- 博客(388)
- 资源 (91)
- 收藏
- 关注
原创 快速人体姿态估计--Pose Proposal Networks
Pose Proposal Networks ECCV2018本文使用 YOLO + bottom-up greedy parsing 进行人体姿态估计its total runtime using a GeForce GTX1080Ti card reaches up to 5.6 ms (180 FPS)人体姿态估计总的来说有两大类方法: top-down and bott...
2018-09-11 11:00:13 5311 3
原创 图像去噪--Noise2Noise: Learning Image Restoration without Clean Data
Noise2Noise: Learning Image Restoration without Clean Data ICML 20181 Introduction 基于 corrupted or incomplete measurements 进行信号重构是一个很重要的课题。今年随着深度学习快速发展,自然也将CNN网络引入来解决图像去噪问题。 training a regression ...
2018-08-28 16:39:01 5011 4
原创 快速人脸验证--MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices
MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices在手机等移动设备上如何进行人脸验证了?本文提出了一个快速准确的网络 MobileFaceNets本文首先分析了一下以前的快速网络为什么在做Face Verification 性能很低下 MobileNetV1...
2018-08-08 10:18:30 7032 1
原创 犯罪分子检测--Eye in the Sky: Real-time Drone Surveillance System for Violent Individuals
Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network CVPRW 2018本文主要讨论了基于无人机的实时犯罪分子检测采用无人机一个优势就是无人机可以飞到你需要...
2018-08-07 15:06:20 2216 6
转载 Linux下批量重命名文件名为数字索引编号(0~N.xxx)的方法
转载自: https://blog.csdn.net/hubai789/article/details/49926019在处理一些数据集的时候,我们经常会碰到数据集的文件名是按时间戳(time stamp),或者其他方式命名的文件,而我们在编写程序时,往往希望读入的这些数据集的文件名是一种更简洁的形式,比如按照索引(index)方式:1.png,2.png,3.png…,那么如何批量重命...
2018-06-04 16:27:25 13557 2
转载 Nvidia TX2 安装中文输入法
https://blog.csdn.net/jiangchao3392/article/details/73650710硬件平台: NVIDIA Jetson TX2系统平台: Ubuntu16.04 LTS搜狗输入法:1,搜狗官网下载搜狗输入法http://pinyin.sogou.com/linux/2,安装,鼠标右键安装。3,重启,就行了 (这里应该需要做些设置...
2018-05-18 14:43:15 9507 2
原创 海康威视的工业相机的使用经历
单位(和海康是属于一个集团的)某一部门 选择用 NVIDIA® JETSON™ TX2 + 海康威视工业相机 的组合来完成 某检测识别任务,在相机选型前用邮件咨询 海康威视工业相机对 TX2 是否支持,得到海康相关人员的肯定答复。 于是采购了海康威视的工业相机回来。 厂家将 相机的 相关驱动和SDK相关资料发过来。 在开发过程中遇到以下问题: 1) 在基于x86-64 的 Ubunt...
2018-05-03 10:22:13 37482 21
原创 人群密度估计--DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation CVPR2018本文针对人群密度问题 将 检测方法和回归方法结合到一起,以此来提升人群密度估计精度人群密度估计问题目前主要的方法有基于检测的和基于回归的方法。我们发现这两种方法各有所长。在...
2018-04-10 16:43:49 5181 2
原创 人群密度估计--CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes CVPR2018针对复杂场景的拥挤场景理解我们提出了一个 CSRNet 网络,该网络主要包括两个部分,前端使用一个 卷积网络用于 2D 特征提取,后端用一个 dilated CNN。 该网络在几个常用的公开人...
2018-04-09 11:15:05 11396 2
原创 人群密度估计--Structured Inhomogeneous Density Map Learning for Crowd Counting
Structured Inhomogeneous Density Map Learning for Crowd Counting https://arxiv.org/abs/1801.06642针对人群密度估计问题,本文分析了当前基于密度估计问题算法存在的问题, inhomogeneous density distribution problem,随后提出解决这个问题的方法,将密度图由2D ...
2018-03-19 14:35:53 3817
原创 人群密度估计--Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank CVPR2018 https://github.com/xialeiliu/CrowdCountingCVPR18本文针对人群密度估计训练数据库规模很小的问题 提出了使用未标定数据来 self-supervised,具体通过 Learning to Rank...
2018-03-19 11:20:21 3878 1
原创 CNN 图像增强--DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks ICCV2017 http://people.ee.ethz.ch/~ihnatova/ https://github.com/aiff22/DPED本文使用CNN网络对手机拍摄的图像进行图像增强。 训练数据的问题怎么解决了? 这里我们使用...
