摘要
本文利用BP神经网络抗干扰性强,识别精准等优点对船舶进行识别跟踪。首先获取原始图像,然后预处理,以图像的全部灰度值为训练样本,以新不变矩特征向量为样本集输入到3层BP神经网络中,对含不同噪声均值的图像进行识别。实验结果表明,以新不变矩特征向量作为样本集时抗噪能力强,识别率高。最后以新不变矩特征向量作为样本集进行目标跟踪得到跟踪误差。
In this paper, because of strong interference and precise identificatio neural network to identification and tracking of ships. First, get the original image, n, etc., use BP then pretreated. Respectively, all of grayscale images is training samples and a new moment invariant feature vector for the sample set input to the BP neural network. Use BP Experimental results show that when a new moment neural network to identify images with different noise. invariant feature vectors as the sample set has strong noise immunity and high recognition rate. Finally, a new moment invariant feature vectors as the sample set for target tracking to get the tracking error
出处
《舰船科学技术》
北大核心
2015年第4期219-222,共4页
Ship Science and Technology
关键词
神经网络
BP算法
图像识别
图像跟踪
neural network
BP algorithm
image recognition
image tracking
