O天涯海阁O-CSDN博客

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

The sources of error for the edge finding technique proposed by Marr and Hildreth (D. Marr and T. Poggio, Proc. R. Soc. London Ser. B204, 1979, 301–328; D. Marr and E. Hildreth, Proc. R. Soc. London Ser. B.207, 1980, 187–217) are identified, and the magnitudes of the errors are estimated, based on idealized models of the most common error producing situations. Errors are shown to be small for linear illuminations, as well as for nonlinear illuminations with a second derivative less than a critical value. Nonlinear illuminations are shown to lead to spurious contours under some conditions, and some fast techniques for discarding such contours are suggested.

2011-10-12

The Canny Edge Detector Revisited

Canny (1986) suggested that an optimal edge detector should maximize both signal-to-noise ratio and localization, and he derived mathematical expressions for these criteria. Based on these criteria, he claimed that the optimal step edge detector was similar to a derivative of a gaussian. However, Canny’s work suffers from two problems. First, his derivation of localization criterion is incorrect. Here we provide a more acurate localization criterion and derive the optimal detector from it. Second, and more seriously, the Canny criteria yield an infinitely wide optimal edge detector. The width of the optimal detector can however be limited by considering the effect of the neighbouring edges in the image. If we do so, we find that the optimal step edge detector, according to the Canny criteria, is the derivative of an ISEF filter, proposed by Shen and Castan (1992). In addition, if we also consider detecting blurred (or non-sharp) gaussian edges of different widths, we find that the optimal blurred-edge detector is the above optimal step edge detector convolved with a gaussian. This implies that edge detection must be performed at multiple scales to cover all the blur widths in the image. We derive a simple scale selection procedure for edge detection, and demonstrate it in one and two dimensions.

2011-08-11

OpenCV 2 Computer Vision Application Programming Cookbook

Overview of OpenCV 2 Computer Vision Application Programming Cookbook Teaches you how to program computer vision applications in C++ using the different features of the OpenCV library Demonstrates the important structures and functions of OpenCV in detail with complete working examples Describes fundamental concepts in computer vision and image processing Gives you advice and tips to create more effective object-oriented computer vision programs Contains examples with source code and shows results obtained on real images with detailed explanations and the required screenshots

2011-06-24

Learning based Symmetric Features Selection for Vehicle Detection

Learning based Symmetric Features Selection for Vehicle Detection This paper describes a symmetric features selection strategy based on statistical learning method for detecting vehicles with a single moving camera for autonomous driving. Symmetry is a good class of feature for vehicle detection, but the areas with high symmetry and threshold for segmentation is hard to be decided. Usually, the additional supposition is added artificially, and this will decrease the robustness of algorithms. In this paper, we focus on the problem of symmetric features selection using learning method for autonomous driving environment. Global symmetry and local symmetry are defined and used to construct a cascaded structure with a one-class classifier followed by a two-class classifier.

2011-04-11

Intensity and Edge-Based Symmetry Detection Applied to Car-Following

Intensity and Edge-Based Symmetry Detection Applied to Car-Following We present two methods for detecting symmetry in images, one based directly on the intensity values and another one based on a discrete representation of local orientation. A symmetry finder has been developed which uses the intensity-based method to search an image for compact regions which display some degree of mirror symmetry due to intensity similarities across a straight axis. In a different approach, we look at symmetry as a bilateral relationship between local orientations. A symmetryenhancing edge detector is presented which indicates edges dependent on the orientations at two different image positions. SEED, as we call it, is a detector element implemented by a feedforward network that holds the symmetry conditions. We use SEED to find the contours of symmetric objects of which we know the axis of symmetry from the intensity-based symmetry finder. The methods presented have been applied to the problem of visually guided car-following. Real-time experiments with a system for automatic headway control on motorways have been successful.

2011-04-11

Accurate Robust Symmetry Estimation

Accurate Robust Symmetry Estimation Stephen Smith and Mark Jenkinson There are various applications, both in medical and non-medical image analysis, which require the automatic detection of the line (2D images) or plane (3D) of reflective symmetry of objects. There exist relatively simple methods of finding reflective symmetry when object images are complete (i.e., completely symmetric and perfectly segmented from image “background”). A much harder problem is finding the line or plane of symmetry when the object of interest contains asymmetries, and may not have well defined edges.

