paralleldomain.data_lab.config.sensor_rig¶
- class CameraIntrinsic(*, proto=None, width=None, height=None, fov=None, supersample=None, capture_rgb=None, capture_depth=None, capture_normals=None, capture_segmentation=None, capture_instance=None, capture_detections=None, capture_motionvectors=None, lut=None, lut_weight=None, post_process_params=None, post_process=None, distortion_params=None, noise_params=None, enable_streaming=None, transmit_gray=None, distortion_lookup_table=None, capture_basecolor=None, capture_properties=None, time_offset=None, capture_backwardmotionvectors=None)¶
Parameters which control the intrinsics of an rgb camera sensor.
- Parameters:
supersample (
Optional
[float
]) –supersample
capture_rgb (
Optional
[bool
]) –capture_rgb
capture_depth (
Optional
[bool
]) –capture_depth
capture_normals (
Optional
[bool
]) –capture_normals
capture_segmentation (
Optional
[bool
]) –capture_segmentation
capture_instance (
Optional
[bool
]) –capture_instance
capture_detections (
Optional
[bool
]) –capture_detections
capture_motionvectors (
Optional
[bool
]) –capture_motionvectors
lut_weight (
Optional
[float
]) –lut_weight
post_process_params (
Optional
[PostProcessParams
]) –post_process_params
post_process (
Optional
[List
[PostProcessNode
]]) –post_process
distortion_params (
Optional
[DistortionParams
]) –distortion_params
noise_params (
Optional
[NoiseParams
]) –noise_params
enable_streaming (
Optional
[bool
]) –enable_streaming
transmit_gray (
Optional
[bool
]) –transmit_gray
distortion_lookup_table (
Optional
[str
]) –distortion_lookup_table
capture_basecolor (
Optional
[bool
]) –capture_basecolor
capture_properties (
Optional
[bool
]) –capture_properties
time_offset (
Optional
[float
]) –time_offset
capture_backwardmotionvectors (
Optional
[bool
]) –capture_backwardmotionvectors
proto (Optional[pd_sensor_pb2.CameraIntrinsic]) –
- width¶
Width of the image in pixels
- height¶
Height of the image in pixels.
- fov¶
Field of view of the camera in degrees. Ignored when fx, fy, cx and cy are set in
DistortionParams
.
- supersample¶
Supersampling to apply during rendering. Supersampling is ignored on pinhole cameras.
- capture_rgb¶
Flag to control whether RGB data is captured.
- capture_depth¶
Flag to control whether depth data is captured.
- capture_normals¶
Flag to control whether surface normal data is captured.
- capture_segmentation¶
Flag to control whether semantic segmentation data is captured.
- capture_instance¶
Flag to control whether instance segmentation data is captured.
- capture_detections¶
Flag to control whether bounding box data is captured.
- capture_motionvectors¶
Flag to control whether motion vector data is captured.
- lut¶
Path to color adjustment map in unreal syntax.
- post_process_params¶
Post processing parameters to apply to the rendered image.
- post_process¶
Array of ‘post_process_entries’, each of which has an unreal material path and a weight (to blend with the previous image). “material” is the path in unreal syntax and “weight” is the blend weight (0->1).
- distortion_params¶
The distortion parameters to apply to the image.
- noise_params¶
The noise parameters to apply to the image.
- enable_streaming¶
- transmit_gray¶
Control whether the returned image is grayscale.
- distortion_lookup_table¶
Path to the distortion lookup table if a lookup table is required by
DistortionParams
.
- capture_basecolor¶
Flag to control whether base color data is captured.
- capture_properties¶
Flag to control whether material propety data is captured.
- time_offset¶
Time offset of captured images.
- capture_backwardmotionvectors¶
Flag to control whether backwards motion vector data is captured.
- class DistortionParams(*, proto=None, k1=None, k2=None, k3=None, k4=None, k5=None, k6=None, p1=None, p2=None, skew=None, is_fisheye=None, fx=None, fy=None, cx=None, cy=None, fisheye_model=None)¶
Parameters that control the lens distortion applied to RGB camera sensors
- Parameters:
is_fisheye (
Optional
[bool
]) –is_fisheye
fisheye_model (
Optional
[int
]) –fisheye_model
proto (Optional[pd_sensor_pb2.DistortionParams]) –
- k1¶
Radial distortion parameter k1 if the Brown Conrady or OpenCV Fisheye models are specified in
fisheye_model
, ignored otherwise.
- k2¶
Radial distortion parameter k2 if the Brown Conrady or OpenCV Fisheye models are specified in
fisheye_model
, ignored otherwise.
- k3¶
Radial distortion parameter k3 if the Brown Conrady or OpenCV Fisheye models are specified in
fisheye_model
, ignored otherwise.
