Image processing method capable of detecting noise and related navigation device

1. An image processing method capable of detecting noise, comprising:

adjusting a lighting unit to acquire an over-exposure image;

comparing each pixel of the over-exposure image with at least one threshold value;

labeling a pixel of the over-exposure image as the noise while bright intensity of the foresaid pixel is lower than the threshold value;

calculating a simulating value according to bright intensity of pixels around the noise and except the noise; and

utilizing the simulating value and bright intensity of other pixels except the noise to execute a displacement detecting calculation;

wherein a computation step for labeling the noise is configured to identify the noise by one of the convolutional neural networks of VGGNet, ResNet, and Inception.

2. The image processing method of claim 1 , wherein adjusting the lighting unit to acquire the over-exposure image comprises:

increasing an exposure duration and/or an exposure intensity of the lighting unit to acquire the over-exposure image.

3. The image processing method of claim 1 , wherein executing the displacement detecting calculation comprises:

removing the noise from the over-exposure image; and

utilizing the over-exposure image without the noise to execute the displacement detecting calculation.

4. The image processing method of claim 1 , wherein executing the displacement detecting calculation comprises:

adjusting the lighting unit to acquire an non-exposure image;

removing the noise from the non-exposure image; and

utilizing the non-exposure image without the noise to execute the displacement detecting calculation.

5. The image processing method of claim 1 , wherein the image processing method is applied to a navigation device having the lighting unit and an image capturing unit, and executing the displacement detecting calculation comprises:

utilizing the image capturing unit to respectively acquire capturing images with the same reference characteristic at different time; and

recognizing position variation of the reference characteristic within the capturing images to determine a displacement of the navigation device.

6. The image processing method of claim 1 , wherein executing the displacement detecting calculation comprises:

ignoring the pixel corresponding to the noise; and

executing the displacement detecting calculation by bright intensity of other pixels except the noise.

7. The image processing method of claim 1 , wherein the predetermined function calculates the simulating value according to the bright intensity of the adjacent pixels by interpolation method, or calculates a mean value or a median value of the bright intensity of the adjacent pixels to be the simulating value.

8. A navigation device with noise detection function, comprising:

a lighting unit, having an adjustable shutter and/or an adjustable diaphragm;

an image capturing unit; and

a processing unit electrically connected to the lighting unit and the image capturing unit, the processing unit being adapted to adjust the adjustable shutter and/or the adjustable diaphragm to acquire an over-exposure image via the image capturing unit, to compare each pixel of the over-exposure image with at least one threshold value, and to label a pixel of the over-exposure image as noise while bright intensity of the foresaid pixel is lower than the threshold value, so as to calculate a simulating value according to bright intensity of pixels around the noise and except the noise, and to execute a displacement detecting calculation by utilization of the simulating value and bright intensity of other pixels except the noise;

wherein a computation step for labeling the noise is configured to identify the noise by one of the convolutional neural networks of VGGNet, ResNet, and Inception.

9. The navigation device of claim 8 , wherein the processing unit delays the adjustable shutter to increase an exposure duration of the lighting unit, or enlarges the adjustable diaphragm to increase an exposure intensity of the lighting unit.

10. The navigation device of claim 8 , wherein the lighting unit has a first operating mode and a second operating mode, and the processing unit switches the lighting unit into the first operating mode to acquire the over-exposure image.

11. The navigation device of claim 8 , wherein the processing unit removes the noise from the over-exposure image, and utilizes the over-exposure image without the noise to execute the displacement detecting calculation.

12. The navigation device of claim 10 , wherein the processing unit further switches the lighting unit into the second operating mode to acquire a non-exposure image, and removes the noise from the non-exposure image to execute the displacement detecting calculation by the non-exposure image without the noise.

13. The navigation device of claim 8 , wherein the processing unit utilizes the image capturing unit to respectively acquire capturing images with the same reference characteristic at different time, and recognizes position variation of the reference characteristic within the capturing images to determine a displacement of the navigation device.

14. The navigation device of claim 8 , wherein the pixel corresponding to the noise is ignored, and the displacement detecting calculation is executed by bright intensity of other pixels except the noise.

15. The navigation device of claim 8 , wherein the predetermined function calculates the simulating value according to the bright intensity of the adjacent pixels by interpolation method, or calculates a mean value or a median value of the bright intensity of the adjacent pixels to be the simulating value.