# US 2019/0378296 A1 · Method and device for positioning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378296 A1 - Document ID: US20190378296A1 - Status: Published application - Kind: A1 - Application number: 16/357,571 - Filed: 2019-03-19 - Published: 2019-12-12 - Earliest claimed: 2018-06-11 - Assignees: Baidu Online Network Technology (Beijing) Co., Ltd. - Applicants: Baidu Online Network Technology (Beijing) Co., Ltd. - Inventors: Jingsen ZHENG; Shichun YI; Xiaolong YANG; Shiyu SONG; Fangfang DONG - Web page: https://patentgrep.com/patent/US20190378296A1 ## CPC - G01C 21/3602: {Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera} - G06T 7/74: {involving reference images or patches} - G01C 21/1652: {with ranging devices, e.g. LIDAR or RADAR} - G01C 21/1656: {with passive imaging devices, e.g. cameras} - G06T 7/73: using feature-based methods - G06T 2207/10016: Video; Image sequence - G06T 2207/30244: Camera pose - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract The present disclosure provides a method and a device for positioning, an apparatus and a computer readable storage medium. The method includes acquiring a visual feature map of a geographic area located by a movable object. The visual feature map includes a first set of visual features. The method further includes acquiring at least one image captured by a camera coupled to the movable object during a motion of the movable object within the geographic area. The method further includes extracting a second set of visual features corresponding to the first set of visual features from the at least one image. In addition, the method further includes determining at least one pose of the movable object during the motion at least based on the visual feature map and the second set of visual features. ## Claims ### Claim 1 A method for positioning, comprising: acquiring a visual feature map of a geographic area located by a movable object, the visual feature map comprising a first set of visual features, and the first set of visual features comprising a first visual feature perpendicular to a road surface of the geographic area; acquiring at least one image captured by a camera coupled to the movable object during a motion of the movable object within the geographic area; extracting a second set of visual features corresponding to the first set of visual features from the at least one image; and determining at least one pose of the movable object during the motion, at least based on the visual feature map and the second set of visual features. ### Claim 2 (depends on 1) The method of claim 1, wherein the first visual feature comprises a columnar object perpendicular to the road surface of the geographic area. ### Claim 3 (depends on 1) The method of claim 1, wherein the first set of visual features further comprises a second visual feature contained on the road surface of the geographic area. ### Claim 4 (depends on 3) The method of claim 3, wherein the second visual feature comprises a road marking line contained on the road surface of the geographic area. ### Claim 5 (depends on 3) The method of claim 3, wherein, extracting the second set of visual features comprises: extracting a third visual feature corresponding to the first visual feature and a fourth visual feature corresponding to the second visual feature from the at least one image; and determining the at least one pose of the movable object during the motion comprises: determining the at least one pose of the movable object during the motion, at least based on the visual feature map, the third visual feature and the fourth visual feature. ### Claim 6 (depends on 1) The method of claim 1, wherein determining the at least one pose of the movable object during the motion comprises: acquiring information related to the motion of the movable object; and determining the at least one pose of the movable object during the motion using particle filtering, based on the visual feature map, the second set of visual features and the information. ### Claim 7 (depends on 6) The method of claim 6, wherein acquiring the information related to the motion of the movable object comprises: acquiring the information from at least one of an inertia measurement unit coupled to the movable object and a velocity sensor coupled to the movable object. ### Claim 8 (depends on 6) The method of claim 6, wherein the information comprises at least one of angular velocity and velocity of the movable object. ### Claim 9 (depends on 6) The method of claim 6, wherein determining the at least one pose of the movable object during the motion using the particle filtering comprises: representing a plurality of possible poses of the movable object at a current moment during the motion, with a plurality of particles; determining a respective state and a respective weight of the plurality of particles at the current moment; and determining a pose of the movable object at the current moment based on the respective state and the respective weight of the plurality of particles at the current moment. ### Claim 10 (depends on 9) The method of claim 9, wherein determining the respective state and the respective weight of the plurality of particles at the current moment comprises: for one of the plurality of particles; determining a first state and a first weight of the particle at a previous moment to the current moment; estimating a second state of the particle at the current moment based on the information and the first state; and determining a second weight of the particle at the current moment based on the first weight and the second state. ### Claim 11 (depends on 10) The method of claim 10, wherein determining the second weight of the particle at the current moment comprises: determining at least one visual feature comprised in the first set of visual features and predicted to be presented in a first image of the at least one image, based on