Login

Proceedings

Find matching any: Reset
Add filter to result:
Crop Row Detection in Maize Fields Inspired on the Human Visual Perception
Z. xueguan, F. Pengfei, M. Wei, W. Xiu
National Engineering Research Center for Intelligent Equipment in Agricultural

It is easy to be interfered with the existing crop positioning method and the slower processing speed, a method of crop line image robust inverse perspective transformation based on vanishing point detection is proposed. Inverse perspective mapping (IPM) has been widely used in computer vision and road traffic makings detection and recognition. Inverse perspective mapping is the inverse process of perspective mapping. It maps the image from the image coordinates to the world coordinate by a combination of intrinsic and extrinsic parameters of the camera, and eliminate the perspective effect. Therefore, a robust inverse perspective mapping method plays a very important role in eliminating the perspective influence and obtaining the invariant information of the image. This paper studies the robust inverse perspective mapping methods based on the vanishing point and its application, and then uses the inverse perspective mapping to detect and recognize the arrow road markings. Using the vanishing point coordinates to calculate the deviation distance of the machine, to provide real-time deviation distance parameter for inverse perspective transform. At the same time, an inverse perspective transform method is improved, correct the deviation, improve the quality of planar top view. Firstly, the vanishing point coordinates are detected, then according to vanishing point calculator yaw distance, finally, the view of the field plane is obtained by reverse perspective transformation, to eliminate the perspective deformation of the field plane. Processing an 840pixel x 680pixel image takes about 28.6 ms, the accuracy of the algorithm is 30 times higher than the direct Houg h transformation detection method, the obtained positioning baseline can represent the trend of the crops.