Parameters

Overview

SENSR is a highly configurable solution allowing users to optimize their site's configuration. This section aims at describing SENSR's settings and their default values.

SENSR settings can be classified into 4 categories:

• General parameters, defining the system's overall behavior,
• Master node parameters, defining the orchestration with algo nodes,
• Algo node parameters, defining the parameters used by the different algorithms to optimize object tracking
• Visualization parameters, defining the user interface settings

important

Tracking results can widely vary depending on the settings applied to a site. Tunning the parameters however comes with trade-offs, over optimizing for certain aspects may come at the cost of degrading others.

General Parameters

General parameters are parameters shared accross a whole project of each components, they can be found in Settings > General Parameters.

Location	Field	Name	Description	Unit	Default	Range
Common	Output	Runtime Mode Point-Cloud Publishing Level	The level of publishing point cloud to output port. This setting will greatly increase the bandwidth between the algo nodes and the master node! - No Points - Object Points - Object Points & Background Points - All Points	int	Object Points
		Zone Setup Point-Cloud Publishing Level	The level of publishing point cloud to output port. This setting will greatly increase the bandwidth between the algo nodes and the master node! - No Points - Object Points - Object Points & Background Points - All Points	int	Object Points & Background points
		Background Points Update Interval	Time between updates of background and ground point cloud information from algo nodes to the master node. Updating frequently can be resource-intensive..	seconds	1
		Sensor Status Update Interval	Time between updates of sensor information from algo nodes to the master node.	seconds	0.5
		Publish Losing Event	Enables SENSR ppublishing loosing event when for a given object the tracking is lost	boolean	FALSE
		Output Sending Type Selection	Method for sending and updating new results. - Instant Sending: Publish result whenever a new one is available. - Fixed-Period Sending: Publish the most recent result periodically. The published result might already have been published in a previous frame. - Fixed-Period w/ Delay: Publish the most recent result periodically. If there is no new result, the sending is postponed until a new result is received or a maximum delay time has passed. - All-Update or Fixed Delay	int	Fixed-Period Sending
		Update Interval	Publish interval for output sending type 1 - Fixed-Period Sending and type 2 - Fixed-Period with Max-Delay	seconds	0.1
		Max Delay	Maximum delay time for "Fixed-Period with Max-Delay".	seconds	0.05
		Point-Cloud Bandwidth Reduction	This decreases the communication burden by reducing pointcloud data size. This option if enable will affects: - In calibration mode, only one point cloud will be sent (circularly) at a time. - In runtime mode, background and ground points will be downsampled - Points out of detection range will not be published regardless of the point cloud publishing level.	boolean	FALSE
		Downsampling Resolution	Resolution of downsampling method for pointcloud bandwidth reduction. Value can be between 0 to 1.	meters	0.3
	Input	Maximum Lidar Input Interval	If there is no response from one of the lidar sensors for this time duration, that lidar sensor will be considered dead.	seconds	20	[0,30]
		Restart Launchers of Unresponsive Lidars		boolean	TRUE
		Launcher Restart Threshold	When enabled, the system automatically restarts lidar launchers if the algo node does not receive any point cloud messages within the designated lidar restart threshold.	seconds	30	[5, +inf]
		Frame Update Setting	Method for updating new frames from received results - Instant: Update frames as soon as results arrive - Use buffer: Update frames using buffer that stores frames after specified delay time in case of network traffic	int	Instant