2018-03-14 14:24:28 13936 9
原创 人体姿态估计--Learning Feature Pyramids for Human Pose Estimation
Learning Feature Pyramids for Human Pose Estimation ICCV2017 Torch: https://github.com/bearpaw/PyraNet本文主要关注人体部件中的尺度问题, scale variations of human body parts, 这种尺度变化主要发生在 camera view changes or s...
2018-03-12 16:01:24 3289 1
原创 人体姿态跟踪--Pose Flow: Efficient Online Pose Tracking
Pose Flow: Efficient Online Pose Tracking https://github.com/MVIG-SJTU/AlphaPose本文主要是关于人体姿态跟踪方面的内容。在对视频每一帧人体姿态估计完成之后,通过分析前后若干帧之间的人体姿态关系来完成人体姿态跟踪问题。主要通过两个步骤来实现的:1) pose flow 姿态流的生成,2)姿态流中进行了非极大值抑制...
2018-03-12 11:37:27 12212
原创 人体姿态估计--RMPE: Regional Multi-Person Pose Estimation
RMPE: Regional Multi-Person Pose Estimation ICCV2017 Code is based Caffe and Torch! https://github.com/MVIG-SJTU/RMPE https://github.com/MVIG-SJTU/AlphaPose多人人体姿态估计本文解决思路: 多人检测+单人人体姿态估计 Faster-R...
2018-03-08 14:37:00 3849
原创 人体姿态估计--Stacked Hourglass Networks for Human Pose Estimation
Stacked Hourglass Networks for Human Pose Estimation ECCV2016 http://www-personal.umich.edu/~alnewell/pose/ Torch code is available本文使用CNN网络来进行人体姿态估计,使用 Stacked Hourglass Networks,这里的 Hourglass ...
2018-03-07 11:20:21 7341
原创 vim 编辑器安装 使用
sudo apt-get install vimubuntu 16.04 开机开启数字小键盘解决方法sudo apt-get install numlockxsudo vim /etc/rc.local:修改文件内容,在exit 0前增加以下内容并保存if [-x /usr/bin/numlockx ]; then numlockx on fivim怎么插入内容呢?...
2018-03-01 15:31:45 1893
原创 Ubuntu16.0.4+1080ti+ cuda9.1+cudnn7.0.5 安装 及 caffe 测试
主要还是要参考官方文档 cuda 安装有两种方法,这里参考 blog.csdn.net/guojunxiu/article/details/78848503 使用 Package Manager Installation的方法目前网上大部分教程都是Runfile Installation安装的,然而这中方法很繁琐,需要关X Server,禁用nouveau等等,还会出现无法开机、无限循环...
2018-02-28 16:51:51 4344
原创 人脸对齐--One Millisecond Face Alignment with an Ensemble of Regression Trees
One Millisecond Face Alignment with an Ensemble of Regression Trees CVPR2014 http://www.csc.kth.se/~vahidk/face_ert.html https://github.com/suzuichi/OneMillisecondFaceAlignment本文也是使用级联回归器来做人脸特征对齐
2018-01-08 15:42:48 10013
原创 人脸对齐--Face Alignment at 3000 FPS via Regressing Local Binary Features
Face Alignment at 3000 FPS via Regressing Local Binary Features CVPR2014 https://github.com/yulequan/face-alignment-in-3000fps https://github.com/luoyetx/face-alignment-at-3000fps https://github.co
2018-01-03 15:58:16 3748
原创 人脸对齐--Robust face landmark estimation under occlusion
Robust face landmark estimation under occlusion ICCV’13 http://www.vision.caltech.edu/xpburgos/ICCV13/本文主要考虑人脸对齐中的遮挡问题,我们对遮挡进行显示的建模分析,detecting occlusions explicitly,并建立了一个人脸特征点遮挡的数据库 Caltech Occlud
2018-01-03 10:40:08 3341
原创 人脸对齐--Face Alignment by Explicit Shape Regression
Face Alignment by Explicit Shape Regression CVPR2012 https://github.com/soundsilence/FaceAlignment本文的三个亮点: a two-level boosted regression, effective shape-indexed features, and a fast correlation-bas
2018-01-02 10:16:39 3093
原创 人脸对齐--Boosted Regression Active Shape Models
Boosted Regression Active Shape Models British Machine Vision Conference 20071 Introduction 这里我们描述一种方法:对一类物体进行建模,然后用该模型对新图像中同一类新物体进行模型拟合。本文讨论的物体就是人脸,当前这个方法可以用于任意类的物体,主要该类不同物体之间存在对应的特征,例如大部分医学图像和人造物体。
2017-12-29 11:16:58 1996
原创 车辆检测--A Closer Look at Faster R-CNN for Vehicle Detection
A Closer Look at Faster R-CNN for Vehicle Detection Intelligent Vehicles Symposium , 2016 :124-129本文主要分析了 Faster R-CNN 对于车辆检测这个问题的性能表现,尝试了各种训练尺寸和测试图像尺寸Examples from the KITTI car dataset The network
2017-12-28 09:28:01 3812 1
原创 高速跟踪--High-Speed Tracking-by-Detection Without Using Image Information