- k4¶
Radial distortion parameter k4 if the Brown Conrady or OpenCV Fisheye models are specified in
fisheye_model
, ignored otherwise.
- k5¶
Radial distortion parameter k5 if the Brown Conrady model is specified in
fisheye_model
. Ignored otherwise.
- k6¶
Radial distortion parameter k6 if the Brown Conrady model is specified in
fisheye_model
. Ignored otherwise.
- p1¶
Tangential distortion parameter p1 if the Brown Conrady model is specified in
fisheye_model
. Ignored otherwise.
- p2¶
Tangential distortion parameter p2 if the Brown Conrady model is specified in
fisheye_model
. Ignored otherwise.
- skew¶
Parameter controlling the skew distortion that is applied to the camera.
- is_fisheye¶
DEPRECATED
- fx¶
The horizontal focal length of the camera.
- fy¶
Vertical focal length of the camera.
- cx¶
Distortion center of the image along the horizontal axis.
- cy¶
Distortion center of the image along the vertical axis.
- fisheye_model¶
The type of fisheye cameras being replicated. The following are valid values:
0 - Pinhole Camera if :attr:`k1`,:attr:`k2`,:attr:`p1`,:attr:`p2`[,:attr:`k3`[,:attr:`k4`,:attr:`k5`,:attr:`k6`]] not specified or Brown Conrady Distortion if distortion parameters are specified 1 - OpenCV Fisheye Distortion 3 - PD Fisheye Distortion 6 - Orthographic Projection
- class NoiseParams(*, proto=None, enable_bayer=None, enable_gauss_noise=None, enable_poisson_noise=None, enable_denoise=None, gauss_noise_sigma=None, poisson_noise_lambda=None, denoise_filter=None, denoise_filter_size=None, bilateral_sigma_d=None, bilateral_sigma_r=None, enable_auto_noise=None, signal_amount=None, pre_amplifier_noise=None, post_amplifier_noise=None, is_using_iso=None, iso_level=None, enable_auto_iso=None, fstop=None, max_exposure_time=None, quantum_efficiency=None)¶
- Parameters:
enable_bayer (
Optional
[bool
]) –enable_bayer
enable_gauss_noise (
Optional
[bool
]) –enable_gauss_noise
enable_poisson_noise (
Optional
[bool
]) –enable_poisson_noise
enable_denoise (
Optional
[bool
]) –enable_denoise
gauss_noise_sigma (
Optional
[float
]) –gauss_noise_sigma
poisson_noise_lambda (
Optional
[float
]) –poisson_noise_lambda
denoise_filter (
Optional
[DenoiseFilter
]) –denoise_filter
denoise_filter_size (
Optional
[int
]) –denoise_filter_size
bilateral_sigma_d (
Optional
[float
]) –bilateral_sigma_d
bilateral_sigma_r (
Optional
[float
]) –bilateral_sigma_r
enable_auto_noise (
Optional
[bool
]) –enable_auto_noise
signal_amount (
Optional
[int
]) –signal_amount
pre_amplifier_noise (
Optional
[float
]) –pre_amplifier_noise
post_amplifier_noise (
Optional
[float
]) –post_amplifier_noise
is_using_iso (
Optional
[bool
]) –is_using_iso
enable_auto_iso (
Optional
[bool
]) –enable_auto_iso
max_exposure_time (
Optional
[float
]) –max_exposure_time
quantum_efficiency (
Optional
[float
]) –quantum_efficiency
proto (Optional[pd_sensor_pb2.NoiseParams]) –
- enable_bayer¶
Flag to enable Bayer noise, also known as RGGB noise, simulates the noise patterns present when using a Bayer filter to capture color images. This filter is a common way to capture color in digital cameras. It shows up as a colors shifting away from pixels. Default: True
- enable_gauss_noise¶
Flag to enable Gaussian noise, also known as white noise, simulates electronic interference caused by thermal vibrations. This type of noise is tied to the temperature of the sensor and the brightness of the scene being captured - this adds noise uniformly on the image Default: True
- enable_poisson_noise¶
Flag to enable Poisson Noise. Simulates the probability of photons being collected by the sensor. This is the most common form of noise in an image, unless it is a low-light capture. Poisson noise is a good way to simulate the natural behavior of photons in an image. This adds more noise to brighter areas, less to darker areas. Default: True
- enable_denoise¶
Flag to add a denoise pass to mimic a real sensor’s stack. Default: True
- gauss_noise_sigma¶
Sigma applied when Gauss Noise is activated. Larger values result in noisier images. Default: 0.025
- poisson_noise_lambda¶
Lambda applied to poisson noise. Smaller values result in noisier images. Default: 1000.0
- denoise_filter¶
Type of denoising filter applied. Default:
DenoiseFilter.MEDIAN_FILTER
- denoise_filter_size¶
Only applies to Bilateral denoising filter. Represents how many pixels to sample. Default: 3
- bilateral_sigma_d¶
Spatial sigma_d of bilateral denoising filter. Default: 3.0
- bilateral_sigma_r¶
sigma_r of bilateral denoising filter. Default: 20.0
- enable_auto_noise¶
Boolean to enable automatic setting of noise parameters based on exposure value. Default: True
- signal_amount¶
Signal amount. Default: 5223
- pre_amplifier_noise¶
Pre-amplifier noise. Default: 7.63
- post_amplifier_noise¶
Post-amplifier noise. Default: 247.5
- is_using_iso¶
Boolean flag to control whether ISO is used to adjust noise parameters Default: True
- iso_level¶
ISO level of the camera. Default: 800
- enable_auto_iso¶
Controls whether IDO is used to scale noise parameters.
