for Vision Navigation System of Agricultural Vehicle in Weed Environment

Abstract:

560ms。 The effect of the weed environment on the path recognition is investigated. On the basis of the conventional path recognition method, a new method based on the BP neural network for the path recognition in the weed environment is proposed. Experimental results prove that the new method is effective for the path recognition in the weed environment, and can obtain the target navigation path rapidly, reliably and accurately. The recognition correct rate is 97%, and the average cost time is 560 ms.