Computer vision

来自开放百科 - 灰狐
(版本间的差异)
跳转到: 导航, 搜索
(厂商)
(链接)
 
(未显示1个用户的35个中间版本)
第13行: 第13行:
  
 
==理论==
 
==理论==
 +
[[deep learning|Deep Learning]] is the hottest topic in Computer Vision
 
*[http://mathworld.wolfram.com/Convolution.html Convolution]
 
*[http://mathworld.wolfram.com/Convolution.html Convolution]
 
*[[Convolutional neural network|卷积神经网络]]
 
*[[Convolutional neural network|卷积神经网络]]
第18行: 第19行:
  
 
==项目==
 
==项目==
 +
计算机视觉的开源深度学习:Torch vs Caffe
 +
 +
[[image:torch-vs-caffe.jpg]]
 +
[[文件:VIAME-logo.png|right|VIAME]]
 
[[文件:cvf.jpg|right]]
 
[[文件:cvf.jpg|right]]
 
*[[Torch]]
 
*[[Torch]]
 
*[[Caffe]]
 
*[[Caffe]]
 +
*[[TensorFlow]]
 
*[https://github.com/luispedro/mahotas Mahotas: Python Computer Vision Library]
 
*[https://github.com/luispedro/mahotas Mahotas: Python Computer Vision Library]
 
*[http://libccv.org/ ccv] - a modern computer vision library
 
*[http://libccv.org/ ccv] - a modern computer vision library
 
*[[OpenFace]]
 
*[[OpenFace]]
 
*[[OpenCV]], [http://docs.huihoo.com/opencv/3.0/da/d60/tutorial_face_main.html 人脸识别]
 
*[[OpenCV]], [http://docs.huihoo.com/opencv/3.0/da/d60/tutorial_face_main.html 人脸识别]
 +
*[https://github.com/BradLarson/GPUImage2 GPUImage 2]
 +
 +
==ImageNet==
 +
[[文件:imagenet-logo.jpg|right]]
 +
*[http://image-net.org ImageNet官网]
 +
*[http://vision.stanford.edu/ Stanford Vision Lab]
  
 
==文档==
 
==文档==
 +
*[http://docs.huihoo.com/infoq/qconbeijing/2016/day1/%E6%96%B0%E5%85%B4%E6%8A%80%E6%9C%AF%E5%8F%8A%E5%BA%94%E7%94%A8%E4%B8%93%E9%A2%98/5-4-%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E6%8A%80%E6%9C%AF%E5%9C%A8%E5%95%86%E4%B8%9A%E9%93%B6%E8%A1%8C%E7%9A%84%E5%BA%94%E7%94%A8%E5%8F%8A%E6%8C%91%E6%88%98-%E7%8E%8B%E6%99%B6.pdf 人脸识别技术在商业银行的应用及挑战]
 
*[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/Seeing-People-with-Deep-Learning.pdf Seeing People with Deep Learning]
 
*[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/Seeing-People-with-Deep-Learning.pdf Seeing People with Deep Learning]
 
*[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/Deep-Learning-Deep-Boltzmann-Machines.pdf Deep Learning: Deep Boltzmann Machines]
 
*[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/Deep-Learning-Deep-Boltzmann-Machines.pdf Deep Learning: Deep Boltzmann Machines]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5713-Collaborative-Feature-Learning-from-Social-Media.pdf Collaborative Feature Learning from Social Media]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5474-CloudCV-Large-Scale-Distributed-Computer-Vision-as-a-Cloud-Service.pdf CloudCV: Large-Scale Computer Vision on the Cloud]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5580-Application-of-GPUs-to-Classification-Problems-Using-Deep-Learning-Architectures.pdf Application of GPUs to Classification Problems Using Deep Learning Architectures]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5577-Building-State-of-Art-Face-Processing-Pipeline-with-GPU.pdf Understand Face with GPU and beyond]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5123-Through-the-Eyes-of-a-Car-Visualizing-a-Car-Camera-System.pdf Visualizing a Car's Camera System: Computer Vision for Automotive]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5457-Maximizing-Face-Detection-Performance-on-GPUs.pdf Maximizing Face Detection Performance]
 +
*[http://docs.huihoo.com/gputechconf/gtc2015/S5182-The-Future-of-Human-Vision-Preferential-Augmentation-Using-GPUs.pdf The Future of Human Vision: Preferential Augmentation Using GPUs]
  