		Minimum Pending Time (for Instant update)	Due to connection issues, the time interval between two point-cloud messages of one lidar can be unreasonably small. This minimum interval will ensure that one lidar point-cloud message of the pipeline has a reasonable time gap with the next one. A message which time difference with the previous message is below this minimum interval will get discarded. (This option is only visible if "Instant" is selected in the Frame Update Method.)	seconds	0.02	[0, 0.1]
		Frame Interval [s] (for Instant update)	Whenever data from all LiDARs have arrived, or the frame interval has been reached, the frame will be bundled and processed by the detection node. Only one frame will be bundled per frame interval.		0.1	[0.05, 5]
		Frame Jitter [s] (for Instant update)	The frame bundler will reuse LiDAR point clouds from previous frames, taking into account the frame jitter.		0.02	[0, +inf]
		Number of Frames Operating Delayed (for Using Buffer Update)	Number of frames operating behind the current time. The frame duration is specified by the frame interval parameter.		3	[1, +inf]
		Frame Interval [s] (For Using Buffer Update)	Perception pipeline will be triggered with new input according to the frame interval.		0.15	[0.1, +inf]
	Retro-Reflection Tracking	Enable Retro-Reflection Tracking	Enables marking of objects as retro-reflective. For this to work properly the retro-reflectivity threshold setting for each lidar also needs to be tuned properly.	boolean	FALSE
		Min Point Count	For an object to be considered retro-reflective it has to have at least this many retro-reflective points.	int	5	[1, +inf]
		History Threshold	The number of frames an object will stay retro-reflective after classified as retro-reflective..	int	10	[0, +inf]
	Reflection Filter	Use Simple Filter [2D]	Enable simple filtering algorithm for faster but less accurate filtering. The height will not be considered.	boolean	TRUE
		Use detection limit	If enabled, any sensor further from the reflection filter than the detection limit will not be considered during filtering. A smaller detection limit will make filtering faster.	boolean	TRUE
		Detection limit [m]	Detection range of the option "Use detection limit".	meters	50	[0, +inf]
	Zone Setting	Trigger Zone Events with MISC Objects	Enabling this will trigger zone events with MISC objects.	boolean	FALSE
		Zone Filter Resolution [m]	Grid Cell Size for Zone Filter.	meters	0.1	[0, +inf]
	Tracking History	Tracking History Length	The number of history positions to keep	int	100	[0, +Inf.]
		History Smoothing Level	Trajectory smoothing level	int	3	[0, 3]
	Trajectory Prediction	Number of Prediction Steps	Number of prediction steps	int	10	[0, +Inf.]
		Prediction Step Time-Horizon	Time step between two predicted points	seconds	0.1	[0, +Inf.]
		Max. Acceleration Filter Threshold	Maximum acceleration for prediction	m/s2	15	[0, +Inf.]
	Data Collection	Enable Anomaly Data-Collector	When enabling the Anomaly Data-Collector, the latest "Num Look-Back Frames" are temporarily stored on the disk. Once tha anomaly detector is triggered, the Look-Back and Look-Ahead frames are saved	boolean	FALSE
		Num Look-Back Frames	Number of previous frames temporarily stored on the disk	int	100	[1, +inf]
		Num Look-Ahead Frames	Number of frames stored on disk after anomaly detected	int	100	[1, +inf]
	Logging	Maximum Log File Size [MB]	Sets the Maximum File Size for a single file. Note that the total size of the logs can be much larger.	MB	10	[1, +inf]
		Maximum Number of Log Files Per Directory	The number of rotating log files that will be kept for the master node and each algo node.	int	3	[2, 999]
		Maximum Number of Log Files Per Node	The specified number of the most recent log folders that will be retained for master node and each individual algo and edge node.	int	5	[2, 999]
	Recovery	Connection Timeout [s]	The time after which an unresponsive node is considered as dead. After exceeding this timeout, recovery is attempted.	seconds	20	[3, +inf]
		Recovery Attempt Timeout [s]	If a recovery attempt was not successful after the specified timeout, the recovery attempt is considered as not successful and aborted.	seconds	30	[3, +inf]
		Maximum Number of Recovery Tries		int	10	[0, +inf]
		Time Between Recovery Attempts [s]		seconds	60	[0, +inf]

Master Node Parameters

Master Node parameters define the orchestraion with Algo Nodes and can be found in Settings > Master Node Parameters.