高速跟踪: 当检测精度较高,视频帧率较高时,跟踪问题就会变得很简单,主要是多阈值目标检测和 判断前后帧的重合率 High-Speed Tracking-by-Detection Without Using Image Information Advanced Video and Signal Based Surveillance (AVSS), 2017 14th IEEE Internat
2017-12-27 13:47:44 24141 5
原创 CNN网络优化加速开源代码汇总
网络裁剪加速 Learning Efficient Convolutional Networks through Network Slimming ICCV2017 https://github.com/liuzhuang13/slimmingCNN网络通道裁剪加速 Channel Pruning for Accelerating Very Deep Neural Networks ICC
2017-12-26 14:32:21 4304 1
原创 目标检测开源代码汇总 object detection algorithm codes
目标检测 Faster RCNN + SSD Single-Shot Refinement Neural Network for Object Detection https://github.com/sfzhang15/RefineDet目标检测 A Unified Multi-scale Deep Convolutional Neural Network for Fast Objec
2017-12-26 14:31:00 14721 2
原创 小目标检测--A closer look: Small object detection in Faster R-CNN
A closer look: Small object detection in Faster R-CNN Improving Small Object Proposals for Company Logo Detection这里主要分析 Faster R-CNN 对小目标检测的性能分析及改进。 主要是 多尺度 RPN 和多尺度分类网络 数据中目标尺寸分布 3.1 Region Proposa
2017-12-26 11:20:03 5869
原创 目标检测--A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection ECCV2016 https://github.com/zhaoweicai/mscnn本文首先指出 Faster RCNN 在小目标检测存在的问题,分析其原因。随后提出本文的解决思路:1)在不同尺度特征图上进行候选区域提取,2)放
2017-12-25 15:01:45 2868
原创 3000类目标检测--R-FCN-3000 at 30fps: Decoupling Detection and Classification
R-FCN-3000 at 30fps: Decoupling Detection and Classification Code will be made available本文主要解决的问题是怎么实时检测3000类物体。主要思路就是将 object检测和物体分类 分离 我们提出的 R-FCN-3000 比 YOLO9000 高 18%,速度每秒 30帧。 对于几十类的物体实时检测已经发
2017-12-22 16:13:25 3026
原创 目标检测--Single-Shot Refinement Neural Network for Object Detection
Single-Shot Refinement Neural Network for Object Detection https://github.com/sfzhang15/RefineDet针对目标检测,本文可以看作将 Faster RCNN 和 SSD 融合起来。1 Introduction 当前基于 CNN 网络的目标检测可以分为两大类:1) the two-stage approach
2017-12-22 09:43:13 8099 2
原创 语义分割--Global Deconvolutional Networks for Semantic Segmentation
语义分割 Global Deconvolutional Networks for Semantic Segmentation BMVC 2016 https://github.com/DrSleep/GDN基于CNN的语义分割在近两年得到飞速的发展,但是这种 pixel-wise labelling with CNNs has its own unique challenges: 特征图
2017-12-21 14:08:46 1311
原创 快速多尺度人脸检测2--Multi-Scale Fully Convolutional Network for Face Detection in the Wild
Multi-Scale Fully Convolutional Network for Face Detection in the Wild CVPRW2017上一篇文献的姊妹篇吧,如何能够快速的实现多尺度人脸检测了? 本文将用于检测的特征图上采样和降采样得到多尺度特征图,在这个多尺度特征图上分别训练若干 FCN 人脸检测器 ,每个FCN 人脸检测器 负责检测相应尺寸的人脸本文最小检测人脸尺寸 1
2017-12-21 11:19:43 1374
原创 快速多尺度人脸检测--Multi-Scale Fully Convolutional Network for Fast Face Detection
Multi-Scale Fully Convolutional Network for Fast Face Detection BMVC 2016如何能够快速的实现多尺度人脸检测了?本文的思路是 将 多尺度模型往后移,这样前面的卷积层都能够共享, can run about 100 FPS on a GPU for VGA images 网络结构图如下所示: 我们的训练图像如下图所示,人
2017-12-19 16:20:29 2356 1
原创 目标检测中的尺度--An Analysis of Scale Invariance in Object Detection – SNIP
An Analysis of Scale Invariance in Object Detection – SNIP Code will be made available at http://bit.ly/2yXVg4c小伙伴们,知道 Larry S. Davis 是谁吗?本文主要对目标检测中的尺度问题进行深入分析,如何实现多尺度目标检测,尤其是小目标检测。 结论:1)combining t
2017-12-19 08:48:49 10196 3
原创 人群密度估计--Crowd Counting Via Scale-adaptive Convolutional Nerual Network
Crowd Counting Via Scale-adaptive Convolutional Nerual Network https://arxiv.org/abs/1711.04433v2 Code: https://github.com/miao0913/SaCNN-CrowdCounting-Tencent_Youtu为了解决人群密度估计中的 scale and perspecti
2017-12-15 15:06:22 6550
原创 人群密度估计--Learning a perspective-embedded deconvolution network for crowd counting
Learning a perspective-embedded deconvolution network for crowd counting 没有找到代码本文在人群密度估计这个问题上的创新点: fuse the perspective into a deconvolution network首先看看 Perspective Perspective is an inherent prope