- fstop¶
F-Stop of the camera. Default: 1.0
- max_exposure_time¶
Inverse of the minimum shutter speed. Default: 0.033
- quantum_efficiency¶
Used when calculating auto ISO defaults. Default: 0.7
- class PostProcessNode(*, proto=None, material=None, weight=None)¶
Node which carries out post processing on a rendered image.
- Parameters:
- material¶
The material to be applied in post processing.
- weight¶
The weight of the post processing to be applied.
- class PostProcessParams(*, proto=None, exposure_compensation=None, exposure_speed_up=None, exposure_speed_down=None, exposure_min_ev100=None, exposure_max_ev100=None, exposure_metering_mask=None, motion_blur_amount=None, motion_blur_max=None, dof_focal_distance=None, dof_depth_blur_amount=None, dof_depth_blur_radius=None, vignette_intensity=None, tone_curve=None, exposure_compensation_curve=None)¶
Parameters that control the post processing applied to rgb camera sensor data.
- Parameters:
exposure_compensation (
Optional
[float
]) –exposure_compensation
exposure_speed_up (
Optional
[float
]) –exposure_speed_up
exposure_speed_down (
Optional
[float
]) –exposure_speed_down
exposure_min_ev100 (
Optional
[float
]) –exposure_min_ev100
exposure_max_ev100 (
Optional
[float
]) –exposure_max_ev100
exposure_metering_mask (
Optional
[str
]) –exposure_metering_mask
motion_blur_amount (
Optional
[float
]) –motion_blur_amount
motion_blur_max (
Optional
[float
]) –motion_blur_max
dof_focal_distance (
Optional
[float
]) –dof_focal_distance
dof_depth_blur_amount (
Optional
[float
]) –dof_depth_blur_amount
dof_depth_blur_radius (
Optional
[float
]) –dof_depth_blur_radius
vignette_intensity (
Optional
[float
]) –vignette_intensity
tone_curve (
Optional
[ToneCurveParams
]) –tone_curve
exposure_compensation_curve (
Optional
[str
]) –exposure_compensation_curve
proto (Optional[pd_sensor_pb2.PostProcessParams]) –
- exposure_compensation¶
Logarithmic adjustment for exposure. When set to 0, there will be no adjustment, -1 is two times darker, -2 is four times darker, 1 is two times brighter, and 2 is four times brighter Default: -100.0
- exposure_speed_up¶
Speeds up eye adaptation in f-stops per second.
- exposure_speed_down¶
Slows down eye adaptation in f-stops per second.
- exposure_min_ev100¶
The minimum brightness limit for auto exposure adaptation, expressed in pixel luminance (cd/m2). Value is typically negative and should be less than or equal to Max EV100. As this value increases, the scene view gets darker. If Min EV100 is equal to Max EV100, auto exposure is disabled. Default: -100.0
- exposure_max_ev100¶
The maximum brightness limit for auto exposure adaptation, expressed in pixel luminance (cd/m2). Value should be positive and should be greater than or equal to Min EV100. As this value decreases, the scene view gets brighter. If Max EV100 is equal to Min EV100, auto exposure is disabled. Default: -100.0
- exposure_metering_mask¶
Texture in unreal syntax. Bright spots on the mask will have high influence on auto exposure metering, and dark spots will have low influence.
- motion_blur_amount¶
Motion blur amount expressed in screen percentage (exposure will affect the final outcome). Default: 1.5
- motion_blur_max¶
Maximum motion blue amount in screen percentage. Default: 5.0
- dof_focal_distance¶
Focal distance (in cm) to near focal plane. Default: -1.0
- dof_depth_blur_amount¶
Distance (in km) where we blur to 50%.
