labelwatershed

这篇论文提出了一种较好的水下图像增强的方法。首先使用经过端到端训练的卷积神经网络去测量输入图片，同时以自适应双边滤波器对传输图片进行处理。接着提出一种基于白平衡的策略来消除图片的颜色偏差，用拉普拉斯金字塔融合获得无雾和色彩校正图像的融合结果。 最后，输出图像被转换为混合小波和方向滤波器组（HWD）域，用于去噪和边缘增强。 实验结果表明，该方法可以消除颜色失真，提高水下图像的清晰度。(This paper proposes a better underwater image enhancement method. Firstly, an end-to-end training convolutional neural network is used to measure the input image, and an adaptive bilateral filter is used to process the transmitted image. Then a strategy based on white balance is proposed to eliminate the color deviation of images. The fusion results of fog-free and color correction images are obtained by Laplacian pyramid fusion. Finally, the output image is converted into hybrid wavelet and directional filter bank (HWD) domain for denoising and edge enhancement. The experimental results show that the method can eliminate color distortion and improve the clarity of underwater images.)

5.在面板中画圆弧的程序，帮助你画出你想要的圆弧。(5 arc in the panel painting program to help you draw your desired arc.)

说明：  QT webview浏览器相关开发，简单webview应用开发(QT WebView browser related development, simple WebView application development)

稀疏表示实现图像融合。改变图像路径能直接应用(Sparse representation for image fusion)

行人目标检测 代码文件基于hog+svm检测技术。(people dectect and depending on hog+svm )

运动的小球、一般本科需要的课后作业设计。有兴趣的可以下载看看(The ball movement, the general undergraduate required homework designs. Interested parties can download and see)

说明：  采用生成对抗网络（GAN）实现图像去模糊，用于图像的清晰化处理(The generated countermeasure network (GAN) is used to remove the blur of the image, which is used to clear the image)

图象增强，内嵌8中方法供您参考比较， 图象增强，内嵌8中方法供您参考比较，(Image enhancement, embedded in 8 methods for your reference comparison, image enhancement, embedded in 8 methods for your reference comparison,)

这款小DEMO是关于自己学习LOD地形分层算法的例子，其中简单显示了实现算法的过程(The DEMO is a small study on their own examples of LOD terrain hierarchical algorithm, which simply shows the process of algorithm)

针对目前工业制造领域面临的难题,提出利用非量测数字摄像机进行工业钣金件高精度三维重建与视觉检测.采用二维直接线性变换分解摄像机参数初值并结合光束法平差进行高精度标定 利用最小二乘模板匹配提取像面上的点、直线信息并进行混合光束法平差,从而进行钣金件的高精度三维重建及其尺寸制造误差的检测.所开发的视觉检测系统硬件成本低、自动化程度较高,实际数据的多次实验均取得了优于1/8 000的相对精度,说明所论述的方法为工业零件的自动化三维检测提供了一条可行途径.(View of the current challenges facing the field of industrial manufacturing, made use of non-metric digital camera precision sheet metal parts for industrial reconstruction and visual inspection. Using two-dimensional direct linear transformation and the decomposition of initial parameters of the camera bundle adjustment with high accuracy calibration extracted by the least square template matching, like the surface of point, line information and mixed bundle adjustment to the three-dimensional reconstruction of high-precision sheet metal parts and the size of the detection of manufacturing errors. visual inspection system developed by the hardware low cost, high degree of automation, the actual data, many experiments have achieved better than 1/8000 of the relative accuracy, that the methods discussed in the automation of industrial components to provide a feasible three-dimensional detection approach.)