At present, most lane line detection methods are aimed at simple road surface. There is still no good solution for the situation that the lane line contains arrow, text and other signs. The edge left by markers such a...At present, most lane line detection methods are aimed at simple road surface. There is still no good solution for the situation that the lane line contains arrow, text and other signs. The edge left by markers such as arrow and text will interfere with the detection of lane lines. In view of the situation of arrow mark and text mark interference between lane lines, the paper proposes a new processing algorithm. The algorithm consists of four parts, Gaussian blur, image graying processing, DLD-threshold (Dark-Light-Dark-threshold) algorithm, correlation filter edge extraction and Hough transform. Among them, the DLD-threshold algorithm and related filters are mainly used to remove the identification interference between lane lines. The test results on the Caltech Lanes dataset are given at the end of the article. The result of verification of this algorithm showed a max recognition rate of 97.2%.展开更多
通过自动识别自然环境下获取果实图像中的未成熟果实,以实现自动化果实估产的目的。该文以番茄为对象,根据视觉显著性的特点,提出了使用基于密集和稀疏重构(dense and sparse reconstruction,DSR)的显著性检测方法检测未成熟番茄果实图...通过自动识别自然环境下获取果实图像中的未成熟果实,以实现自动化果实估产的目的。该文以番茄为对象,根据视觉显著性的特点,提出了使用基于密集和稀疏重构(dense and sparse reconstruction,DSR)的显著性检测方法检测未成熟番茄果实图像,该方法首先计算密集和稀疏重构误差;其次使用基于上下文的重构误差传播机制平滑重构误差和提亮显著性区域;再通过多尺度重构误差融合与偏目标高斯细化;最后通过贝叶斯算法融合显著图得到DSR显著灰度图。番茄DSR灰度图再经过OTSU算法进行分割和去噪处理,最终使用该文提出的改进随机Hough变换(randomized hough transform,RHT)圆检测方法识别番茄果簇中的单果。结果显示,该文方法对未成熟番茄果实的正确识别率能达到77.6%。同时,该文方法与人工测量的圆心和半径的相关系数也分别达到0.98和0.76,研究结果为估产机器人的多种果实自动化识别提供参考。展开更多
文摘At present, most lane line detection methods are aimed at simple road surface. There is still no good solution for the situation that the lane line contains arrow, text and other signs. The edge left by markers such as arrow and text will interfere with the detection of lane lines. In view of the situation of arrow mark and text mark interference between lane lines, the paper proposes a new processing algorithm. The algorithm consists of four parts, Gaussian blur, image graying processing, DLD-threshold (Dark-Light-Dark-threshold) algorithm, correlation filter edge extraction and Hough transform. Among them, the DLD-threshold algorithm and related filters are mainly used to remove the identification interference between lane lines. The test results on the Caltech Lanes dataset are given at the end of the article. The result of verification of this algorithm showed a max recognition rate of 97.2%.