- dof_depth_blur_radius¶
Radius of how many pixels to blur. Default: -1.0
- vignette_intensity¶
Strength of vignette applied.
- tone_curve¶
Type of tone curve applied to the image.
- exposure_compensation_curve¶
Curve in unreal syntax. The X and Y-axis values in the Curve graph translate to the Average Scene EV100 and Exposure Compensation (Curve) values
- class SensorConfig(*, proto=None, display_name=None, camera_intrinsic=None, lidar_intrinsic=None, radar_intrinsic=None, sensor_extrinsic=None, render_ego=None)¶
A configuration of one sensor.
- Parameters:
display_name (
Optional
[str
]) –display_name
camera_intrinsic (
Optional
[CameraIntrinsic
]) –camera_intrinsic
lidar_intrinsic (
Optional
[LidarIntrinsic
]) –lidar_intrinsic
radar_intrinsic (
Optional
[RadarIntrinsic
]) –radar_intrinsic
sensor_extrinsic (
Optional
[SensorExtrinsic
]) –sensor_extrinsic
render_ego (
Optional
[bool
]) –render_ego
proto (Optional[pd_sensor_pb2.SensorConfig]) –
- display_name¶
The name of the sensor.
- camera_intrinsic¶
Instrinsics of a camera sensor.
- lidar_intrinsic¶
Instrinsics of a lidar sensor.
- radar_intrinsic¶
Instrinsics of a radar sensor.
- sensor_extrinsic¶
The extrinsics of the sensor.
- render_ego¶
Control whether or not the attached ego agent is rendered if present
- get_sensor_to_ego(coordinate_system='FLU')¶
- Parameters:
coordinate_system (
str
) – The coordinate system the return transformation is in- Return type:
- Returns:
The transformation from sensor to ego in the given coordinate system
- property ego_to_sensor: Transformation¶
Returns: The transformation from ego to sensor in FLU
- property sensor_to_ego: Transformation¶
Returns: The transformation from sensor to ego in FLU
- class SensorExtrinsic(*, proto=None, yaw=None, pitch=None, roll=None, x=None, y=None, z=None, lock_to_yaw=None, attach_socket=None, follow_rotation=None)¶
Object to store extrinsic parameters of sensors. All extrinsics are stored in the RFU coordinate system relative to the agent to which the sensor is attached.
- Parameters:
lock_to_yaw (
Optional
[bool
]) –lock_to_yaw
attach_socket (
Optional
[str
]) –attach_socket
follow_rotation (
Optional
[bool
]) –follow_rotation
proto (Optional[pd_sensor_pb2.SensorExtrinsic]) –
- yaw¶
Yaw of the sensor in degrees.
- pitch¶
Pitch of the sensor in degrees.
- roll¶
Roll of the sensor in degrees.
- x¶
x position of the sensor in meters.
- y¶
y position of the sensor in meters.
- z¶
z position of the sensor in meters.
- lock_to_yaw¶
Setting this flag to true will cause the yaw value of the sensor orientation to be locked to the agent to which the sensor is attached, but leave the pitch and roll values as zero with respect to the world frame.
- attach_socket¶
Controls the socket on the agent to which the sensor should be attached.
- follow_rotation¶
Controls whether or not the sensor follows the rotation of the socket to which it is attached if
attach_socket
is True.
- class SensorRig(*args, **kwargs)¶
A configuration of a rig of sensors containing one or more sensors.
- Parameters:
sensor_configs –
sensor_configs
sensor_rig_artifact_uid –
sensor_rig_artifact_uid
default_sensor_splits_list –
default_sensor_splits_list
- sensor_configs¶
The configuration of sensors within a particular sensor rig.
- sensor_rig_artifact_uid¶
The s3 path to a sensor rig if it is not stored locally.
- default_sensor_splits_list¶
A list of sensor names to control which sensors are rendered in parallel.
- class ToneCurveParams(*, proto=None, slope=None, toe=None, shoulder=None, black_clip=None, white_clip=None)¶
Parameters that control the tone curve applied to the image.
- Parameters:
- slope¶
A slope tone curve. Default: 0.66
- toe¶
A toe tone curve. Default: 0.52
- shoulder¶
A shoulder tone curve. Default: 0.49
- black_clip¶
A black_clip tone curve. Default: 0.0
- white_clip¶
A white_clip tone curve. Default: 0.08
- class DenoiseFilter(value)¶
The type of denoising filter applied to an image.
- AVERAGE_FILTER = 0¶
Denoising filter using average method.
- BILATERAL_FILTER = 3¶
Denoising filter using bilateral method.
- FAST_MEDIAN_FILTER = 2¶
Denoising filter using fast median method.
- MEDIAN_FILTER = 1¶
Denoising filter using median method.