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

Most video surveillance systems require to manually set a motion detection sensitivity level to generate motion alarms. The performance of motion detection algorithms, embedded in closed circuit television (CCTV) camera and digital video recorder (DVR), usually depends upon the preselected motion sensitivity level, which is expected to work in all environmental conditions. Due to the preselected sensitivity level, false alarms and detection failures usually exist in video surveillance systems. The proposed motion detection model based upon variational energy provides a robust detection method at various illumination changes and noise levels of image sequences without tuning any parameter manually. We analyze the structure mathematically and demonstrate the effectiveness of the proposed model with numerous experiments in various environmental conditions. Due to the compact structure and efficiency of the proposed model, it could be implemented in a small embedded system.

2011-03-17

Optimal multi-level thresholding using a two-stage Otsu optimization approach

Otsu’s method of image segmentation selects an optimum threshold by maximizing the between-class variance in a gray image. However, this method becomes very time-consuming when extended to a multi-level threshold problem due to the fact that a large number of iterations are required for computing the cumulative probability and the mean of a class. To greatly improve the efficiency of Otsu’s method, a new fast algorithm called the TSMO method (Two-Stage Multithreshold Otsu method) is presented. The TSMO method outperforms Otsu’s method by greatly reducing the iterations required for computing the between-class variance in an image. The experimental results show that the computational time increases exponentially for the conventional Otsu method with an average ratio of about 76. For TSMO-32, the maximum computational time is only 0.463 s when the class number M increases from two to six with relative errors of less than 1% when compared to Otsu’s method. The ratio of computational time of Otsu’s method to TSMO-32 is rather high, up to 109,708, when six classes (M = 6) in an image are used. This result indicates that the proposed method is far more efficient with an accuracy equivalent to Otsu’s method. It also has the advantage of having a small variance in runtimes for different test images.

2011-03-17

A Background Reconstruction Method Based on Double-background

In this paper, we show a new method to reconstruct and update the background. This approach is based on double-background. We use the statistical information of the pixel intensity to construct a background that represents the status during a long time, and construct another background with feedback information in motion detection that represents the recent changes at a short time. This couple of background images is fused to construct and update the background image used to motion detection. The background reconstruction algorithm can perform well on the tests that we have applied it to.

2011-03-17

Statistical Change Detection by the Pool Adjacent Violators Algorithm

In this paper we present a statistical change detection approach aimed at being robust with respect to the main disturbance factors acting in real-world applications, such as illumination changes, camera gain and exposure variations, noise. We rely on modeling the effects of disturbance factors on images as locally order-preserving transformations of pixel intensities plus additive noise. This allows us to identify within the space of all the possible image change patterns the subspace corresponding to disturbance factors effects. Hence, scene changes can be detected by a-contrario testing the hypothesis that the measured pattern is due to disturbance factors, that is by computing a distance between the pattern and the subspace. By assuming additive gaussian noise, the distance can be computed within a maximum likelihood non-parametric isotonic regression framework. In particular, the projection of the pattern onto the subspace is computed by an O(N) iterative procedure known as Pool Adjacent Violators algorithm.

2011-03-17

Cooperative Fusion of Stereo and Motion

Cooperative Fusion of Stereo and Motion This paper presents a new matching algorithm based on cooperative fusion of stereo and motion cues. In this algorithm, stereo disparity and image flow values are recovered from two successive pairs of stereo images by solving the stereo and motion corresponde

2011-03-09

A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)

Love, A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749).djvu 第三部分（共三部分）

2011-02-27

A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)

Love, A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749).djvu 第二部分（共三部分）

2011-02-27

Love, A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749)

Love, A Treatise on Mathematical Theory of Elasticity (1944)(ISBN 0486601749) 第一部分（共三部分）

2011-02-27

Computation of Real-Time Optical Flow Based on Corner Features

This paper describes an approach to real-time optical flow computation that combines the corner features and pyramid Lucas-Kanade. Corners instead of all the points in the image are taken into optical flow computation, which could reduce the amount of calculation to a large extend. The experiment has shown that using this optical flow algorithm to track targets is effective and could meet the requirements of real-time applications.

2011-02-24

II-LK – A Real-Time Implementation for Sparse Optical Flow

In this paper we present an approach to speed up the computation of sparse optical flow fields by means of integral images and provide implementation details. Proposing a modification of the Lucas-Kanade energy functional allows us to use integral images and thus to speed up the method notably while affecting only slightly the quality of the computed optical flow. The approach is combined with an efficient scanline algorithm to reduce the computation of integral images to those areas where there are features to be tracked. The proposed method can speed up current surveillance algorithms used for scene description and crowd analysis.