Location	Name	Description	Unit	Default	Range
Rosbag Sync	Max Rosbag Difference [s]	This parameter can be used to make sure that the played rosbag files come approximately from the same recording time. The value of this parameter will limit the difference between the rosbag files in terms of starting and ending time. If the difference between the maximum starting time and the minimum starting time is above this value, the algo nodes will not be launched. The same check is performed for the ending time.	int	3600	[0, +inf]
Master Replay	Use Pseudo Realtome for the Frame-by-Frame Mode		boolean	TRUE
Result Update	Result Update Method	Methods for updating algo nodes results. 0: Instant 1: Use buffer Instant method will process algo nodes results as soon they arrived on master node. Use Buffer method will process algo nodes results based on intervals specified by Algo Nodes Results Update Interval. All received results will be stored in a buffer which maximum size is Number of Algo Node Results Operating Delayed.	int	0	{0,1}
	Number of Algo Node Results Operating Delayed	Number of algo nodes results operating behind the current time.	int	10	[1,+inf]
	Algo Nodes Results Update Interval [s]	Algo nodes results processing will be triggered according to the update interval.	seconds	0.15	[0.01,+inf]
Output-Merger > Algo-Node Result Timeouts	Algo-Node Object Result-Timeout	Compares the elapsed time between 2 algo node of object information messages. if the elapsed time is greater than the threshold, the algo node result is not taken into account during the aggregation.	seconds	2	[0.1, +Inf.]
	Algo-Node Point Result Timeout	For the point result, the point-cloud update frequency is added to this timeout.	seconds	2	[0.1, +Inf.]
	Algo-Node Sensor Status Timeout	For the sensor statuses, the sensor update frequency is added to this timeout.	seconds	10	[0.1, +Inf.]
Output-Merger > Multi Algo-Node Merger	Use Multi Algo Object Association	Merges objects found between 2 algo nodes if they are within bound.	boolean	TRUE
	Grow-Size x-Tolerance	Tolerance on the x-axis for object distortion before merger	meters	2	[0, +Inf.]
	Grow-Size y-tolerance	Tolerance on the y-axis for object distortion before merger	meters	1.5	[0, +Inf.]
	Grow-Size Rate-Tolerance	Distortion tolerance ration before merger	percent	1.2	[0, +Inf.]
	Grow-Size Addition-Tolerance	Additional toleration for object growth before merger	meters	0.5	[0, +Inf.]
	Association Distance Threshold	Distance threshold to associate objects in two nodes	meters	2	[0, +Inf.]

Algo Node Parameters

Algo node parameters define the parameters used by SENSR's multiple algorithms to process 3D data. The parameters are specific to a given Algo node allowing to optimize tracking differently from an Algo node to another. The parameters can be found in Settings > Algo Node Parameters> Algorithm (ip_address). Please change algorithm parameters with caution, as wrong parameters can negatively affect the performance.

