基于反对称小波的车型识别研究

基金项目: 国家自然科学基金资助项目(79970025);国防科技预研基金资助项目(00J15.3.JW0528)

详细信息

Vehicle Recognition Based on Anti-symmetrical Wavelet

¹ Dept. of Control Science & Engineering,Huazhong University of Science and Technology,1037 Luoyu Road,Wuhan 430074, China;² School of Computer Science, Wuhan University, 129 Luoyu Road,Wuhan 430079,China;

Funds: 国家自然科学基金资助项目(79970025);国防科技预研基金资助项目(00J15.3.JW0528)

摘要: 在对车型识别去噪和边缘检测进行分析的基础上,提出了一种基于反对称小波的检测方法。首先采用尺度间相关性和尺度内相位法进行有效去噪,然后检测变换模极大值,并进行有效区分保留真正边缘模极大值,最后进行相关恢复处理得到比较清晰的车型边缘。结果表明,该方法提高了车型边缘检测的准确性和车型识别率,具有很好的应用前景
- 去噪 /
- 边缘检测 /
- 反对称小波 /
- 车型识别
Abstract: On the basis of the analysis of denoising and edge detection of vehicle recognition, this paper proposes an effective detection method based on anti-symmetrical wavelet. The specific steps are illustrated. The results verify that this method improves the precision and the level of recognition.
- enoising /
- edge detection /
- anti-symmetrical wavelet /
- vehicle recognition