 
==图书==
 
==图书==
第36行: 第56行:
 
==视频==
 
==视频==
 
*[https://www.youtube.com/watch?v=40riCqvRoMs 李飞飞: 我们怎么教计算机理解图片?赋予计算机视觉智能] ps: 在2007年发起了[http://www.image-net.org/ ImageNet(图片网络)]计划.
 
*[https://www.youtube.com/watch?v=40riCqvRoMs 李飞飞: 我们怎么教计算机理解图片?赋予计算机视觉智能] ps: 在2007年发起了[http://www.image-net.org/ ImageNet(图片网络)]计划.
 +
 +
==课程==
 +
*[http://vision.stanford.edu/teaching.html 斯坦福计算机视觉课程]
 +
*[http://www-inst.eecs.berkeley.edu/~cs280/sp15/index.html 伯克利 CS280: Computer Vision], [http://docs.huihoo.com/computer-vision/berkeley/cs280-computer-vision 幻灯片下载]
 +
 +
==研究组==
 +
*[https://torrvision.com/ Torr Vision Group]
 +
*[https://www.robots.ox.ac.uk/~vgg/ Visual Geometry Group]
  
 
==厂商==
 
==厂商==
*[https://www.azure.cn/projectoxford/vision 微软牛津计划 Computer Vision API]
+
*[https://www.azure.cn/projectoxford/vision 微软牛津计划 Computer Vision API][https://github.com/Microsoft/ProjectOxford-ClientSDK GitHub]
 
*[http://www.faceplusplus.com.cn/ Face++人脸识别]
 
*[http://www.faceplusplus.com.cn/ Face++人脸识别]
 
*[http://deepglint.com/ 格灵深瞳]: 三维计算机视觉 + 深度学习,车辆识别和安防产品
 
*[http://deepglint.com/ 格灵深瞳]: 三维计算机视觉 + 深度学习,车辆识别和安防产品
 
*[https://open.tuputech.com/ 图普科技]: 专注于图像识别和视觉检测
 
*[https://open.tuputech.com/ 图普科技]: 专注于图像识别和视觉检测
 +
*[http://sensetime.com/ 商汤科技]
 +
*[http://www.sensetime.com/cn SenseTime]
 +
*[http://www.hiscene.com HiScene]
 +
*[[vision.ai]]
 +
*[http://cloudsightapi.com/ CloudSight]
 +
*[http://cloudcv.org/ CloudCV]
 +
*[http://www.clarifai.com/ Clarifai]
 +
*[http://vision.alchemy.ai/ Alchemy Vision], [http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/alchemy-vision.html IBM AlchemyVision]
 +
*[https://www.imageidentify.com/ The Wolfram Language Image Identification Project]
 +
*[http://www.adaptive-vision.com Machine Vision Software and Libraries - Adaptive Vision]
 +
*[http://itseez.com/ Itseez - Computer Vision Consulting - Machine Learning]
  