Location	Field	Name	Description	Unit	Default	Range
Parameters > Performance		CPU Thread Utilization of the Preprocessing Node [%]	This parameter can be used to optimize the runtime performance of the preprocessing node. It specifies the percentage of the system's CPU threads that will be allocated for computationally expensive tasks on the preprocessing node.	percent	30	[10,100]
		CPU Thread Utilization of the Detection Node [%]	This parameter can be used to optimize the runtime performance of the detection node. It specifies the percentage of the system's CPU threads that will be allocated for computationally expensive tasks on the detection node.	percent	50	[10,100]
		CPU Thread Utilization of the Environment Update Node [%]	This parameter can be used to optimize the runtime performance of the environment node. It specifies the percentage of the system's CPU threads that will be allocated for computationally expensive tasks on the environment node.	percent	10	[10,100]
		CPU Thread Utilization of the Long-Running Tasks Node [%]	This parameter can be used to optimize the runtime performance of the long-running tasks node. It specifies the percentage of the system's CPU threads that will be allocated for computationally expensive tasks on the long-running tasks node.	percent	10	[10,100]
Parameters > Object	-	Allow Floating-Object	If True, min. z of the object is set to be the min. z-value of the object bounding box instead of ground height.	boolean	FALSE
	Filter Objects Based on Number of Points and Radius	Enable	If activated, this filter will sort out objects based on their number of points and their radius.	boolean	TRUE
		Tracked Object's Min. Points	The minimum number of points of an object to be tracked.	int	5	[0, +Inf.]
		Tracked Object's Min Radius	Minimum object radius to be tracked.	meters	0.15	[0, +Inf.]
Parameters > Tracking	-	Validation Period	Period of checking validity in the early stage of tracking. This time determines length of the VALIDATION period, or how quickly a new object will be tracked and classified.	seconds	0.5	[0, +Inf.]
		Invalidation Period	Period of short term prediction when tracking is lost while in the VALIDATION period. A longer period will allow for objects that are at the edge of detection range to be tracked, but will be more likely to introduce false alarms.	seconds	0.5	[0, +Inf.]
		Drifting Period	Period of short term location prediction when tracking is lost in TRACKING status. A longer period can help with obstructions, but can lead to object ID switching in busy environments	seconds	1	[0, +Inf.]
		Drifting Period for Miscellaneous Objects	Drifting period apply for Miscellaneous Objects.	seconds	1	[0, +Inf.]
Parameters > Edge Node	LZ4 Compression	Publish Point Cloud Intensity		boolean	TRUE
		Output Type	Raw Point Cloud: No processing is applied, Filtered Point Cloud: Detection range filtering is applied by default. Downsampling could be applied for further compression.	int	Raw Point Cloud
		Apply LZ4 Compression		boolean	TRUE
		Enable rounding of the coordinate values	Rounding float values can positively affect the compression rate	boolean	TRUE
		Rounding decimal precision	2 means all values will be rounded to 0.01	int	2	[0,inf]
		Sort points in the point cloud	Compression rate can be improved when the point cloud is sorted	boolean	FALSE
Algorithm Components > Ground Detector	Level Ground Detector	Apply	If True, use the ground detector.	boolean	TRUE
		Ground Margin	Maximum height for ground segmentation.	meters	0.3	[-0.5, +Inf.]
		Resolution	Size of the grid used on the ground profiling function	meters	5	[0, +Inf.]
		Limit Detection Range	To limit the ground detection range (xy-range). If enable, all points out of certain xy-range will not be considered as ground points. Note that it's not applied for z detection range.	boolean	FALSE
		Limit Detection Range > Max Detection Range	Maximum xy-range to apply ground detection.	meters	130	[0, +Inf.]
Algorithm Components > Obstruction Detector	Range Obstruction Detector	Apply	The Obstruction detector checks whether the sensors are obstructed or not based on a distance and proportion of obstruction.	boolean	TRUE
		Maximum Distance	This parameter defines the range around the sensor where obstructions will be looked for. If the value is too high, false positives may be triggered by passing objects.	meters	1	[0, +Inf.]
