搜索资源列表
Gaussian-modeling-approach
- vc++和opencv,运用高斯建模的方法对场景进行背景建模，背景差分。从而检测出运动的物体，如机动车辆、行人，烟火等。-vc++ and opencv, using the method of Gaussian modeling scene background modeling, background difference. To detect moving objects, such as motor vehicles, pedestrians, fireworks, etc.
Depth_Chapter_11
- 深度图 获取场景中各点相对于摄象机的距离是计算机视觉系统的重要任务之一．场景中各点相对于摄象机的距离可以用深度图(Depth Map)来表示，即深度图中的每一个像素值表示场景中某一点与摄像机之间的距离-Scene depth map for each point the distance relative to the camera computer vision system is one of the important tasks. Scene points relative to the
DetectiveContour
- 视频场景切换及轮廓检测（VS2008+opencv）,采用VC编写，注意源代码里的视频名称是“sunyanzi.avi”,改成自己的视频名称即可-scene change detection and detective contours,write with vc,remember change the name of video in the code into yours
flightsim
- Uses blender to generate a scene with reference objects. Takes input images and uses opencv methods to estimate the object translation and rotation from the camera. Reads the object 3D coordinates from a file and uses color to detect the objects in t
VCPOpenCVPget-background
- 提取静态场景的背景，用于图像图像目标检测，使用OpenCV平台，请在在vc++环境下运行 -Extract the static scene background for the image image target detection using OpenCV platform, running in vc++ environment
testMatchTemplateCAM
- 通过调用OpenCV库，采用逐差法进行视频跟踪。在源码中输入要跟踪的图样，运行文件，程序可以识别跟踪摄像头摄取场景内与图样相关性最高的目标-By calling the OpenCV library, using a case-by-difference method for video tracking. Input source you want to track the pattern, run the file, the program can identify tracking cam
find_obj
- 在监控系统的某一场景下，检测是否有物体存在，并定位其位置。-The scene of a monitoring system to detect whether there are objects and locate its position.
gaosi
- 基于混合高斯背景建模的方法用于检测场景中的运动车辆，采用Visual C++和OpenCV实现，程序有详细注释，并且附带测试视频，希望对大家有帮助。-The movement of vehicles, based on Gaussian mixture background modeling method for detecting the scene to adopt the Visual C++ and OpenCV realization, procedures detailed note
3
- 输入： 自拍两幅同一个场景(或物体)的角度/远近有差别的图像 （对于学有余力的同学，建议多测试几张角度/远近差别较大的图像） 任务： 在每张图像中检测特征点位置并将匹配画出匹配得最好的10-20对特征点 输出要求（以下三个结果分别输出，不要重叠在一张图上）： 1. 在两张图上分别画出检测到的特征点位置 2. 对匹配得最好的10-20对特征点：每对特征点对用连接线画出 3. 用椭圆形式在图上画出上述每个特征点的描述子方向与尺度等信息 编程工具： Visual
vehicle-detection
- 基于帧间差分的方法用于检测场景中的运动车辆，采用Visual C++和OpenCV实现，程序有详细注释，并且附带测试视频，希望对大家有帮助。-The movement of vehicles based on frame difference method is used to detect scene using the Visual C++ and OpenCV realization procedures detailed notes, and come with a test video
TurnYourBook
- 实现挥手翻书的的源码，但是在部分场景下的反映不够灵敏，只供学习-Wave open book source, but a reflection in part of the scene is not sensitive enough for learning
KALMANPI-TRACKING
- 在视频场景中检测到行人的存在，并用红色矩形框对行人进行跟踪-In the presence of a pedestrian is detected in the video scene, and with a red rectangle pedestrian tracking
keyframe
- 视频关键帧提取。全阈值算法找到每个镜头的关键帧并保存-Video key frame extraction.Using threshold algorithm to find key frames in every scene and save them.
hand-label
- 道路场景识别，通过对样本图像处理和特征提取，再通过bp神经网络进行学习，最后通过学习后得到的权值进行样本识别。-Road scene recognition, through the sample image processing and feature extraction, and then through bp neural network learning, and finally by learning the weights obtained after the sample ide
Codebook_model
- Codebook model 视频抠像 xp sp3 + vs2005 + OpenCV 2.3.1-For a more detailed explanation of a “codebook” model refer to [reference: Gary Bradski and Adrian Kaehler: Learning Opencv, September 2008: First Edition. p. 278]. During the application of the
JustForFun
- 同一场景不同角度的多图融合代码，包括了特征检测、匹配、变换，本人写的代码，也借鉴了不少别人的知识，可以运行。-The same scene from different angles multi-image integration code, including feature detection, matching, transformation, I wrote the code, but also learn a lot of other ones knowledge, you can
opencv
- 图像场景分类的bow模型opencv源代码，采用k-means聚类构造单词，采用支持向量机的svm分类器。-Image scene classification bow model opencv source code, using k-means clustering structure of words, using support vector machine svm classifier.
opencv-Optical-
- LK稀疏光流Demo可以在场景中自动找出关键点并自动跟踪-LK Sparse Optical Flow Demo automatically identify the key points in the scene and automatically track
OpenCV_TEST
- 基于OPENCV的道路中心线的识别，对清晰的道路场景具有适应性.-Based on the identificationOPENCV road centerline based on a clear road scene adaptive.
Average-background-method
- 平均背景法是一种学习背景场景和分割前景目标的简单方法。这种方法只能用于背景场景中不包含运动部分。而且，这种方法还要求光线保持不变，比如室内静止场景。-Average background method is a simple way to split the background and foreground objects scene study. This method can only be used for background scene does not contain moving