Appendix 1. Description of the parameters of the configuration file «vehicleEngine.conf»#
General parameters#
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
 |
Allowed | |
| logSeverity | The parameter sets the logging mode of the VehicleEngine | - 4 – logging debug information; |
| - 3 – logging information about work plus information for 4; | ||
| - 2 – logging warning record plus information for 3; | ||
| - 1 – logging error record plus information for 2; | ||
| - 0 – disable logging | ||
| profiling | Profiling | - 0 – profiling is disabled; |
| - 1 – profiling is enabled | ||
| defaultVehicle DetectorType | Vehicle detector by default | VehicleDetectorV4 |
| defaultPlate DetectorType | LP detector by default | PlateDetectorV5 |
| defaultAnimal DetectorType | Animals detctor by default | AnimalDetectorV1 |
| defaultSmokeFire DetectorType | Smoke and Fire detector | SmokeFireDetectorV1 |
| defaultAggregatedPlateAttributes EstimatorType | A version of the algorithm for estimating the accuracy of recognized LP attributes. Each version of the algorithm contains a specific set of countries to evaluate. For more information, see the plate_aggregated_*.conf configuration file in the CARS_API package |
V4; V5 |
| defaultCountryPlateEstimatorType | A version of the algorithm for evaluating the accuracy of recognizing the country of ownership of the LP. Each version of the algorithm contains a specific set of countries to evaluate. For more information, see the grz_country_recognition_*.conf configuration file in the CARS_API package |
V4 |
Estimator AggregatedPlateAttributesEstimator#
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| nonZeroingLPDataScoreThreshold | Parameter to allow zeroing out data when the plate recognition score is low | 0.000…1.000 |
| complexedLPScoreCalcPolicy | Parameter that allows to calculate aggregated license plate score based on averaging the plate recognition score and the plate’s country recognition score | None - off |
| AveragingWithLPCountry Score - on |
Estimator LicensePlateEstimator#
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| aggregatedLPScoreCalcPolicy | Parameter to choose the method of aggregated plate score calculation | - Multiplication (multiply symbols scores); |
| - Average (sum symbols scores divided by the number of symbols); | ||
| - Median (median value) |
Detector VehicleDetectorV4#
Parameters forbidden to be changed#
| Parameter | Description | Possible values |
|---|---|---|
 |
Forbidden | |
| imageSize | The size of the image in pixels on the larger side on which the vehicle is detected. Increasing the size will allow better detection of vehicles in the background, but this will increase the processing time. If it is necessary to detect a large number of small objects, it is recommended to use the VehicleDetectorV2Large detector | 320…1280 |
| minInputSize | Minimum image size for inference. Measured in pixels. The parameter value must be strictly less than the imageSize value. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| squareFormat | Enable Square Format - Automatically adds black bars to the edges of a rectangular frame to create a square frame. Turning it on will increase image processing time | - 0 - on; |
| - 1 – off | ||
| minSize | Minimal size of detection. Detections of a smaller size will not be returned to the user and will not be used for the further processing. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| redetectImageSize | The size of the image in pixels along the larger side, on which the vehicle is redetected | 100…1280 |
| redetectExpandCoeff | Image scaling factor | 1.000…2.000 (1.4375 by default) |
| redetectSquareThreshold | The threshold value for skipping redetections by area. Redetections whose area is less than the specified threshold are not used for further work. The parameter value is derived theoretically and cannot be changed | - |
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
 |
Not recommended | |
| NMSThreshold | Threshold value for non-maximum suppression. The higher the threshold, the higher the probability of detecting a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 |
| SecondNMSThreshold | Rechecking the non-maximum suppression threshold, with a larger value. Increasing the value will reduce the number of false positive detections | 0.000…1.000 |
| detectionToFrameRatioThreshold | Threshold ratio of the detection area to the frame area | 0.000…1.000 |
| nms | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes | ||
| redetectScoreThreshold | Threshold for estimation of vehicle redetection accuracy. Increasing the threshold reduces the number of false negative detection results | 0.000…1.000 (0.25 by default) |
| redetectOneNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.4 by default) |
| redetectNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.5 by default) |
| redetectNMS | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes |
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| ScoreThreshold | Vehicle detection accuracy threshold. Increasing the threshold reduces the number of false positive detections but increases the number of false negative detection (misses) | 0.000…1.000 |
| alignment | This parameter can only be used when the squareFormat=0 parameter is set. When used, it adjusts the height or width of the input image to the specified value, and the remaining space is filled with black pixels. Using this parameter improves performance when working on batch processing. The parameter value must be equal to 2 raised to the power of n (i.e. 2/4/8/16/…) | 2…512 |
| maxFlowerBatchSize | Maximum number of images used for inference at once | 1…16 |
Detector VehicleDetectorV5#
Parameters forbidden to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Forbidden | |
| imageSize | The size of the image in pixels on the larger side on which the vehicle is detected. Increasing the size will allow better detection of vehicles in the background, but this will increase the processing time. If it is necessary to detect a large number of small objects, it is recommended to use the VehicleDetectorV2Large detector | 320…1280 |
| minInputSize | Minimum image size for inference. Measured in pixels. The parameter value must be strictly less than the imageSize value. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| squareFormat | Enable Square Format - Automatically adds black bars to the edges of a rectangular frame to create a square frame. Turning it on will increase image processing time | - 0 - on; |
| - 1 – off | ||
| minSize | Minimal size of detection. Detections of a smaller size will not be returned to the user and will not be used for the further processing. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| redetectImageSize | The size of the image in pixels along the larger side, on which the vehicle is redetected | 100…1280 |
| redetectExpandCoeff | Image scaling factor | 1.000…2.000 (1.4375 by default) |
| redetectSquareThreshold | The threshold value for skipping redetections by area. Redetections whose area is less than the specified threshold are not used for further work. The parameter value is derived theoretically and cannot be changed | - |
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Not recommended | |
| NMSThreshold | Threshold value for non-maximum suppression. The higher the threshold, the higher the probability of detecting a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 |
| SecondNMSThreshold | Rechecking the non-maximum suppression threshold, with a larger value. Increasing the value will reduce the number of false positive detections | 0.000…1.000 |
| detectionToFrameRatioThreshold | Threshold ratio of the detection area to the frame area | 0.000…1.000 |
| nms | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes | ||
| redetectScoreThreshold | Threshold for estimation of vehicle redetection accuracy. Increasing the threshold reduces the number of false negative detection results | 0.000…1.000 (0.25 by default) |
| redetectOneNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.4 by default) |
| redetectNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.5 by default) |
| redetectNMS | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes |
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| ScoreThreshold | Vehicle detection accuracy threshold. Increasing the threshold reduces the number of false positive detections but increases the number of false negative detection (misses) | 0.000…1.000 |
| alignment | This parameter can only be used when the squareFormat=0 parameter is set. When used, it adjusts the height or width of the input image to the specified value, and the remaining space is filled with black pixels. Using this parameter improves performance when working on batch processing. The parameter value must be equal to 2 raised to the power of n (i.e. 2/4/8/16/…) | 2…512 |
| maxFlowerBatchSize | Maximum number of images used for inference at once | 1…16 |
Detector VehicleDetectorV6#
Parameters forbidden to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Forbidden | |
| imageSize | The size of the image in pixels on the larger side on which the vehicle is detected. Increasing the size will allow better detection of vehicles in the background, but this will increase the processing time. If it is necessary to detect a large number of small objects, it is recommended to use the VehicleDetectorV2Large detector | 320…1280 |
| minInputSize | Minimum image size for inference. Measured in pixels. The parameter value must be strictly less than the imageSize value. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| squareFormat | Enable Square Format - Automatically adds black bars to the edges of a rectangular frame to create a square frame. Turning it on will increase image processing time | - 0 - on; |