		Obstructed Proportion Threshold	This parameter defines the portion of the pointcloud that has to be obstructed to trigger an alarm. The value is defined as a percentage.	percentage	0.7	[0, 1]
Algorithm Components > Tilt Detection & Auto-Correction	Tilt Detection & Auto-Correction	Apply		boolean	TRUE
		Enable Auto-Correction		boolean	TRUE
		Max Number of Lidar Processed at One Time		int	2	[0, +Inf.]
		Use Points Around Lidar	When disabled, uses all points inside algo node	boolean	FALSE
	Auto-Correction	Min. Angular Offset to Apply Recalibration [deg]	Auto-correction will neglect the change if the detected angle offset is smaller than this threshold.	degrees	0.2	[0.01, +Inf.]
		Min. Distance Offset to Apply Recalibration [m]	Auto-correction will neglect the change if the detected distance offset is smaller than this threshold.	neters	0.1	[0.01, +Inf.]
		Max. Angular Offset to Apply Recalibration [deg]	Auto-correction will not attempt to correct the tilt if the detected angle offset is bigger than this threshold. Lidar Tilt Status will be sent and user is recommended to manually check lidar calibration	degrees	5	[0.01, +Inf.]
		Max. Distance Offset to Apply Recalibration [m]	Auto-correction will not attempt to correct the tilt if the detected distance offset is bigger than this threshold. Lidar Tilt Status will be sent and user is recommended to manually check lidar calibration	neters	0.5	[0.01, +Inf.]
Algorithm Components > Background Detector	Background Detector	Apply	If True, use the background detector.	boolean	TRUE
		Time to Initialize Background	Initiated period to learn background points.	seconds	5	[0, +Inf.]
		Time to Become Background	The period for static objects becomes background.	seconds	600	[1, +Inf.]
		Time to Become Foreground	The period for a background object becomes foreground when it starts moving.	seconds	2	[1, +Inf.]
		Use Multi-lidar Background Fusion	Fuse background information from multi-lidar	boolean	FALSE
		Number of Frames To Estimate Detection Range	Number of initial frames used to estimate the background detection range	int	3	[1, +Inf]
		Use Global Detection Range	If use this option, the global detection range will be used for background detection range instead of using initial frames estimation	boolean	FALSE
		Auto Save	This parameter lets SENSR to save a snapshot of the background pointcloud	boolean	FALSE
		Auto Load	This pararmeter lets SENSR load a perviously saved snapshot of the background points	boolean	FALSE
	Resolutions	Range	Range resolution	meeters	0.2	[0, +Inf.]
		Azimuth	Azimuth angle resolution	degree	0.8	[0, 180]
		Elevation	Elevation resolution	degree	1	[0, 180]
Algorithm Components > Clusterer	Grid-Clusterer	x-Resolution	Grid resolution in x-axis.	meters	0.15	[0, +Inf.]
		y-Resolution	Grid resolution in y-axis.	meters	0.15	[0, +Inf]
		Cell Point Threshold	Minimum points per cell for clustering	int	1	[1, +Inf.]
		Point-Size Growing > Enable Point-Size Growing	To allow using bigger clustering resolution to far-distant objects.	boolean	FALSE
		Point-Size Growing > Point-Size Scaling Factor per Meter	The scaling factor of point size's radius per metter with respect to the distance to lidar.	meters	0.002	[0, 0.01]
		Point-Size Growing > Max. x-Resolution	Max grid resolution in x-axis when using Point-Size Growing.	meters	0.8	[0, +inf]
		Point-Size Growing > Max. y-Resolution	Max grid resolution in y-axis when using Point-Size Growing.	meters	0.8	[0, +inf]
Algorithm Components > Cluster Merger (GPU plug-in)	Cluster Merger	Apply	If True, enables Cluster Merger.	True/ False
Algorithm Components > Tracker	Hybrid-Tracker	Apply	If true, use Hybrid-Tracker	boolean	TRUE
		Association-Distance	Distance threshold to associate objects in two consecutive frames.	meters	1.5	[0.01, +Inf]
		Merge Object Level	Object merging level to decide how easily small closed objects can be merged into one object.	float	4	[0, 10]
		Max. Grow-Size Tolerance	Maximum size of merged object can grow	meters	(1, 2)	[1, +inf]
		Max-Dimensions (W, L)	Maximum size of object can be tracked.	meters	(4, 15)	[0.01, +inf]
	Human-Tracker	Apply	If true, use Human-Tracker	boolean	FALSE
		Association-Distance	Distance threshold to associate objects in two consecutive frames.	meters	0.2	[0.01, +Inf]
		Merge/Split Size Mul. Threshold	Size ratio threshold that allows to merge/split	meters	1.8	[0.0, +Inf]