 
==图集==
 
==图集==
 
<gallery>
 
<gallery>
 
image:computer-vision.png|Computer Vision
 
image:computer-vision.png|Computer Vision
 +
image:computer-vision-2.png|Compuer Vision
 +
image:computer-vision-application.png|典型应用
 
image:computer-vision-zh-cn.jpg|计算机视觉
 
image:computer-vision-zh-cn.jpg|计算机视觉
 +
image:computer-graphics-and-computer-vision.png|计算机图形和计算机视觉
 
image:image-processing-and-computer-vision-python-ecosystem.png|Python生态
 
image:image-processing-and-computer-vision-python-ecosystem.png|Python生态
 
image:openface.jpg|OpenFace
 
image:openface.jpg|OpenFace
 +
image:metamind-imagenet-accuracy.png|ImageNet精确度
 +
image:AVCaptureStillImageOutput-CIFaceDetector.png|人脸识别
 +
image:android-face-recognition-with-deep-learning-library.png|Android人脸识别深度学习库
 +
image:Accelerated-Vision-API-Landscape-Overview.png|视觉加速API
 
</gallery>
 
</gallery>
  
第58行: 第104行:
 
*[http://vision.stanford.edu/ Stanford Computer Vision Lab]
 
*[http://vision.stanford.edu/ Stanford Computer Vision Lab]
 
*[http://bvlc.eecs.berkeley.edu/ Berkeley Vision and Learning Center]
 
*[http://bvlc.eecs.berkeley.edu/ Berkeley Vision and Learning Center]
*[http://www.sensetime.com/cn SenseTime]
 
*[http://www.hiscene.com HiScene]
 
 
*[http://cs.stanford.edu/people/karpathy/ Andrej Karpathy]、[https://github.com/karpathy Andrej @ GitHub]
 
*[http://cs.stanford.edu/people/karpathy/ Andrej Karpathy]、[https://github.com/karpathy Andrej @ GitHub]
*[https://vision.ai/ vision.ai]
 
 
*[http://www.chinacloud.cn/show.aspx?id=21212&cid=17 2015深度学习回顾:ConvNet、Caffe、Torch及其他]
 
*[http://www.chinacloud.cn/show.aspx?id=21212&cid=17 2015深度学习回顾:ConvNet、Caffe、Torch及其他]
 +
*[https://www.zhihu.com/question/20672053 计算机视觉,计算机图形学和数字图像处理,三者之间的联系和区别是什么?]
 +
*[http://geek.csdn.net/news/detail/93514 基于计算机视觉的无人驾驶感知系统]
 +
*[https://zhuanlan.zhihu.com/p/37736910 FlowNet到FlowNet2.0:基于卷积神经网络的光流预测算法]
  
 
[[category:artificial intelligence]]
 
[[category:artificial intelligence]]
 
[[category:computer vision]]
 
[[category:computer vision]]
 
[[category:deep learning]]
 
[[category:deep learning]]
 +
[[category:computer science]]

2022年8月9日 (二) 10:08的最后版本

Wikipedia-35x35.png 您可以在Wikipedia上了解到此条目的英文信息 Computer vision Thanks, Wikipedia.

Computer vision 计算机视觉

计算机视觉是一门研究如何使机器“看”的科学,更进一步的说,就是指用摄影机和计算机代替人眼对目标进行识别、跟踪和测量等机器视觉,并进一步做图像处理,用计算机处理成为更适合人眼观察或传送给仪器检测的图像。

计算机视觉系统组成部分包括:

  • 过程控制(例如工业机器人和无人驾驶汽车)
  • 事件监测(例如图像监测)
  • 信息组织(例如图像数据库和图像序列的索引创建)
  • 物体与环境建模(例如工业检查,医学图像分析和拓扑建模)
  • 交感互动(例如人机互动的输入设备)

目录

[编辑] 理论

Deep Learning is the hottest topic in Computer Vision

[编辑] 项目

计算机视觉的开源深度学习:Torch vs Caffe

Torch-vs-caffe.jpg

VIAME
Cvf.jpg

[编辑] ImageNet

Imagenet-logo.jpg

[编辑] 文档

[编辑] 图书

[编辑] 视频

[编辑] 课程

[编辑] 研究组

[编辑] 厂商

[编辑] 图集

[编辑] 链接

分享您的观点
个人工具
名字空间

变换
操作
导航
工具箱