2011-02-24

Medical Image Reconstruction A Conceptual Tutorial --pdf

Medical Image Reconstruction: A Conceptual Tutorial" introduces the classical and modern image reconstruction technologies, such as two-dimensional (2D) parallel-beam and fan-beam imaging, three-dimensional (3D) parallel ray, parallel plane, and cone-beam imaging. This book presents both analytical and iterative methods of these technologies and their applications in X-ray CT (computed tomography), SPECT (single photon emission computed tomography), PET (positron emission tomography), and MRI (magnetic resonance imaging). Contemporary research results in exact region-of-interest (ROI) reconstruction with truncated projections, Katsevich's cone-beam filtered backprojection algorithm, and reconstruction with highly undersampled data with l0-minimization are also included.

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

角点检测方法研究---根据实现方法不同可将角点检测方法分为两大类:基于边缘的角点检测方法与基于灰度变化的角点检测方法,并对现有的角点检测方法作了较为详细的分析与比较,指出角点检测技术的研究与发展方向.

2011-02-22

图像融合中角点检测技术研究

图像融合中角点检测技术研究--图像融合中角点检测技术研究

2011-02-22

Fast image region growing

Fast image region growing---Fast image region growing

2011-02-22

Simple Low Level Features for Image Analysis

2011-02-22

Direct methods for sparse matrices

second edition 2017, Oxford University Press

2024-04-07

百面机器学习.pdf

收录了超过100道机器学习算法工程师的面试题目和解答，本书将从特征工程、模型评估、降维等经典机器学习领域出发，构建一个算法工程师必-备的知识体系。其中大部分源于Hulu算法研究岗位的真实场景。

2019-06-01

CLIP-Q CVPR2018 code

CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization，CVPR2018 code

2018-10-30

Vehicle model recognition from frontal view image measurements

This paper deals with a novel vehicle manufacturer and model recognition scheme, which is enhanced by color recognition for more robust results. A probabilistic neural network is assessed as a classiﬁer and it is demonstrated that relatively simple image processing measurements can be used to obtain high performance vehicle authentication. The proposed system is assisted by a previously developed license plate recognition, a symmetry axis detector and an image phase congruency calculation modules. The reported results indicate a high recognition rate and a fast processing time, making the system suitable for real-time applications.

2011-10-15

Vehicle Detection and Tracking in Car Video Based on Motion Model

Vehicle Detection and Tracking in Car Video Based on Motion Model--This work aims at real-time in-car video analysis to detect and track vehicles ahead for safety, auto-driving, and target tracing. This paper describes a comprehensive approach to localize target vehicles in video under various environmental conditions. The extracted geometry features from the video are projected onto a 1D profile continuously and are tracked constantly. We rely on temporal information of features and their motion behaviors for vehicle identification, which compensates for the complexity in recognizing vehicle shapes, colors, and types. We model the motion in the field of view probabilistically according to the scene characteristic and vehicle motion model. The Hidden Markov Model is used for separating target vehicles from background, and tracking them probabilistically. We have investigated videos of day and night on different types of roads, showing that our approach is robust and effective in dealing with changes in environment and illumination, and that real time processing becomes possible for vehicle borne cameras.

2011-10-15

Projection and Least Square Fitting

Projection and Least Square Fitting with Perpendicular Offsets based Vehicle License Plate Tilt Correction

2011-10-15

An Algorithm for License Plate Recognition Applied to ITS

An algorithm for license plate recognition (LPR) applied to the intelligent transportation system is proposed on the basis of a novel shadow removal technique and character recognition algorithms. This paper has two major contributions. One contribution is a new binary method, i.e., the shadow re- moval method, which is based on the improved Bernsen algorithm combined with the Gaussian ﬁlter. Our second contribution is a character recognition algorithm known as support vector machine (SVM) integration. In SVM integration, character features are extracted from the elastic mesh, and the entire address character string is taken as the object of study, as opposed to a single character. This paper also presents improved techniques for im- age tilt correction and image gray enhancement. Our algorithm is robust to the variance of illumination, view angle, position, size, and color of the license plates when working in a complex environment. The algorithm was tested with 9026 images, such as natural-scene vehicle images using different backgrounds and ambient illumination particularly for low-resolution images. The license plates were properly located and segmented as 97.16%and 98.34%, respectively. The optical character recognition system is the SVM integration with different character features, whose performance for numerals, Kana, and address recognition reached 99.5%, 98.6%, and 97.8%, respectively. Combining the preceding tests, the overall performance of success for the license plate achieves 93.54% when the system is used for LPR in various complex conditions