		Merge/Split Size Add. Threshold	Size increasing/decreasing threshold that allows to merge/split	meters	0.5	[0.0, +Inf]
		Min. Time for Splitting	Minimum lifetime of objects to apply merger/ splitter check	seconds	3	[0.0, +Inf]
	Static tracker	Apply	If True, use GPU Pipeline Supported Tracker	boolean	FALSE
		Tracking Association Distance	Distance threshold to associate objects in two consecutive frames.	meters	2	[0.0, +Inf]
		Bounding Box Configure > Use Object Tight Box	This option will ensure wrap a bounding box as tight as possible around the object	boolean	FALSE
		Bounding Box Configure > Use Position Smoothing	This option will smooth the object's postion to reduce jitter.	boolean	TRUE
		Bounding Box Configure > Use Size Smoother DL Car	This option will adjust the car size to create a more seamless transition, thereby minimizing abrupt changes when occlusion occurs.	boolean	TRUE
		Yaw Smoothing > Apply Heading Smoothing	This option will smooth the yaw of vehicles, reducing abberations.	boolean	TRUE
		Merge/Split Setting > Affected Objects	This parameter allows selecting what types of objects will be affected by the static tracker - Cars only: only cars will be tracked in a static zone - Cars & Small Objects: only small objects will be tracked in a static zone - All Objects: all objects will be tracked in the static zone	int	All Objects
		Merging level	Level of agressiveness on the merging, if objects break due to high speed, use a higher setting	int
		Reference Size Reduce Rate	Shrinking rate of tracked object size. In case of occlusion, the size of a tracked object will be learnt and kept with this shrinking rate.	float	0.98	[0.0, +Inf]
		Use Splitting	Allows spliting objects if needed	boolean	FALSE
		Merge/Split Size Mul. Threshold (Manual Setting)	Additional threshold for merging and splitting process objects	meters	2.1	[0.0, +Inf]
		Merge/Split Size Add. Threshold (Manual Setting) (Min)	Size threshold for merging and splitting process objects	meters	1.5	[0.0, +Inf]
		Merge/Split Size Add. Threshold (Manual Setting) (Max)	Additional threshold for merging and splitting process objects	meters	3	[0.0, +Inf]
		Allow Merging with Deep Learning Vehicle (Manual Setting)		boolean	FALSE
		Increased size Merging Threshold for Deep Learning Vehicle (Manual Setting) (Min)		meters	1
		Increased size Merging Threshold for Deep Learning Vehicle (Manual Setting) (Max)		meters	2
		Max. Distance to Apply Merging [m] (Manual Setting)		meters	1.5
Algorithm Components > Classifier	Light ML Classifier	Apply	If True, use Light ML Classifier	boolean	TRUE
	Target Classification Classes	CAR/PED/CYC/MISC	The classes the output of the classifier will include. E.g. if only PED(estrian) and MISC(ellaneous) are chosen all the objects will be classified as either PED or MISC.	boolean	TRUE
	Only Classify Tracked Objects		If selected, only objects with tracking status will be classified	boolean	TRUE
	Skipped Classification Classes	CAR/PED/CYC/MISC	Any class marked with this option will be ignored by the classifier.	boolean	FALSE
	Object Class Stability	Stability Level	Classification stability level: - Disabled, - Semi-permanently If an object class is stable, the classification will be kept until replaced by another stable class, - Permanently: If an object class is stable, the classification will be kept permanently.		Permanently
		Min. Number of Frames for Stable Class Label	The number of frames an object class need to be continuously kept in order to turn to semi-permanently (for Stability Level = 1) or permanently (for Stability Level = 2).	int	20
		Max. Enlarged size	Size threshold for enlarged objects to maintain their class stabability for PED and CYC	meters	2.5	[0.0, +Inf]
	First Order Classifier		This session will be applied first and only if it can’t classify the objects the send order classifier can assist it.			[0.0, +Inf]
	Size Classifier for Big Objects	Apply	If True, use the size classifier for big objects. If used, all objects which have size bigger than Min Length, Width, Height will be classified as one of Include Classes.	boolean	TRUE
		Length Range/ Width Range/ Height Range	The range of length, width, height to classify as big objects.	meters	[3,20][1.8, 4] [1, 5]	[0, +Inf]
		Include Classes	The classes the output of the size classifier for big objects will include.	boolean	CAR: TRUE, MISC: FALSE
