional implementation, another way to establish a preset mapping relationship is to first obtain the acquisition area range of the image data collected by each acquisition device in the acquisition picture corresponding to each preset position. For example, for a camera set up for road traffic, the road area range in the acquisition picture of the camera when it is preset can be obtained. In some embodiments, it can be obtained by manual drawing, and in other embodiments, it can also be obtained by acquiring images and identifying roads. Some navigation systems, such as AutoNavi Maps, usually provide an interface for binding GPS addresses. After obtaining the acquisition area range, the interface of the navigation system can be called to establish a mapping relationship between the acquisition area range and the GPS address within the acquisition area range. The mapping relationship can, for example, include but is not limited to the GPS position range covered by the acquisition area range, and the relative position of each GPS position within the acquisition area range.

[0167] In an optional implementation of this embodiment, the first determining submodule includes:

[0168] A second determining submodule is configured to determine a candidate area involved in the event occurrence location;

[0169] A third determining submodule is configured to determine a candidate acquisition device for acquiring image data in the candidate area and a candidate acquisition screen of the candidate acquisition device;

[0170] A second acquisition submodule is configured to acquire current image data captured in the candidate acquisition screen of the candidate acquisition device;

[0171] The fourth determination submodule is configured to determine the target acquisition device and the target acquisition screen by identifying the current image data.

[0172] In this optional implementation, the location where the incident occurred can be a rough geographical range. For example, when an individual or a relevant department learns that a suspected incident may have occurred at a certain location, but is not sure of the GPS location coordinates of the location, a rough geographical range of the location can be given in the event handling request, such as location information of a certain section of a highway. In this case, the candidate acquisition device can be located according to the rough geographical range, and the positioning method can be based on a pre-established mapping relationship, which can include a mapping relationship between the acquisition device, the acquisition screen, and the geographical range covered by the image data collected by the acquisition screen. The candidate area is determined by the location where the incident occurred, that is, the geographical range involved in the location where the incident occurred, and then the candidate area is matched with the above-mentioned mapping relationship to obtain the candidate acquisition device and the candidate acquisition screen. If the geographical range given by the location where the incident occurred is large, multiple candidate acquisition devices and multiple candidate acquisition screens of the multiple candidate acquisition devices may be located. In order to accurately locate the target acquisition device and the target acquisition screen, the image data acquired by the multiple candidate acquisition screens of the multiple candidate acquisition devices can be obtained, and then the image data can be preliminarily identified using a pre-set algorithm. The preliminary identification can be a relatively rough identification process, which mainly identifies whether there is an abnormality from the image data. If an abnormality is identified, it can be considered that the location of the event is the location of the abnormality. Therefore, the candidate acquisition device and candidate acquisition screen corresponding to the image data with the identified abnormality can be determined as the target acquisition device and target acquisition screen. In this way, the party reporting the event processing request does not need to give the precise location of the event, but can give a rough geographical range, which can improve the scope of scenarios for the application of the embodiment of the present disclosure.

[0173] In an optional implementation of this embodiment, the first acquisition submodule includes:

[0174] A fifth determining submodule is configured to determine a relative position of the event occurrence location in the target acquisition screen of the target acquisition device;

[0175] an adjusting submodule, configured to dynamically adjust a collection mode of the target collection device according to the relative position;

[0176] The third acquisition submodule is configured to acquire the first image data acquired by the adjusted acquisition method.

[0177] In this optional implementation, after determining the target acquisition device and the target acquisition screen, since a single acquisition screen can capture image data hundreds of meters away, when the event location is located farther away from the field of view, it may not be possible to accurately identify relevant information from the image data captured in the current acquisition screen. Therefore, the acquisition method of the target acquisition device can be dynamically adjusted based on the relative position of the event location in the target acquisition screen. This acquisition method can be a zoom method. For example, when the event location is farther away from the target acquisition device, more accurate first image data at the event location can be obtained by magnifying the acquisition magnification, and then accurate recognition results can be obtained by recognizing this first image data.

[0178] In an optional implementation of this embodiment, the first acquisition submodule includes:

[0179] The fourth acquisition submodule is configured to acquire current image data and historical image data collected in the target acquisition screen of the target acquisition device.

[0180] In this optional implementation, after the target acquisition device and the target acquisition screen are determined, the image frame sequence continuously captured by the target acquisition device in the target acquisition screen can be obtained and analyzed in real time. At the same time, if necessary, the historical image data captured by the target acquisition device and the target acquisition screen before and after receiving the event processing request can also be obtained. By analyzing and identifying the historical image data and the real-time image data, more accurate event recognition results can be obtained.

[0181] In an optional implementation of this embodiment, the event processing request includes a suspected event reporting request from the navigation system, a manual reporting request from the terminal and / or a reporting request generated by preliminarily identifying third image data at the location where the event occurred.

