# US 11,308,798 B2 · Method for reporting traffic event, electronic device and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,798 B2 - Document ID: US11308798B2 - Status: Granted - Kind: B2 - Application number: 17/331,838 - Filed: 2021-05-27 - Published: 2021-10-21 - Granted: 2022-04-19 - Earliest claimed: 2020-06-03 - Assignees: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. - Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd. - Inventors: Bo Liu - Web page: https://patentgrep.com/patent/US11308798B2 ## CPC - G08G 1/0116: {from roadside infrastructure, e.g. beacons} - G08G 1/0133: {for classifying traffic situation} - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G08G 1/0129: {for creating historical data or processing based on historical data} - G08G 1/04: using optical or ultrasonic detectors - G08G 1/052: with provision for determining speed or overspeed {(speed measuring in general G01P)} - G08G 1/054: photographing overspeeding vehicles - H04N 7/188: {Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253)} - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract The application discloses a method and an apparatus for reporting a traffic event, an electronic device and a storage medium. The detailed implementation scheme is: obtaining a surveillance video and an object in a surveillance video; obtaining location information and/or speed information of the object; determining whether the object occurs a traffic event based on the location information and/or the speed information of the object; in response to determining that the traffic event is occurred, reporting starting information of the traffic event and generating state information of the traffic event, in which the state information of the traffic event is updated with the location information and/or the speed information of the object; supervising the state information of the traffic event; reporting ending information of the traffic event in response to determining that the traffic event ends based on the state information of the traffic event. ## Claims ### Claim 1 A method for reporting a traffic event, implemented by an electronic device, and comprising: obtaining a surveillance video captured by a camera and an object in the surveillance video; obtaining location information and/or speed information of the object; in response to determining that the traffic event has occurred based on the location information and/or the speed information of the object, reporting starting information of the traffic event and generating state information of the traffic event to a cloud platform, wherein, the state information of the traffic event is updated with the location information and/or the speed information of the object; supervising the state information of the traffic event; and reporting ending information of the traffic event to the cloud platform in response to determining that the traffic event ends based on the state information of the traffic event; wherein the state information of the traffic event comprises a current state identification of the traffic event and the number of consecutive frames not detecting the traffic event, and wherein the method further comprises: after the traffic event is occurred, storing the traffic event, the current state identification of the traffic event and the number of the consecutive frames not detecting the traffic event in a history cache; updating the current state identification according to the location information and/or the speed information of the object; updating the number of the consecutive frames not detecting the traffic event according to the current state identification; and determining that the traffic event ends in response to the number of the consecutive frames not detecting the traffic event being greater than a preset threshold. ### Claim 2 (depends on 1) The method according to claim 1, after determining that the traffic event ends, further comprising: deleting the traffic event from the history cache. ### Claim 3 (depends on 1) The method according to claim 1, wherein updating the current state identification according to the location information and/or the speed information of the object, comprises: obtaining the location information and/or the speed information of the object in each frame; determining whether the traffic event is continuous based on the location information and/or the speed information of the object in each frame; keeping the current state identification as a first state in response to the traffic event being continues; and restoring the current state identification as a second state in response to the traffic event being non-continuous. ### Claim 4 (depends on 3) The method according to claim 3, wherein updating the number of the consecutive frames not detecting the traffic event according to the current state identification, comprises: obtaining the current state identification stored in the historical cache of each frame; setting the number of the consecutive frames not detecting the traffic event as a default value in response to the current state identification being the first state; and increasing the number of the consecutive frames not detecting the traffic event by 1 in response to the current state identification being the second state. ### Claim 5 (depends on 1) The method according to claim 1, further comprising: after detecting the object, tracking the object in the surveillance video according to an object tracking algorithm; obtaining a traffic event corresponding to the object after failing to track the object in the surveillance video; and deleting the traffic event corresponding to the object from the history cache. ### Claim 6 (depends on 1) The method according to claim 1, after reporting starting information of the traffic event or ending information of the traffic event, further comprising: determining whether confirming information is received within a preset time; and in response to not receiving the confirming information within the preset time, repeatedly reporting the starting information of the traffic event or the ending information of the traffic event, and recording the number of reporting times. ### Claim 7 (depends on 6) The method according to claim 6, further comprising: determining whether the number of the reporting times reaches a preset reporting threshold; and in response to the number of the reporting times reaching the preset reporting threshold, performing an alarm and deleting the traffic event from the history cache. ### Claim 8 (depends on 1) The method according to claim 1, wherein the starting information of the traffic event comprises an identification of the traffic event, a starting time of the traffic event, a location of the traffic event and an area of the traffic event, and the ending information of the traffic event comprises the identification of the traffic event, an ending time of the traffic event, the location of the traffic event, and the area of the traffic event. ### Claim 9 (depends on 1) The method according to claim 1, wherein obtaining the location information and/or the speed information of the object, comprises: obtaining depth information of the object in each frame; obtaining the location information of the object according to the depth information of the object in each frame; and obtaining the speed information of the object according to the location information of the object in consecutive frames. ### Claim 10 An electronic device, comprising: at least one processor; and a memory communicating with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, when the instructions are executed by the at least one processor, the at least one processor is configured to: obtain a surveillance video captured by a camera and obtaining an object in the surveillance video; obtain location information and/or speed information of the object; in response to determining that the traffic event has occurred based on the location information and/or the speed information of the object, report starting information of the traffic event and generate state information of the traffic event to a cloud platform, wherein the state information of the traffic event is updated with the location information and/or the speed information of the object; and supervise the state information of the traffic event; report ending information of the traffic event to the cloud platform in response to determining that the traffic event ends based on the state information of the traffic event; wherein the at least one processor is configured to: after the traffic event is occurred, store the traffic event, the current state identification of the traffic event and the number of the consecutive frames not detecting the traffic event in a history cache; update the current state identification according to the location information and/or the speed information of the object; update the number of the consecutive frames not detecting the traffic event according to the current state identification; and determine that the traffic event ends in response to the number of the consecutive frames not detecting the traffic event being greater than a preset threshold. ### Claim 11 (depends on 10) The electronic device according to claim 10, wherein the at least one processor is configured to: delete the traffic event from the history cache. ### Claim 12 (depends on 10) The apparatus according to claim 10, wherein the at least one processor is configured to: obtain the location information and/or the speed information of the object in each frame; determine whether the traffic event is continuous based on the location information and/or the speed information of the object in each frame; and keep the current state identification as a first state in response to the traffic event being continues, and restore the current state identification as a second state in response to the traffic event being non-continuous. ### Claim 13 (depends on 12) The electronic device according to claim 12, wherein the at least one processor is configured to: obtain the current state identification stored in the historical cache of each frame; and set the number of the consecutive frames not detecting the traffic event as a default value in response to the current state identification being a first state, and, increase the number of the consecutive frames not detecting the traffic event by 1 in response to the current state identification being a second state. ### Claim 14 (depends on 10) The electronic device for reporting a traffic event according to claim 10, wherein the at least one processor is configured to: after detecting the object, track the object in the surveillance video according to an object tracking algorithm; obtain a traffic event corresponding to the object after failing to track the object in the surveillance video; and delete the traffic event corresponding to the object from the history cache. ### Claim 15 (depends on 10) The electronic device according to claim 10, wherein the at least one processor is configured to: determine whether confirming information is received within a preset time; in response to not receiving the confirming information within the preset time, repeatedly report the starting information of the traffic event or the ending information of the traffic event, and record the number of reporting times. ### Claim 16 (depends on 15) The electronic device according to claim 15, wherein the at least one processor is configured to: determine whether the number of the reporting times reaches a preset time threshold; and in response to the number of the reporting times reaching the preset reporting threshold, perform an alarm and delete the traffic event from the history cache. ### Claim 17 (depends on 10) The electronic device according to claim 10, wherein the starting information of the traffic event comprises an identification of the traffic event, a starting time of the traffic event, a location of the traffic event and an area of the traffic event, and the ending information of the traffic event comprises the identification of the traffic event, an ending time of the traffic event, the location of the traffic event, and the area of the traffic event. ### Claim 18 A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to cause the computer execute a method for reporting a traffic event, and the method comprises: obtaining a surveillance video captured by a camera and an object in the surveillance video; obtaining location information and/or speed information of the object; in response to determining that the traffic event has occurred based on the location information and/or the speed information of the object, reporting starting information of the traffic event and generating state information of the traffic event to a cloud platform, wherein the state information of the traffic event is updated with the location information and/or the speed information of the object; supervising the state information of the traffic event; and reporting ending information of the traffic event to the cloud platform in response to determining that the traffic event ends based on the state information of the traffic event; wherein the state information of the traffic event comprises a current state identification of the traffic event and the number of consecutive frames not detecting the traffic event, the method further comprises: after the traffic event is occurred, storing the traffic event, the current state identification of the traffic event and the number of the consecutive frames not detecting the traffic event in a history cache; updating the current state identification according to the location information and/or the speed information of the object; updating the number of the consecutive frames not detecting the traffic event according to the current state identification; and determining that the traffic event ends in response to the number of the consecutive frames not detecting the traffic event being greater than a preset threshold.