	Size Classifier for Small Objects	Apply	If True, use the size classifier for small objects. If used, all objects which have size in the Length Range, Width Range, Height Range will be classified as one of Include Classes. If an object is classified as a big object, it won’t be classified as a small object even though it’s in the small object range.	boolean	TRUE
		Length Range/ Width Range/ Height Range	The range of length, width, height to classify as small objects.	meters	[0.2, 1.3][0.2, 0.8] [0.5, 2.2]	[0, +Inf]
		Include Classes	If True, the classes the output of the size classifier for big objects will include.	boolean	TRUE
	Velocity Classifier	Apply	If True, use the velocity classifier.	boolean	TRUE
		Non-MISC Min Displacement	Minimum displacement which object will not be classified as a MISC.	meters	2	[0, +Inf]
		Non-MISC Min Velocity	Minimum velocity which object will not be classified as a MISC.	km/h	2	[0, +Inf]
		PED Max Velocity	Minimum velocity which object will not be classified as a PED.	km/h	12	[0, +Inf]
		Use Velocity Estimator	Enable this to use the velocity estimator	boolean	FALSE
	Second Order Classifier > ML Classifier	Apply	If True, use the machine learning classifier. If applied, it will be used only after using size classifier and velocity classifier. E.g, After the size classifier and velocity classifier, the object is classified as either PED or CYC, ML classifier will decide whether it’s a PED or a CYC.	boolean	TRUE
		Min Num Points	Minimum number of points to use ML classifier.	int	30	[0, +inf]
		Max Num Objects To Classify	Maximum number of objects can be classified by ML classier.	int	100	[0, +inf]
Algorithm Components > Object Detector (GPU plug-in)	2D Object Detector	Apply	If True, enables the 2D Object Detector	boolean	TRUE
		Use Light Model	Use light model can speed up processing time. However, it might have a potential impact on the detection quality.	boolean	FALSE
		Car Probability Threshold	Minimum probability to be considered CAR	float	0.45	[0.0, 1.0]
		Pedestrian Probability Threshold	Minimum probability to be considered PED	float	0.35	[0.0, 1.0]
		Cyclist Probability Threshold	Minimum probability to be considered CYC	float	0.35	[0.0, 1.0]
		Exclude Invalid Points	If selected, points in an exclusion zone will not be included in the object detection model.	boolean	FALSE
		Exclude Ground Points	Exclude Ground points from the object detection	boolean	FALSE
		Exclude Ceiling Points	Exclude Ceiling points from the object detection	boolean	FALSE
		Exclude Points in Exclusion Zones	Exclude Exclusion zone points from the object detection	boolean	TRUE
		Use Ground Substraction	Use this parameter working in GPU mode with a significant slope	boolean	FALSE
		Limit Detection Range > Enable	This to allow object detection cover in a smaller area compared to the global detection range model.	boolean	FALSE
		Limit Detection Range > Max Detection Range	Maximum range to apply object detection.	meters	100	[0, +Inf]
Algorithm Components > Output Object Filter	Noise Object Filter	Exclude Zero-Area Objects	Filter objects that have a dimension = 0	boolean	FALSE
		Object Filter Level	Methods for filtering noise objects. Target filtering including low intensity objects and occluded objects. + Object is called "Low Intensity" if the number of points whose intensity is higher than "Intensity Threshold" is smaller than "Min. Number of Bright Points". + Object is called "Occluded" if it is blocked by another objects considering lidar positions. - Disabled : Not using noise object filter. - Filter Low Intensity Occluded Object : Filter objects which is both low intensity and occluded at the same time. - Filter Occluded Object - Filter Low Intensity Object - Filter either Low Intensity or Occluded Object : Filter both low intensity objects and occluded objects.		Disabled
		Intensity Threshold	Intensity Threshold to define low intensity objects.	int	10	[0, +inf]
		Min. Number of Bright Points	Min. Number of Bright Points to define low intensity objects.	int	5	[0, +inf]
Algorithm Components > Ceiling Filter		Apply Ceiling Filtering	Filter to discard points and data coming from the ceiling	boolean	FALSE
		Min Height for Ceiling	Defines the height of the ceiling, points above that value will be discarded	meters	2	[0, +inf]