[0182] In this optional implementation, after receiving a suspected event such as a road congestion reported by a user, the navigation system reports an event processing request to the system so that the system can execute the event processing method proposed in the embodiment of the present disclosure to identify the true situation of the event. Individuals or relevant departments can also report event processing requests for suspected events to the system through the terminal. For example, after encountering a traffic congestion, a vehicle occupant reports an event processing request to the system in order to understand the situation of the accident ahead, so as to understand the current traffic congestion event situation and the subsequent processing progress, so as to decide whether to change lanes. The traffic department can also determine the cause of the traffic incident, the vehicle involved, and other related information by reporting the event processing request. In addition, the system can also set up a special processing module for performing simple recognition processing on the video data collected in real time by the acquisition device. When a suspected event such as vehicle congestion or highway parking is initially identified in the current video data, an event processing request can be reported based on the acquisition location of the current video data so that further event details can be obtained through the method of the embodiment of the present disclosure. After obtaining the recognition result, an alarm can be issued.

[0183] The technical details of the above optional implementations can be found in the above description of the event handling method and will not be repeated here.

[0184] Figure 7 FIG. 2 shows an event processing device according to another embodiment of the present disclosure. Figure 7 As shown, the device can be implemented as part or all of the electronic device through software, hardware or a combination of both. The event processing device includes:

[0185] The first output module 701 is configured to output a location input interface in response to an event reporting request;

[0186] An acquisition module 702 is configured to acquire the event location provided by the user through the location input interface;

[0187] The calling module 703 is configured to call a pre-deployed event processing interface so that the event processing interface mobilizes the target acquisition device to obtain the first image data according to the event occurrence location and recognize the first image data;

[0188] The second output module 704 is configured to output the recognition result returned by the server.

[0189] The event processing device in this embodiment is Figure 5 The event processing methods in the illustrated embodiments correspond to each other. For specific details, please refer to the above description of the event processing method, which will not be repeated here.

[0190] Figure 8It is a structural diagram of an electronic device suitable for implementing the event processing method according to an embodiment of the present disclosure.

[0191] like Figure 8 As shown, the electronic device 800 includes a processing unit 801, which can be implemented as a processing unit such as a CPU, a GPU, an FPGA, an NPU, etc. The processing unit 801 can perform various processes in the embodiment of any of the above methods of the present disclosure according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0192] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, and the like; an output section 807 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 808 including a hard disk; and a communication section 809 including a network interface card such as a LAN card or a modem. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 810 as needed, so that computer programs read therefrom can be installed into the storage section 808 as needed.

[0193] In particular, according to embodiments of the present disclosure, any of the methods described above with reference to the embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a computer-readable medium, the computer program comprising program code for executing any of the methods described in the embodiments of the present disclosure. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 809 and / or installed from a removable medium 811.

[0194] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the diagram or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, as well as the combination of boxes in the block diagram and / or flow chart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0195] The units or modules described in the embodiments of the present disclosure may be implemented in software or hardware. The units or modules described may also be provided in a processor, and the names of these units or modules do not, in certain circumstances, limit the units or modules themselves.

[0196] As another aspect, the present disclosure further provides a computer-readable storage medium. This computer-readable storage medium may be included in the apparatus described in the above embodiments, or may be a standalone computer-readable storage medium not incorporated into the apparatus. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the methods described in the present disclosure.

[0197] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

1. An event processing method, wherein: include: Receive event processing requests; The event processing request includes the location where the event occurred; controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and identifying the first image data; Return the recognition result; Controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request includes: Determining, according to the event processing request, acquisition information at the location where the event occurred; the acquisition information includes first indication information of the target acquisition device and second indication information of the target acquisition screen of the target acquisition device; the target acquisition device includes a device that reciprocates to acquire images at a plurality of preset positions in a sequential manner and / or at fixed time intervals; the second indication information includes acquisition screen identification information for identifying the target acquisition screen in the target acquisition device; Acquire the first image data captured in the target acquisition screen of the target acquisition device; Determining, according to the event processing request, collected information at the location where the event occurred, including: The event location is mapped to the target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship, wherein the preset mapping relationship refers to the preset mapping relationship between the acquisition area and its geographical location in the current acquisition screen of the target acquisition device at each preset position.

2. The method according to claim 1, wherein Controlling a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and identifying the first image data, including: A pre-deployed event processing interface is called so that the event processing interface mobilizes the target acquisition device to obtain the first image data and recognize the first image data according to the event processing request.

3. The method according to claim 1, wherein The target area in the target acquisition picture includes the target area in the acquisition picture corresponding to at least one preset position of the target acquisition device.

4. The method according to claim 3, further comprising: When the target acquisition device is fixed at each preset position, acquiring second image data of the object from one end to the other end of the current acquisition screen from near to far or from far to near, and a position sequence of the object within the second image data; The preset mapping relationship between the acquisition area and the position in the current acquisition picture is established according to the position sequence and the second image data.