| - 1 – off | ||
| minSize | Minimal size of detection. Detections of a smaller size will not be returned to the user and will not be used for the further processing. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| redetectImageSize | The size of the image in pixels along the larger side, on which the vehicle is redetected | 100…1280 |
| redetectExpandCoeff | Image scaling factor | 1.000…2.000 (1.4375 by default) |
| redetectSquareThreshold | The threshold value for skipping redetections by area. Redetections whose area is less than the specified threshold are not used for further work. The parameter value is derived theoretically and cannot be changed | - |
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Not recommended | |
| NMSThreshold | Threshold value for non-maximum suppression. The higher the threshold, the higher the probability of detecting a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 |
| SecondNMSThreshold | Rechecking the non-maximum suppression threshold, with a larger value. Increasing the value will reduce the number of false positive detections | 0.000…1.000 |
| detectionToFrameRatioThreshold | Threshold ratio of the detection area to the frame area | 0.000…1.000 |
| nms | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes | ||
| redetectScoreThreshold | Threshold for estimation of vehicle redetection accuracy. Increasing the threshold reduces the number of false negative detection results | 0.000…1.000 (0.25 by default) |
| redetectOneNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.4 by default) |
| redetectNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.5 by default) |
| redetectNMS | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes |
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| ScoreThreshold | Vehicle detection accuracy threshold. Increasing the threshold reduces the number of false positive detections but increases the number of false negative detection (misses) | 0.000…1.000 |
| alignment | This parameter can only be used when the squareFormat=0 parameter is set. When used, it adjusts the height or width of the input image to the specified value, and the remaining space is filled with black pixels. Using this parameter improves performance when working on batch processing. The parameter value must be equal to 2 raised to the power of n (i.e. 2/4/8/16/…) | 2…512 |
| maxFlowerBatchSize | Maximum number of images used for inference at once | 1…16 |
Detector VehicleDetectorV7#
Parameters forbidden to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Forbidden | |
| imageSize | The size of the image in pixels on the larger side on which the vehicle is detected. Increasing the size will allow better detection of vehicles in the background, but this will increase the processing time. If it is necessary to detect a large number of small objects, it is recommended to use the VehicleDetectorV2Large detector | 320…1280 |
| minInputSize | Minimum image size for inference. Measured in pixels. The parameter value must be strictly less than the imageSize value. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| squareFormat | Enable Square Format - Automatically adds black bars to the edges of a rectangular frame to create a square frame. Turning it on will increase image processing time | - 0 - on; |
| - 1 – off | ||
| minSize | Minimal size of detection. Detections of a smaller size will not be returned to the user and will not be used for the further processing. This parameter is selected theoretically, has one default value and must not be changed by users | - |
| redetectImageSize | The size of the image in pixels along the larger side, on which the vehicle is redetected | 100…1280 |
| redetectExpandCoeff | Image scaling factor | 1.000…2.000 (1.4375 by default) |
| redetectSquareThreshold | The threshold value for skipping redetections by area. Redetections whose area is less than the specified threshold are not used for further work. The parameter value is derived theoretically and cannot be changed | - |
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Not recommended | |
| NMSThreshold | Threshold value for non-maximum suppression. The higher the threshold, the higher the probability of detecting a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 |
| SecondNMSThreshold | Rechecking the non-maximum suppression threshold, with a larger value. Increasing the value will reduce the number of false positive detections | 0.000…1.000 |
| detectionToFrameRatioThreshold | Threshold ratio of the detection area to the frame area | 0.000…1.000 |
| nms | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes | ||
| redetectScoreThreshold | Threshold for estimation of vehicle redetection accuracy. Increasing the threshold reduces the number of false negative detection results | 0.000…1.000 (0.25 by default) |
| redetectOneNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.4 by default) |
