• documentation
main content

labeling -凯发k8网页登录

interactive point cloud labeling for object detection, semantic segmentation, and classification

use the app to interactively label ground truth data in a point cloud or a point cloud sequence. you can label cuboids and polylines for object detection, voxels for semantic segmentation, and scenes for point cloud classification.

the app provides algorithms to automate the labeling process for object tacking and interpolation. you can use one of the included algorithms or create and import a custom automation algorithm. for more information, see .

for information on how to start labeling a point cloud sequence, see .

you can also use lidar toolbox™ functions to define labels and programmatically automate the labeling process.

apps

label ground truth data in lidar point clouds

functions

use lidar labels

lidar ground truth label data
select ground truth data by label name or type
select ground truth data by label group name
select ground truth data by label name
select ground truth data by label type
change file paths in ground truth data
label type enumerations for labeling
lidar label type enumerations for labeling
attribute type enumerations for labeling

create label definitions

store, modify, and create label definitions tables for lidar
add attribute to label in label definition creator for lidar workflow
add label to label definition creator object for lidar workflow
create label definitions table from label definition creator object for lidar workflow
modify attribute description in label definition creator object for lidar workflow
change group name in label definition creator for lidar workflow
modify label description in label definition creator for lidar workflow
modify label group name in label definition creator object for lidar workflow
display label or attribute information stored in label definition creator for lidar workflow
remove attribute from label in label definition creator for lidar workflow
remove label from label definition creator for lidar workflow

load ground truth data sources

interface for loading signal data into lidar labeler app
load signals from point cloud sequence sources into lidar labeler app
load signals from velodyne lidar sources into lidar labeler app
load signals from las or laz file sequence sources into lidar labeler app
load signals from rosbag sources into lidar labeler app
load point cloud data from custom sources into lidar labeler app

sync external image viewer

interface to connect external tool to lidar labeler app
update external tool when connecting to signal being loaded into lidar labeler app
update external tool when new frame is displayed in lidar labeler app
update current time in lidar labeler app
close external tool connected to lidar labeler app
disconnect external tool from lidar labeler app

action flags

initialize state for algorithm execution (optional)
run label automation on every frame in interval
terminate automated algorithm (optional)

validation

set up validation (optional)
validate signal type
validate label definition

algorithm

interface for algorithm automation in ground truth labeling
display algorithm settings (optional)
mixin interface for adding temporal context to automation algorithms

topics

get started


  • interactively label a point cloud or point cloud sequence.

  • use keyboard shortcuts and mouse actions to increase productivity while using the lidar labeler app.

  • create a reader function to load a custom image data source into the lidar labeler.

automate labeling


  • create a custom automation algorithm to use in a labeling app.

  • create a time-based custom tracking algorithm to import into a labeling app.
网站地图