智能视频监控中舰船假目标图像检测算法

Research on image detection algorithms for ship false targets in intelligent video surveillance

传统舰船假目标图像检测算法存在检测精准度低的缺陷,为此提出智能视频监控中舰船假目标图像检测算法研究。将智能视频监控中采集的图像采用灰度化处理得到灰度图像,利用直方图均衡化处理灰度图像,提升图像的质量。采用滤波处理方法将得到的图像进行去噪,完成图像的预处理,为图像检测做准备。采用小波变换方法对上述得到的图像进行特征提取,将得到的图像特征输入到图像检测模型中,与真目标图像特征进行逐一比较,输出假目标图像,实现了对舰船假目标图像的检测。实验结果表明,提出的舰船假目标图像检测算法检测精准度比传统算法高出21.8%,说明提出的舰船假目标图像检测算法具备极高的有效性。

Traditional ship false target image detection algorithm has the defect of low detection accuracy, so this paper proposes the research of ship false target image detection algorithm in intelligent video surveillance. The gray image is acquired by gray processing in intelligent video surveillance. The gray image is processed by histogram equalization to improve the quality of the image. The image is denoised by filtering method, and the image preprocessing is completed to prepare for image detection. Wavelet transform method is used to extract the features of the above-mentioned images. The obtained image features are input into the image detection model, and compared with the real target image features one by one. The false target image is output, which realizes the detection of the ship false target image. The experimental results show that the detection accuracy of the proposed algorithm is 21.8% higher than that of the traditional algorithm, which shows that the proposed algorithm is highly effective.