| redetectNMSThreshold | The value of the non-maximum suppression threshold for vehicle redetection. The higher the threshold, the higher the probability of repeated detection of a vehicle blocked by objects. Increasing the threshold will increase the number of false positive detections | 0.000…1.000 (0.5 by default) |
| redetectNMS | Parameter affecting the accuracy of vehicle localization on the frame. Higher accuracy, reduces performance. | - best – the mode in which the best BBox is the one whose intersection with other BBoxes has the maximum value; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes |
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| ScoreThreshold | Vehicle detection accuracy threshold. Increasing the threshold reduces the number of false positive detections but increases the number of false negative detection (misses) | 0.000…1.000 |
| alignment | This parameter can only be used when the squareFormat=0 parameter is set. When used, it adjusts the height or width of the input image to the specified value, and the remaining space is filled with black pixels. Using this parameter improves performance when working on batch processing. The parameter value must be equal to 2 raised to the power of n (i.e. 2/4/8/16/…) | 2…512 |
| maxFlowerBatchSize | Maximum number of images used for inference at once | 1…16 |
Detector PlateDetectorV5#
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Not recommended | |
| ScoreThreshold | LP detection accuracy threshold. Increasing the threshold reduces the number of false positive detections, but increases the number of false negatives (missed LP). | 0.000…1.000 |
| imageSize | The image size in pixels along the larger side where license plate detection occurs. This size is fixed to achieve the best detection results. Increasing the size will improve the detection of small license plates on large vehicles, but it will also increase processing time | 200…440 |
| maxFlowerBatchSize | Maximum number of images used for inference at once | 1…16 |
| NMSThreshold | The threshold value of the nms parameter. The higher the threshold, the greater the likelihood of detecting a license plate that is overlapped by other objects (not of interest). Increasing the threshold will lead to an increase in the number of false positive detections | 0.000…1.000 |
| SecondNMSThreshold | An additional threshold for the nms parameter to perform a reprocessing step of the algorithm. This threshold should be set to a higher value than the NMSThreshold parameter. Increasing this value will help reduce the number of false positive detections | 0.000…1.000 |
| nms | Selection of the algorithm mode for suppressing the non-maximum BBox of the license plate to choose the best BBox within the detection procedure. This parameter affects the accuracy of determining the license plate's position in the frame. The higher the accuracy, the lower the processing speed | - best – the mode in which the best BBox is considered the one that has the maximum intersection with other BBoxes; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes | ||
| detectionToFrameRatioThreshold | Threshold ratio of the detection area to the frame area | 0.000…1.000 |
Detector SmokeFireDetectorV1#
Parameters allowed to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Allowed | |
| ScoreThreshold | Increasing the threshold reduces the number of false positive detections, but increases the number of false negatives (missed detections of smoke and fire) | 0.000…1.000 |
Detector AnimalDetectorV1#
Parameters forbidden to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Forbidden | |
| minSize | Minimal size of detection. Detections of a smaller size will not be returned to the user and will not be used for the further processing. This parameter is selected theoretically, has one default value and must not be changed by users | - |
Parameters not recommended to be changed#
| Parameter | Description | Possible values |
|---|---|---|
|
Not recommended | |
| ScoreThreshold | Increasing the threshold reduces the number of false positive detections, but increases the number of false negatives (missed animal detections) | 0.000…1.000 |
| NMSThreshold | The higher the threshold, the greater the likelihood of detecting an animal that is overlapped by other objects (not of interest). Increasing the threshold will result in more false positive detections | 0.000…1.000 |
| imageSize | Increasing the size will improve the detection of small animals, but will also increase processing time | 320…1280 |
| nms | This parameter affects the accuracy of determining the animal's position in the frame. The higher the accuracy, the lower the processing speed | - best – the mode in which the best BBox is considered the one with the maximum intersection with other BBoxes; |
| - mean – the mode in which the best BBox is determined by averaging the values of all intersecting BBoxes |