Visualization parameters

The Visualization settings allow users to change the graphical aspects of SENSR, they can be found in View > Preference (or by pressing F11)

Location	Name	Description	Default
Visibility	Draw Object Points	Enable or disable showing points belonging to objects.	TRUE
	Draw Ground Point	Enable or disable showing ground points. (e.g. floor.)	TRUE
	Draw Background Points	Enable or disable showing background points. (e.g. wall or desk…)	TRUE
	Intensity Visual Mode	Enable this to color point-cloud by intensity values. Off: Intensity color visualization is off. Fixed Range: Use max and min intensity value from Range below. Auto Range: Calculate max and min intensity value from each frame.	0: Off 1: Fixed Range 2: Auto Range
	Draw Grid	Enable or disable showing squared Grid.	TRUE
	Draw Grid Circular	Enable or disable showing circular Grid.	FALSE
	Draw Axis	Enable or disable showing the world XYZ coordinate axis.	TRUE
	Draw Objects	Enable or disable showing tracked objects. (e.g. pedestrian)	TRUE
	Draw Misc Objects	Enable or disable showing miscellaneous objects.	TRUE
	Draw Drifting Objects	Enable or disable showing drifting objects.	TRUE
	Draw Invalidating Objects	Enable or disable showing invalidating objects.	TRUE
	Draw Validating Objects	Enable or disable showing validating objects.	TRUE
	Draw Object Trail	Enable or disable showing the object trail.	TRUE
	Draw Predicted Trajectory	Enable or disable showing the predicted trajectory of moving objects.	FALSE
	Draw Map Image	Enable or disable showing a map image.	TRUE
	Draw Notification Window	Enable or diable showing the Notification window	TRUE
	Draw Detection Range	Enable or disable showing the Detection range	TRUE
	Detection Range Draw Mode	Draws the detection range in either 2D or 3D	3D
	Draw Lidar Name	Enable or disable showing the name of each sensor.	FALSE
	Draw Lidar Topic	Enable or disable showing the topic of each sensor.	FALSE
	Draw Algo Node Name	Enable or disable showing the name of each algo node.	FALSE
	Draw Zone Name	Enable or disable showing the name of each zone.	FALSE
	Draw Retro-Reflective Objects	Enable or disable showing the retro-reflective objects.	FALSE
	Draw Draw Annotations	Enable or disable drawing object annotations	FALSE
	Visible Annotations -> Show Object ID	If object annotations are enabled the object’s ID is shown	TRUE
	Visible Annotations -> Show Object Class and Probability	If object annotations are enabled the object’s class and probability score of that class is shown	FALSE
	Visible Annotations -> Show Object Speed	If object annotations are enabled the object’s speed is shown	TRUE
	Visible Annotations -> Show Object Height	If object annotations are enabled the object’s height is shown	FALSE
Color	Background Color	Color of the background.	-
	Ground Point Color	Color of the ground points.	-
	Background Point Color	Color of the background points.	-
	Object Point Color	Color of points belonging to objects.	-
	Car Color	Color of cars.	-
	Pedestrian Color	Color of pedestrians.	-
	Cyclist Color	Color of cyclists.	-
	Misc Color	Color of miscellaneous objects.	-
	Event Zone Color	Color of event zones.	-
	Exclusion Zone Color	Color of exclusion zones.	-
	Map Exclusion Zone Color	Color of exclusion zones on 3D maps.	-
	Reflection Zone Color	Color of reflection zones.	-
	Static Zone Color	Color of static zones.	-
	Detection Range Color	Color of the detection range outline.	-
	Retro-Reflective Object Color	Color of the retro-reflective object	-
Miscellaneous	Cloud Point Size	Control the visual size of the rendered points. The values can range from 1.0 to 10.0.	1
	Use Random Obj. Color	This option colors each object in a different color.	FALSE
	Grid Interval [m]	Display grid size.	10
View Range	Enable Z Clipping Range	Enable Z-Range to not display pointclouds outside of it	FALSE
	Z Clipping Range Limits [m]	Display Z-range.	[-10.0, 10.0]

Export Configuration

SENSR can export the configuration changes the user has made into a human-readable format. This is useful for checking a project's settings against the settings SENSR uses by default.

To export the configuration changes go to sensor setup mode and in the top menu-bar navigate to File->Export Parameter change Report. This will bring up a dialog-box to choose where to export the text-file.