the second state and the visual feature map, the first image being captured by the camera coupled the movable object at the current moment; determining a matching degree between the at least one visual feature predicted to be presented in the first image and at least one visual feature comprised in the second set of visual features and extracted from the first image; and determining the second weight based on the first weight and the matching degree. ### Claim 12 An electronic device, comprising: one or more processors; and a storage device, configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are configured to: acquire a visual feature map of a geographic area located by a movable object, the visual feature map comprising a first set of visual features, and the first set of visual features comprising a first visual feature perpendicular to a road surface of the geographic area; acquire at least one image captured by a camera coupled to the movable object during a motion of the movable object within the geographic area; extract a second set of visual features corresponding to the first set of visual features from the at least one image; and determine at least one pose of the movable object during the motion, at least based on the visual feature map and the second set of visual features. ### Claim 13 (depends on 12) The electronic device of claim 12, wherein the first set visual features further comprises a second visual feature contained on the road surface of the geographic area. ### Claim 14 (depends on 13) The electronic device of claim 13, wherein the one or more processors are configured to extract the second set of visual features by extracting a third visual feature corresponding to the first visual feature and a fourth visual feature corresponding to the second visual feature from the at least one image; and the one or more processors are configured to determine the at least one pose of the movable object during the motion by determining the at least one pose of the movable object during the motion, at least based on the visual feature map, the third visual feature and the fourth visual feature. ### Claim 15 (depends on 12) The electronic device of claim 12, wherein the one or more processors are configured to determine the at least one pose of the movable object during the motion by: acquiring information related to the motion of the movable object; and determining the at least one pose of the movable object during the motion using particle filtering, based on the visual feature map, the second set of visual features and the information. ### Claim 16 (depends on 15) The electronic device of claim 15, wherein the one or more processors are configured to acquire the information related to the motion of the movable object by: acquiring the information from at least one of an inertia measurement unit coupled to the movable object and a velocity sensor coupled to the movable object. ### Claim 17 (depends on 15) The electronic device of claim 15, wherein the one or more processors are configured to determine the at least one pose of the movable object during the motion using the particle filtering by: representing a plurality of possible poses of the movable object at a current moment during the motion, with a plurality of particles; determining a respective state and a respective weight of the plurality of particles at the current moment; and determining a pose of the movable object at the current moment based on the respective state and the respective weight of the plurality of particles at the current moment. ### Claim 18 (depends on 17) The electronic device of claim 17, wherein the one or more processors are configured to determine the respective state and the respective weight of the plurality of particles at the current moment by: for one of the plurality of particles; determining a first state and a first weight of the particle at a previous moment to the current moment; estimating a second state of the particle at the current moment based on the information and the first state; and determining a second weight of the particle at the current moment based on the first weight and the second state. ### Claim 19 (depends on 18) The electronic device of claim 18, wherein the one or more processors are configured to determine the second weight of the particle at the current moment by: determining at least one visual feature comprised in the first set of visual features and predicted to be presented in a first image of the at least one image, based on the second state and the visual feature map, the first image being captured by the camera coupled the movable object at the current moment; determining a matching degree between the at least one visual feature predicted to be presented in the first image and at least one visual feature comprised in the second set of visual features and extracted from the first image; and determining the second weight based on the first weight and the matching degree. ### Claim 20 A computer readable storage medium, having computer programs stored thereon, wherein when the computer programs are executed by a processor, the processor is configured to execute a method for positioning, the method comprising: acquiring a visual feature map of a geographic area located by a movable object, the visual feature map comprising a first set of visual features, and the first set of visual features comprising a first visual feature perpendicular to a road surface of the geographic area; acquiring at least one image captured by a camera coupled to the movable object during a motion of the movable object within the geographic area; extracting a second set of visual features corresponding to the first set of visual feature features from the at least one image; and determining at least one pose of the movable object during the motion, at least based on the visual feature map and the second set of visual features.