Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 5 Next »

The Witness software will attempt to reliably classify all targets based on all the attributes available from the radar sensor. It does this using a weighted scoring system based on a series of pre-defined models. Each model provides a series of value ranges and the prioritises the values which are more relevant to that classification type. When a target under analysis conforms to the specified values a weighted scoring is added for the matching model or models. Once the agreed number of classification samples have been processed then the model which has achieved the highest score is selected. A probability is assigned to each classification based on the score where 100% is a classification with the highest confidence.

Since V3.12 the classification has been improved to work with aggregated values, which means we can sample the data, apply a suitable statistical summary (i.e. min, max, average etc) and then use these values to test each model. This has proved to be a more reliable way of distinguishing between targets which are exhibiting similar behaviour to another classification type (i.e. a vehicle vs a person when the vehicle is moving at walking pace).

The information in this section will be based on the newer statistical approach implemented in V.312 and later. 

On this page:

Target Assessment


Each target (or track) is assessed based on properties provided by the radar and tracking software. These are as follows:

SerPropertyDescriptionDefault Assessment
1SizeThe surface area of the target calculated using size in range x size in azimuth.Does the (truncated) average size of the track across all sightings fall within the range of the model?
2SpeedThe speed of the track.Does the maximum speed seen across all sightings fall within the range of the model?
3Expected SpeedThe typical speed expected of a track. This would normally be a smaller subset of the overall speed range. For example a car can move as slowly as a walking person, however its expected speed would normally be much quicker.Does the (truncated) average speed of the track across all sightings fall within the expected speed range of the model?
4AccelerationThis is the change in speed between track sightings.Does the maximum acceleration across all sightings fall within the range of the model?
5WeightThe total number of cells that make up the target.Does the (truncated) average number of cells across all sightings fall within the range of the model?
6StrengthSum of the signal strength for each cell which makes up the target. Note this value is only truly effective if using "Input" or "Level Above" for the thresholding process.Does the (truncated) average signal strength across all samples fall within the range of the model?
7Seen Moving

8Direction ChangeThe absolute change in direction from one sighting to the next.Does the average change in direction across all sightings fall within the range of the model?

Categories

Each track property is group into a category. This is so each category can be weighted on a model by model to ensure the scoring system is biased towards the key attributes for a specific classification.

The categories are as follows:

SerCategoryDefault Properties
1Speed and AccelerationSpeed, Expected Speed and Acceleration
2Weight and StrengthWeight and Strength
3BehaviourSeen Moving and Direction Change
4SizeSize

Category and Property Weighting

Each category and property is given a weighting. This can vary from model to model. These weightings will directly affect the model scoring. For example, if a target property matches a critical attribute then the score will be 5, whereas a matching optional property would only get a single point.

SerCategoryScore Weighting
1Criticalx5
2Desirablex3
3Optionalx1

Related information

  • No labels