Vehicle detection method based on deep convolution neural network
A convolutional neural network, vehicle detection technology, applied in the field of road safety, to achieve high accuracy and avoid limitations
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0031] Such as Figure 1-Figure 4 As shown, a vehicle detection method based on deep convolutional neural network, including:
[0032] The camera collects the road surface picture in real time, preprocesses and normalizes its size, the preprocessing includes grayscale and mean value filtering, and the camera is a monocular camera;
[0033] Segment the shadow area of road vehicles by selecting an appropriate threshold;
[0034] Since 1 / 3 of a general road image contains irrelevant information such as the sky and mountains, we only need to detect the area below 1 / 3 of the image. Generally speaking, the shadow is caused by the light being obscured by the vehicle, so the gray level of the general shadow The value is lower than the road surface, so just get the normal gray value of the road surface, and the bottom shadow can be segmented out.
[0035] In order to prevent the influence of ground signs such as speed bumps and text, this paper combines the current statistical data...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 