2011-10-15

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

Automatic video analysis from urban surveillance cameras is a fast-emerging ﬁeld based on computer vision techniques. We present here a comprehensive review of the state-of-the-art computer vision for trafﬁc video with a critical analysis and an outlook to future research directions. This ﬁeld is of increasing relevance for intelligent transport systems (ITSs). The decreasing hardware cost and, therefore, the increasing de- ployment of cameras have opened a wide application ﬁeld for video analytics. Several monitoring objectives such as congestion, trafﬁc rule violation, and vehicle interaction can be targeted using cameras that were typically originally installed for human oper- ators. Systems for the detection and classiﬁcation of vehicles on highways have successfully been using classical visual surveillance techniques such as background estimation and motion tracking for some time. The urban domain is more challenging with respect to trafﬁc density, lower camera angles that lead to a high degree of occlusion, and the variety of road users. Methods from object categorization and 3-D modeling have inspired more advanced techniques to tackle these challenges. There is no commonly used data set or benchmark challenge, which makes the direct com- parison of the proposed algorithms difﬁcult. In addition, evalu- ation under challenging weather conditions (e.g., rain, fog, and darkness) would be desirable but is rarely performed. Future work should be directed toward robust combined detectors and classiﬁers for all road users, with a focus on realistic conditions during evaluation.

2011-10-15

On Improving the Efficiency of Tensor Voting

This paper proposes two alternative formulations to reduce the high computational complexity of tensor voting, a robust perceptual grouping technique used to extract salient information from noisy data. The first scheme consists of numerical approximations of the votes, which have been derived from an in-depth analysis of the plate and ball voting processes. The second scheme simplifies the formulation while keeping the same perceptual meaning of the original tensor voting: The stick tensor voting and the stick component of the plate tensor voting must reinforce surfaceness, the plate components of both the plate and ball tensor voting must boost curveness, whereas junctionness must be strengthened by the ball component of the ball tensor voting. Two new parameters have been proposed for the second formulation in order to control the potentially conflictive influence of the stick component of the plate vote and the ball component of the ball vote. Results show that the proposed formulations can be used in applications where efficiency is an issue since they have a complexity of order O(1). Moreover, the second proposed formulation has been shown to be more appropriate than the original tensor voting for estimating saliencies by appropriately setting the two new parameters.

2011-10-11

Selecting Critical Patterns Based on Local Geometrical

Pattern selection methods have been traditionally developed with a dependency on a specific classifier. In contrast, this paper presents a method that selects critical patterns deemed to carry essential information applicable to train those types of classifiers which require spatial information of the training data set. Critical patterns include those edge patterns that define the boundary and those border patterns that separate classes. The proposed method selects patterns from a new perspective, primarily based on their location in input space. It determines class edge patterns with the assistance of the approximated tangent hyperplane of a class surface. It also identifies border patterns between classes using local probability. The proposed method is evaluated on benchmark problems using popular classifiers, including multilayer perceptrons, radial basis functions, support vector machines, and nearest neighbors. The proposed approach is also compared with four state-of-the-art approaches and it is shown to provide similar but more consistent accuracy from a reduced data set. Experimental results demonstrate that it selects patterns sufficient to represent class boundary and to preserve the decision surface.

2011-10-11

Fast LOG Filtering Using Recursive Filters

Marr and Hildreth's theory of LoG filtering with multiple scales has been extensively elaborated. One problem with LoG filtering is that it is very time-consuming, especially with a large size of filters. This paper presents a recursive convolution scheme for LoG filtering and a fast algorithm to extract zero-crossings. It has a constant computational complexity per pixel and is independent of the size of the filter. A line buffer is used to determine the locations of zero-crossings along with filtering hence avoiding the need for an additional convolution and extra memory units. Various images have been tested

2011-10-11

A discrete expression of Canny's criteria for step

Optimal filters for edge detection are usually developed in the continuous domain and then transposed by sampling to the discrete domain. Simpler filters are directly defined in the discrete domain. We define criteria to compare filter performances in the discrete domain. Canny has defined (1983, 1986) three criteria to derive the equation of an optimal filter for step edge detection: good detection, good localization, and low-responses multiplicity. These criteria seem to be good candidates for filter comparison. Unfortunately, they have been developed in the continuous domain, and their analytical expressions cannot be used in the discrete domain. We establish three criteria with the same meaning as Canny's.

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