Baidu Online Network Technology (Beijing) Co., Ltd.

Apollo Intelligent Driving Technology (Beijing) Co., Ltd.

Baidu Online Network Technology Co., Ltd.

Xianpeng Lang

Changjie Ma

Yifei Zhan

Miao Yan

Wang Zhou

Xiong Duan

Yonggang Jin

Li Liu

Zhaoyan Jiang

Tangwu Du

Rui Ai

Guofu Xie

Rui Al

Wenbo Hou

A method, apparatus, and computer readable storage medium for updating an electronic map are disclosed. A method for updating an electronic map includes: acquiring a group of collected images collected by a collection entity and associated with a target map element in the electronic map, the target map element having a target image and a target location; executing inter-group matching between the group of collected images and the target image; executing intra-group matching among the group of collected images; and updating a location of a to-be-updated map element associated with the target map element based on the inter-group matching, the intra-group matching and the target location. In this way, the positioning precision of map elements can be improved.

Method, apparatus, and computer readable storage medium for updating electronic map

Embodiments of the present disclosure can include a method and apparatus for adjusting a point cloud data acquisition trajectory, and a computer readable medium. According to the embodiments of the present disclosure, a trajectory may be adjusted based on a characteristic extracted from point cloud data. A parameter that needs to be adjusted may be selected according to the property of the characteristic, instead of adjusting all parameters at the same time. In addition, according to the embodiments of the present disclosure, when trajectories are fused, the sequence relationships between the trajectory points in the trajectories can be considered, which avoids that a loop cannot be closed.

Method and apparatus for adjusting point cloud data acquisition trajectory, and computer readable medium

Implementations of the present disclosure can include a method and apparatus for processing point cloud data. Specifically, the method for processing point cloud data can be provided, including: acquiring a first frame and a second frame respectively from the point cloud data; extracting a first candidate object from the first frame and a second candidate object corresponding to the first candidate object from the second frame, respectively; determining a first location of the first candidate object and a second location of the second candidate object in a coordinate system of the point cloud data, respectively; and identifying any one of the first candidate object and the second candidate object as a moving object, in response to an offset between the first location and the second location.

Method and apparatus for processing point cloud data

A method, apparatus, and computer readable medium for generating a raster map are provided. The method includes generating a first raster map having a first resolution based on acquired laser point cloud. The method further includes generating a second raster map having a second resolution by merging rasters in the first raster map, the second resolution being lower than the first resolution. In addition, the method further includes storing the first raster map and an association between the first raster map and the second raster map. Some embodiments of the present disclosure are capable of meeting different levels of navigation or positioning requirements by generating raster maps of multiple resolutions. Furthermore, some embodiments of the present disclosure store only the raster map having the highest resolution and the association between the various levels of maps, thereby saving the storage space.

Method and apparatus for generating raster map

A method for generating a point cloud data recovery model includes: acquiring at least one 2D image associated with a first point cloud data frame; partitioning the first point cloud data frame into at least one point cloud data set based on attributes of objects in the 2D image; and for each point cloud data set: determining a matching image of the first point cloud data frame from the at least one 2D image; determining 3D position data of a pixel point in the matching image based on the first point cloud data frame and at least one second point cloud data frame; and using 2D position data and the 3D position data of corresponding pixel points in the matching image as training input data and output data of a training model to generate a point cloud data recovery model for the object corresponding to the point cloud data set.

Method and apparatus for recovering point cloud data

Embodiments of the present disclosure provide a method, apparatus, and computer readable storage medium for processing an image. The method described herein includes determining a to-be-processed first region and a to-be-processed second region in an input image, the first region is at least partially filled with a first color, the second region is at least partially filled with a second color, and the first region and the second region are adjacent regions sharing a common boundary region. The method further includes shrinking the first region and the second region, to enable neither of the shrunken first region and the shrunken second region to include the boundary region. The method further comprises expanding the shrunken first region and the shrunken second region, to enable the boundary region to be filled with at least one color of the first color or the second color.

Method, apparatus, and computer readable medium for adjusting color annotation of an image

The disclosure relates to a method, apparatus, device, and computer readable storage medium for determining a lane line on a road. The method includes: acquiring a first curve as a reference curve, the first curve being obtained by fitting a first set of points selected from sets of points in different areas of the road; iteratively executing operations: selecting a second set of points from the sets of points based on the reference curve; generating a second curve by fitting the second set of points, determining a difference between a fitting degree associated with the reference curve and a fitting degree associated with the second curve, determining whether a convergence condition is met based on the difference, and setting the second curve as the reference curve if not met and determining the lane line of the road based on the second set of points if met.

Method, apparatus, and device for determining lane line on road

Exemplary embodiments of the present disclosure provide a method, apparatus and computer readable storage medium for creating a map and positioning a moving entity. A method for creating a map includes acquiring an image acquired when an acquisition entity is moving and location data and point cloud data associated with the image, the location data indicating a location where the acquisition entity is located when the image is acquired, the point cloud data indicating three-dimensional information of the image. The method further includes generating a first element in a global feature layer of the map based on the image and the location data. The method further includes generating a second element in a local feature layer of the map based on the image and the point cloud data, the first element corresponding to the second element.

