forked from ros-perception/vision_msgs
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Updated documentation and started preparing package for primetime
- Loading branch information
Showing
12 changed files
with
100 additions
and
256 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
/** | ||
\mainpage | ||
\htmlinclude manifest.html | ||
|
||
\b sensor_msgs is a package which collects the common message data types for | ||
robot sensors. It also provides a set of methods for conversion between these | ||
data types. | ||
|
||
|
||
*/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,17 +1,18 @@ | ||
# Defines a 2D detection result. | ||
# | ||
# This is similar to a 2D classification, but includes position information, | ||
# allowing a classification result for a specific crop or image point to | ||
# to be located in the larger image. | ||
# allowing a classification result for a specific crop or image point to | ||
# to be located in the larger image. | ||
|
||
Header header | ||
|
||
# Class probabilities | ||
ObjectHypothesisWithPose[] results | ||
|
||
# 2D bounding box surrounding the object. | ||
# A 2D bounding box surrounding the object, specified in the coordinates of the | ||
# original input image. | ||
BoundingBox2D bbox | ||
|
||
# The 2D data that generated these results (i.e. region proposal cropped out of | ||
# the image). Not required for all use cases, so it may be empty. | ||
# the image). Not required for all use cases, so it may be empty. | ||
sensor_msgs/Image source_img |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,5 +1,5 @@ | ||
# A list of 3D detections, for a multi-object 2D detector. | ||
# A list of 2D detections, for a multi-object 2D detector. | ||
|
||
# list of the detected proposals. For a multi-proposal detector, this list could | ||
# have many objects. | ||
# A list of the detected proposals. A multi-proposal detector might generate | ||
# this list with many candidate detections generated from a single input. | ||
Detection2D[] detections |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,18 +1,19 @@ | ||
# Defines a 3D detection result. | ||
# | ||
# This extends a basic 3D classification by including position information, | ||
# allowing a classification result for a specific position in an image to | ||
# to be located in the larger image. | ||
# allowing a classification result for a specific position in an image to | ||
# to be located in the larger image. | ||
|
||
Header header | ||
|
||
# Class probabilities. Does not have to include hypotheses for all possible | ||
# object ids, the scores for any ids not listed are assumed to be 0. | ||
# object ids, the scores for any ids not listed are assumed to be 0. | ||
ObjectHypothesisWithPose[] results | ||
|
||
# 3D bounding box surrounding the object. | ||
BoundingBox3D bbox | ||
|
||
# The 3D data that generated these results (i.e. region proposal cropped out of | ||
# the image). Not required for all detectors, so it may be empty. | ||
# the image). This information is not required for all detectors, so it may be | ||
# empty. | ||
sensor_msgs/PointCloud2 source_cloud |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,5 +1,5 @@ | ||
# A list of 3D detections, for a multi-object 3D detector. | ||
|
||
# list of the detected proposals. For a multi-proposal detector, this list could | ||
# have many objects. | ||
# A list of the detected proposals. A multi-proposal detector might generate | ||
# this list with many candidate detections generated from a single input. | ||
Detection3D[] detections |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,8 +1,10 @@ | ||
# An object hypothesis that contains no position information. | ||
|
||
# ID of element detected. | ||
# The unique numeric ID of object detected. To get additional information about | ||
# this ID, such as its human-readable name, listeners should perform a lookup | ||
# in a metadata database. See vision_msgs/VisionInfo.msg for more detail. | ||
int64 id | ||
|
||
# The probability or confidence value of the detected element. Should be in the | ||
# range 0-1. | ||
# The probability or confidence value of the detected object. By convention, | ||
# this value should lie in the range [0-1]. | ||
float64 score |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,14 +1,19 @@ | ||
# ID of element detected. | ||
# An object hypothesis that contains position information. | ||
|
||
# The unique numeric ID of object detected. To get additional information about | ||
# this ID, such as its human-readable name, listeners should perform a lookup | ||
# in a metadata database. See vision_msgs/VisionInfo.msg for more detail. | ||
int64 id | ||
|
||
# The probability or confidence value of the detected element. Should be in the | ||
# range 0-1. | ||
# The probability or confidence value of the detected object. By convention, | ||
# this value should lie in the range [0-1]. | ||
float64 score | ||
|
||
# the 6D pose of the object hypothesis. This pose should be | ||
# defined as the pose of some fixed reference point on the object, such as the | ||
# geometric center of the bounding box or the center of mass of the object. | ||
# Note that this pose is not stamped; frame information can be defined by parent | ||
# messages. Also note that different classes predicted | ||
# for the same input data may have different predicted 6D poses. | ||
# messages. | ||
# Also note that different classes predicted | ||
# for the same input data may have different predicted 6D poses. | ||
geometry_msgs/Pose pose |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,22 +1,40 @@ | ||
# Provides meta-information about a classifier (or detector). | ||
# Provides meta-information about a visual pipeline. | ||
# | ||
# This message serves a similar purpose to sensor_msgs/CameraInfo, but instead | ||
# of being tied to hardware, it represents information about a specific computer | ||
# vision classfier or detector. This information stays constant (or relatively | ||
# constant) over time, and so it is wasteful to send it with each individual | ||
# detection message. By listening to these messages, subscribers will receive | ||
# the context in which published vision messages are to be interpreted. | ||
# of being tied to hardware, it represents information about a specific | ||
# computer vision pipeline. This information stays constant (or relatively | ||
# constant) over time, and so it is wasteful to send it with each individual | ||
# result. By listening to these messages, subscribers will receive | ||
# the context in which published vision messages are to be interpreted. | ||
# Each vision pipeline should publish its VisionInfo messages to its own topic, | ||
# in a manner similar to CameraInfo. | ||
|
||
# Used for sequencing | ||
Header header | ||
|
||
# Name of the classifier | ||
# Name of the vision pipeline. This should be a value that is meaningful to an | ||
# outside user. | ||
string method | ||
|
||
# ROS parameter name where the metadata database is stored in XML format. | ||
# The exact information stored in the database is left up to the user. | ||
string database_param | ||
# Location where the metadata database is stored. The recommended location is | ||
# as an XML string on the ROS parameter server, but the exact implementation | ||
# and information is left up to the user. | ||
# The database should store information attached to numeric ids. Each | ||
# numeric id should map to an atomic, visually recognizable element. This | ||
# definition is intentionally vague to allow extreme flexibility. The elements | ||
# could be classes in a pixel segmentation algorithm, object classes in a | ||
# detector, different people's faces in a face detection algorithm, etc. | ||
# Vision pipelines report results in terms of numeric IDs, which map into this | ||
# database. | ||
# The information stored in this database is, again, left up to the user. The | ||
# database could be as simple as a map from ID to class name, or it could | ||
# include information such as object meshes or colors to use for | ||
# visualization. | ||
string database_location | ||
|
||
# locally-incremented metadata database version. This counter is incremented | ||
# each time the classifier responds to changes in the metadata database. | ||
# Metadata database version. This counter is incremented | ||
# each time the pipeline begins using a new version of the database (useful | ||
# in the case of online training or user modifications). | ||
# The counter value can be monitored by listeners to ensure that the pipeline | ||
# and the listener are using the same metadata. | ||
int32 database_version |
Oops, something went wrong.