2017-12-13 16:35:20 1107
原创 Boosting 简介--A (small) introduction to Boosting
A (small) introduction to Boosting https://codesachin.wordpress.com/tag/adaboost/这里翻译了一下这篇博客,对 boosting 介绍的很好What is Boosting? 什么是 Boosting Boosting is a machine learning meta-algorithm that aims to
2017-12-12 16:54:56 802
原创 语义分割--Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
Mix-and-Match Tuning for Self-Supervised Semantic Segmentation AAAI Conference on Artificial Intelligence (AAAI) 2018 http://mmlab.ie.cuhk.edu.hk/projects/M&M/ https://github.com/XiaohangZhan/mix-an
2017-12-12 16:05:02 2185
原创 Decision stump、Bootstraping、bagging、boosting、Random Forest、Gradient Boosting
1)首先来看看 Decision stump https://en.wikipedia.org/wiki/Decision_stump A decision stump is a machine learning model consisting of a one-level decision tree.[1] That is, it is a decision tree with one in
2017-12-11 16:37:46 717
Accuracy of Laplacian Edge Detectors
2011-10-12
The Canny Edge Detector Revisited
2011-08-11
OpenCV 2 Computer Vision Application Programming Cookbook
2011-06-24
Learning based Symmetric Features Selection for Vehicle Detection
2011-04-11
Intensity and Edge-Based Symmetry Detection Applied to Car-Following
2011-04-11
Accurate Robust Symmetry Estimation
2011-04-11
Approach of vehicle segmentation based on texture character
2011-04-01
Method of removing moving shadow based on texture
2011-04-01
Environmentally Robust Motion Detection for Video Surveillance
2011-03-17
Optimal multi-level thresholding using a two-stage Otsu optimization approach
2011-03-17
A Background Reconstruction Method Based on Double-background
2011-03-17
Statistical Change Detection by the Pool Adjacent Violators Algorithm
2011-03-17
Cooperative Fusion of Stereo and Motion
2011-03-09
A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)
2011-02-27
A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)
2011-02-27
Love, A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)
2011-02-27
Computation of Real-Time Optical Flow Based on Corner Features
2011-02-24
II-LK – A Real-Time Implementation for Sparse Optical Flow
2011-02-24
Medical Image Reconstruction A Conceptual Tutorial --pdf
2011-02-24
Extraction and recognition of license plates of motorcycles and vehicles on highways
2011-02-22
High Performance Implementation of License Plate Recognition in Image Sequences
2011-02-22
Vs-star-- A visual interpretation system for visual surveillance
2011-02-22
Robust fragments-based tracking with adaptive feature selection
2011-02-22
Robust and automated unimodal histogram thresholding and potential applications
2011-02-22
角点检测方法研究-- 毛雁明, 兰美辉
2011-02-22
Simple Low Level Features for Image Analysis
2011-02-22
百面机器学习.pdf
2019-06-01
CLIP-Q CVPR2018 code
2018-10-30
Vehicle model recognition from frontal view image measurements
2011-10-15
Vehicle Detection and Tracking in Car Video Based on Motion Model
2011-10-15
Projection and Least Square Fitting
2011-10-15
An Algorithm for License Plate Recognition Applied to ITS
2011-10-15
A Review of Computer Vision Techniques for the Analysis of Urban Traffic
2011-10-15
On Improving the Efficiency of Tensor Voting
2011-10-11
Selecting Critical Patterns Based on Local Geometrical
2011-10-11
Fast LOG Filtering Using Recursive Filters
2011-10-11
A discrete expression of Canny's criteria for step
2011-10-11
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人