Method and apparatus for creating map and positioning moving entity

Embodiments of the present disclosure can provide a method, apparatus and computer readable storage medium for determining a matching relationship between point cloud data. The method can include extracting a first characteristic associated with first point cloud data and a second characteristic associated with second point cloud data. The first point cloud data and the second point cloud data are acquired for the same object. The method can further include performing characteristic matching between the first characteristic and the second characteristic. In addition, the method can further include determining, based on the characteristic matching, a matching relationship between the first point cloud data and the second point cloud data.

Method and apparatus for determining matching relationship between point cloud data

According to the exemplary embodiments of the present disclosure, a method and apparatus for detecting a lane line, and a medium are provided. A method for generating a lane line detection model includes: detecting a lane line in an original image to generate a first image associated with the detected lane line; acquiring a second image generated based on the original image and associated with a marked lane line; generating at least one tag indicating whether the detected lane line is accurate, based on the first image and the second image; and training a classifier model for automatically identifying the lane line, based on the first image and the at least one tag. In such case, the lane line detection may be achieved in a simple and effective way.

Method and apparatus for detecting lane line, and medium

A method and apparatus for fusing point cloud data, and a computer readable storage medium are provided. Some embodiments of the method can include: acquiring a first image and a second image, the first image and the second image being respectively associated with a first frame of point cloud data and a second frame of point cloud data acquired for a given scene; determining a point cloud movement matrix between the first frame of point cloud data and the second frame of point cloud data on the basis of the first image and the second image; and fusing the first frame of point cloud data with the second frame of point cloud data on the basis of the point cloud movement matrix.

Method and apparatus for fusing point cloud data

A method and apparatus for identifying an intersection in an electronic map, and a computer readable medium are provided. An embodiment of the method includes: acquiring boundary information related to road boundaries from an electronic map; determining a topological relationship between the road boundaries in an area having a predetermined size in the electronic map based on the boundary information; and determining a distribution of an intersection in the area based on the topological relationship. The apparatus corresponding to the method, the device implementing the method of the present disclosure, and the computer readable medium are also provided. Through the technical solutions, the intersection may be automatically identified by detecting the road boundaries, which improves the efficiency of producing a high-precision map, and has the advantage of high accurate recall rate, strong universality, or simple method.

Method and apparatus for identifying intersection in electronic map

A scene reconstruction method, apparatus, terminal device, and storage medium. The method includes: acquiring a first image set matching a to-be-reconstructed scene (); extracting a characteristic region of an image in the first image set by using a characteristic extraction algorithm (); performing recognition on the characteristic region to obtain a scene characteristic region in the image (); and performing three-dimensional reconstruction on the to-be-reconstructed scene according to the scene characteristic region in the image, and rendering and generating the to-be-reconstructed scene (). Some useless and unstable characteristic regions are filtered off, and the three-dimensional reconstruction on the to-be-reconstructed scene is performed only according to the scene characteristic region associated with the to-be-reconstructed scene, thereby improving the efficiency and accuracy of reconstruction.

Method and apparatus for reconstructing scene, terminal device, and storage medium

The present application discloses a picture presentation method and apparatus. A specific implementation of the method includes: acquiring an original picture set encompassing a same scene; selecting, from the original picture set, a reconstruction picture set for reconstructing a three-dimensional structure of the scene, and reconstructing the three-dimensional structure of the scene by using reconstruction pictures in the reconstruction picture set, the three-dimensional structure of the scene comprising three-dimensional feature points; selecting a to-be-presented picture set from the reconstruction picture set, a number of the three-dimensional feature points included in the to-be-presented picture set being above a preset threshold; determining a presentation order of to-be-presented pictures in the to-be-presented picture set, and generating a picture presentation sequence based on the presentation order of the to-be-presented pictures; and presenting pictures in the picture presentation sequence continuously. By acquiring pictures encompassing a same scene, determining a presentation order of the pictures based on the association relationship between the pictures, and continuously presenting the pictures according to the presentation order, this implementation improves the spatial continuity of the scene in the pictures when the pictures are presented.

Picture presentation method and apparatus

The present disclosure provides a panoramic image generation method and apparatus for a user terminal. The panoramic image generation method for a user terminal includes: obtaining a plurality of images shot by a user terminal, determining an adjacence relationship among the plurality of images, and performing feature matching on adjacent images to obtain matched feature-point-pairs; obtaining an optimized camera parameter according to the matched feature-point-pairs and an initial camera parameter; performing a color adjustment on the adjacent images to obtain color adjusted adjacent images; and mosaicking the color adjusted adjacent images according to the optimized camera parameter to generate a panoramic image.

Growing community of inventors

Beijing, China

Xianpeng Lang