针对经典霍夫车道线检测方法实用性较差,无法准确区分车道线和路沿与应用道路场景简单等问题,提出了一种基于消失点和颜色过滤器的车道线检测算法,不仅提高车道线检测的准确率,而且能够应用较复杂行车场景;首先,对行车视频连续五帧图像...针对经典霍夫车道线检测方法实用性较差,无法准确区分车道线和路沿与应用道路场景简单等问题,提出了一种基于消失点和颜色过滤器的车道线检测算法,不仅提高车道线检测的准确率,而且能够应用较复杂行车场景;首先,对行车视频连续五帧图像进行预处理,获取行车环境下车道线消失点位置,能够自适应选取行车环境图像的感兴趣区域(Region of Interest,ROI);然后,对ROI图像根据车道线颜色特征进行过滤得到二值图像,获取二值图像中所有连通区域质心和倾斜角等数据,通过结合消失点特征和角度阈值进行限制,筛选记录符合车道线特征连通区域的数据,接着分割较大区域获取更多质心点,识别漏检符合车道线特征的区域质心点;最后,对获取的质心点使用最小二乘法进行拟合并标识车道线;实验结果表明:算法能够在多场景道路上快速准确的检测出车道线,与经典霍夫算法进行仿真比较,算法具有一定的鲁棒性和实时性。展开更多
To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventiona...To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventional filters whose template shapes and coefficients were fixed,multi-templates were defined and the right template for each pixel could be matched adaptively based on local image characteristics in the proposed method.The superiority of this method was verified by former results concerning the matching experiment of actual image with the comparison of conventional filtering methods.The adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover(IGAE) was used to optimize threshold t of the transformation function,and then combined with wavelet transformation to estimate noise variance.Multi-experiments were performed to test the validity of IGAE.The results show that the filtered result of t obtained by IGAE is superior to that of t obtained by other methods,IGAE has a faster convergence speed and a higher computational efficiency compared with the canonical genetic algorithm with the elitism and the immune algorithm with the information entropy and elitism by multi-experiments.展开更多
A more efficiem noise filtering technique is needed in ensemble data assimilation, to improve traditional spectral filtering methods that cannot reflect the local characteristics of spatial scales. In this paper, we p...A more efficiem noise filtering technique is needed in ensemble data assimilation, to improve traditional spectral filtering methods that cannot reflect the local characteristics of spatial scales. In this paper, we present the design of a novel constrained wavelet threshold denoising method （CWTDNM） by introducing an improved threshold value and a new constraining parameter. The proposed method aims to filter noise swamped over different scales. We prepared an ideal experiment object based on the two-dimensional barotropic vorticity equation. A suitable wavelet basis function （i.e., Dbl 1） and the optimal number of decomposition levels （i.e., five） were first selected. The results show that, given the wavelet coefficients are constrained by the parameter, the CWTDNM can produce better filtering results with the smallest root mean square error （RMSE） compared to similar methods. In addition, the filtering accuracy of 10 ensemble sample variances using the CWTDNM is equivalent to that estimated directly from 80 ensemble samples, but with the runtime reduced to approximately one-seventh. Furthermore, a large peak signal-to-noise ratio, which implies a low RMSE, suggests that the proposed method suitably preserves most of the information after denoising.展开更多
文摘针对经典霍夫车道线检测方法实用性较差,无法准确区分车道线和路沿与应用道路场景简单等问题,提出了一种基于消失点和颜色过滤器的车道线检测算法,不仅提高车道线检测的准确率,而且能够应用较复杂行车场景;首先,对行车视频连续五帧图像进行预处理,获取行车环境下车道线消失点位置,能够自适应选取行车环境图像的感兴趣区域(Region of Interest,ROI);然后,对ROI图像根据车道线颜色特征进行过滤得到二值图像,获取二值图像中所有连通区域质心和倾斜角等数据,通过结合消失点特征和角度阈值进行限制,筛选记录符合车道线特征连通区域的数据,接着分割较大区域获取更多质心点,识别漏检符合车道线特征的区域质心点;最后,对获取的质心点使用最小二乘法进行拟合并标识车道线;实验结果表明:算法能够在多场景道路上快速准确的检测出车道线,与经典霍夫算法进行仿真比较,算法具有一定的鲁棒性和实时性。
基金Project(20040533035) supported by the National Research Foundation for the Doctoral Program of Higher Education of ChinaProject (60874070) supported by the National Natural Science Foundation of China
文摘To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventional filters whose template shapes and coefficients were fixed,multi-templates were defined and the right template for each pixel could be matched adaptively based on local image characteristics in the proposed method.The superiority of this method was verified by former results concerning the matching experiment of actual image with the comparison of conventional filtering methods.The adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover(IGAE) was used to optimize threshold t of the transformation function,and then combined with wavelet transformation to estimate noise variance.Multi-experiments were performed to test the validity of IGAE.The results show that the filtered result of t obtained by IGAE is superior to that of t obtained by other methods,IGAE has a faster convergence speed and a higher computational efficiency compared with the canonical genetic algorithm with the elitism and the immune algorithm with the information entropy and elitism by multi-experiments.
基金supported by the National Natural Science Foundation of China(Grant Nos.41375113,41475094,41305101&41605070)
文摘A more efficiem noise filtering technique is needed in ensemble data assimilation, to improve traditional spectral filtering methods that cannot reflect the local characteristics of spatial scales. In this paper, we present the design of a novel constrained wavelet threshold denoising method （CWTDNM） by introducing an improved threshold value and a new constraining parameter. The proposed method aims to filter noise swamped over different scales. We prepared an ideal experiment object based on the two-dimensional barotropic vorticity equation. A suitable wavelet basis function （i.e., Dbl 1） and the optimal number of decomposition levels （i.e., five） were first selected. The results show that, given the wavelet coefficients are constrained by the parameter, the CWTDNM can produce better filtering results with the smallest root mean square error （RMSE） compared to similar methods. In addition, the filtering accuracy of 10 ensemble sample variances using the CWTDNM is equivalent to that estimated directly from 80 ensemble samples, but with the runtime reduced to approximately one-seventh. Furthermore, a large peak signal-to-noise ratio, which implies a low RMSE, suggests that the proposed method suitably preserves most of the information after denoising.
