Please enable JavaScript to view this site.

Deprecated, the IDSAxon is only used in the Module-X v1.
For later models use this link

 

In ANPR the infrared sensor is the main sensor to provide the images for recognition.

The settings of this sensor can be changed in the IDSAxon.

Default the resolution of the sensor is 1600 by 900 pixels. This resolution enables a large viewing area where more then one license plate can be recognized.  Analyzing an image with this size costs a certain amount of processing power. When possible the image should be cropped by choosing an optimal Region of Interest ,ROI. This will boost the amount of frames per second.

 

Important! Cropping is done in the IDSAxon. Do not use the ImgCropAxon. The operations of this Axon will cost more processing power.

A new feature is the crop map, where recognitions of the past determine the cropped area.

 

The benefits of ROI explained

 

Higher framerate

By cropping the image in the image sensor itself, the image sensor can produce more frames per second.

 

Less pixels to process

Next to a higher framerate, adjusting the region of interest by cropping, speeds up recognition. Less pixels mean less processing power is needed per image.

 

Less background noise

Cropping minimizes the amount of random background that needs to be analyzed. This will not only speed up recognition, but will improve performance as well.

 

Higher threshold values

Thresholding is the tool to correct circumstances that influence a straight forward recognition like head lights shining in the camera, license plate that are difficult to read.

The threshold defines the amount of times a license plate needs to be recognized identically to become a valid Anpr result. An increase in frame rate allows for higher threshold values. The higher the threshold values the more accurate the result will be. The threshold and its parameters can be configured in the ANPRThresholdAxon.

 

 

Selecting the region of interest

 


MIR_Select_ROI_ANPR_sensor_4

MIR_Select_ROI_ANPR_sensor_3

 

The viewpanel of the IDSAxon diplays the live view of the IR sensor.

 

Rubber banding can be used to select an area of interest. Hold left mouse button, draw the rectangle of the desired region of interest and let go.

 

The view of the Axon will immediately change. To reverse the crop click 'reset image size'.

 

 

 

 

 

Using the crop map


MIR_Select_ROI_ANPR_sensor_5

 

 

A special feature to get the best possible recognition area is the "crop map" function of the IDSAxon.

The coordinates of recognized license plates are stored and are used to determine the best crop area.

 

The "crop map" is an overlay, that can be activated by right clicking the view of the IDSAxon and choose "crop map". The overlay will show the crop map as a cloud, that represents all past recognitions.

 

The cloud is the most dense (white) in the area most license plates are recognised.

In the black parts of the image, no license plate is ever read.

In the screenshot the crop can even less high.

 

 

 

Some examples of cropped images






GK_DE.AC-BY1712

GK_PL.OK-66777

GK_CW.D37-3