5. The method according to claim 4, further comprising: Obtaining the acquisition area range of the target acquisition device in the acquisition picture corresponding to each preset position; A preset interface of the navigation system is called to establish a preset mapping relationship between the position within the acquisition area and the acquisition area in the current acquisition picture.

6. The method according to claim 1, wherein Determining, according to the event processing request, collected information at the location where the event occurred, including: Determining candidate areas involved in the location where the event occurred; Determine a candidate acquisition device for acquiring image data in the candidate area and a candidate acquisition screen of the candidate acquisition device; Acquire current image data captured in the candidate capture screen of the candidate capture device; The target acquisition device and the target acquisition screen are determined by identifying the current image data.

7. The method according to claim 1, wherein Acquiring the first image data collected in the target acquisition screen of the target acquisition device includes: Determine the relative position of the event occurrence location in the target acquisition screen of the target acquisition device; Dynamically adjust the acquisition mode of the target acquisition device according to the relative position; The first image data acquired by the adjusted acquisition method is acquired.

8. The method according to claim 1, wherein Acquiring the first image data collected in the target acquisition screen of the target acquisition device includes: The current image data and the historical image data collected in the target acquisition screen of the target acquisition device are acquired.

9. The method according to any one of claims 1 to 8, wherein: The event processing request includes a suspected event reporting request from the navigation system, a manual reporting request from the terminal, and / or a reporting request generated by preliminarily identifying third image data at the location where the event occurred.

10. An event processing method, wherein: include: In response to the event reporting request, output a location input interface; Obtaining the event location provided by the user through the location input interface; Calling a pre-deployed event processing interface so that the event processing interface mobilizes a target acquisition device to acquire first image data according to the event occurrence location and identifies the first image data; Output the recognition results returned by the server; The method further comprises: Determining, based on an event processing request, acquisition information at the location where the event occurred, wherein the event processing request includes the location where the event occurred; the acquisition information includes first indication information of the target acquisition device and second indication information of a target acquisition screen of the target acquisition device; the target acquisition device includes a device that reciprocates in a sequential manner and / or at fixed time intervals at a plurality of preset positions to acquire images; and the second indication information includes acquisition screen identification information for identifying a target acquisition screen in the target acquisition device; Acquire the first image data captured in the target acquisition screen of the target acquisition device; Determining, according to the event processing request, collected information at the location where the event occurred, including: The event location is mapped to the target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship, wherein the preset mapping relationship refers to the preset mapping relationship between the acquisition area and its geographical location in the current acquisition screen of the target acquisition device at each preset position.

11. An event processing device, wherein: include: A receiving module configured to receive an event processing request; The event processing request includes the location where the event occurred; a control module configured to control a target acquisition device at the event occurrence location to acquire first image data according to the event processing request, and to identify the first image data; A result returning module configured to return a recognition result; Control module, including: a first determining submodule configured to determine, based on an event processing request, acquisition information at a location where the event occurred; the acquisition information comprising first indication information of a target acquisition device and second indication information of a target acquisition screen of the target acquisition device; the target acquisition device comprising a device that reciprocates to acquire images at a plurality of preset positions in a sequential manner and / or at fixed time intervals; and the second indication information comprising acquisition screen identification information for identifying a target acquisition screen in the target acquisition device; A first acquisition submodule is configured to acquire the first image data captured in the target acquisition screen of the target acquisition device; The first determination submodule includes: The mapping submodule is configured to map the location where the event occurred to the target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship, wherein the preset mapping relationship refers to the preset mapping relationship between the acquisition area and its geographical location in the current acquisition screen of the target acquisition device at each preset position.

12. An event processing device, wherein: include: A first output module is configured to output a location input interface in response to an event reporting request; An acquisition module configured to acquire the event occurrence location provided by the user through the location input interface; a calling module configured to call a pre-deployed event processing interface so that the event processing interface mobilizes a target acquisition device to acquire first image data according to the event occurrence location and recognizes the first image data; A second output module is configured to output the recognition result returned by the server; Wherein, the event processing device is further configured to: Determining, based on an event processing request, acquisition information at the location where the event occurred, wherein the event processing request includes the location where the event occurred; the acquisition information includes first indication information of the target acquisition device and second indication information of a target acquisition screen of the target acquisition device; the target acquisition device includes a device that reciprocates in a sequential manner and / or at fixed time intervals at a plurality of preset positions to acquire images; and the second indication information includes acquisition screen identification information for identifying a target acquisition screen in the target acquisition device; Acquire the first image data captured in the target acquisition screen of the target acquisition device; Determining, according to the event processing request, collected information at the location where the event occurred, including: The event location is mapped to the target area in the target acquisition screen of the target acquisition device according to a preset mapping relationship, wherein the preset mapping relationship refers to the preset mapping relationship between the acquisition area and its geographical location in the current acquisition screen of the target acquisition device at each preset position.

13. An electronic device, wherein: comprising a memory and a processor; wherein, The memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 10.

14. A computer-readable storage medium having computer instructions stored thereon, wherein: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images