- 博客(374)
- 资源 (92)
- 论坛 (1)
- 收藏
- 关注

原创 有开源代码的文献
目标检测开源代码汇总跟踪算法开源代码汇总人脸检测识别代码汇总人群分析、人群计数 开源代码文献及数据库语义分割+视频分割 开源代码文献集合网络优化加速开源代码汇总计算机视觉&深度学习相关资源汇总 https://joshua19881228.github.io/2016-08-25-my-jumble-of-computer-vision/https://git.
2016-11-21 16:52:55
6763
原创 Kullback-Leibler Divergence
http://alpopkes.com/files/kl_divergence.pdfKullback-Leibler 散度定义: Kullback-Leibler 散度用于度量两个分布的相似性(或差异)。对于两个离散概率分布 P 和 Q ,在一个点集合 X 上 Kullback-Leibler 散度定义如下:DKL(P∣∣Q)=∑x∈XP(x)log(P(x)Q(x)) D_{KL}(P||Q)=\sum_{x\in X}^{}P(x)log(\frac{P(x)}{Q(x)} ) DKL(
2021-01-08 15:01:53
23
转载 Bias Variance Tradeoff – Clearly Explained
Bias Variance Tradeoff is a design consideration when training the machine learning model. Certain algorithms inherently have a high bias and low variance and vice-versa. In this one, the concept of bias-variance tradeoff is clearly explained so you make a
2021-01-08 11:10:30
38
转载 What is Mahalanobis distance? 马氏距离
https://blogs.sas.com/content/iml/2012/02/15/what-is-mahalanobis-distance.htmlhttps://blogs.sas.com/content/iml/2012/02/08/.htmlA variance-covariance matrix expresses linear relationships between variables. Given the covariances between variables, did yo
2021-01-08 10:39:53
17
转载 梯度下降原理解析
1 原理在机器学习的核心内容就是把数据喂给一个人工设计的模型,然后让模型自动的“学习”,从而优化模型自身的各种参数,最终使得在某一组参数下该模型能够最佳的匹配该学习任务。那么这个“学习”的过程就是机器学习算法的关键。梯度下降法就是实现该“学习”过程的一种最常见的方式,尤其是在深度学习(神经网络)模型中,BP反向传播方法的核心就是对每层的权重参数不断使用梯度下降来进行优化。梯度下降法(gradient descent)是一种常用的一阶(first-order)优化方法,是求解无约束优化问题最简单、最经典的方法
2020-08-05 11:44:25
130
原创 加法神经网络--AdderNet: DoWe Really Need Multiplications in Deep Learning?
AdderNet: DoWe Really Need Multiplications in Deep Learning?CVPR2020https://arxiv.org/abs/1912.13200当前主流的CNN网络使用了大量的乘法运算来计算 输入特征层和卷积滤波器的相似性(cross-correlation),由于乘法运算耗时明显大于加法运算耗时,所有本文提出一个加法神经网络,使用 l1 范数来计算 输入特征层和卷积滤波器的相似性。这样在计算滤波器的输出响应时基本不用乘法运算。针对该加法神经网络
2020-06-11 15:15:59
398
原创 图像 主轴 相关知识
二值图像中物体几何主轴的提取方法https://www.docin.com/p-764752910.html主轴的定义:1)从投影的角度来说,沿着主轴方向做投影,物体所得到的宽度最小;2)从统计学的角度来说,主轴的方向就是该物体的主分量的方向,以该主分量为基础做线性变换可以去掉随机向量中各元素间的相关性;3)从纹理分析和频谱分析的角度来说,对规则的狭长型物体,主轴方向就是垂直于频谱图上能...
2019-10-29 15:19:50
638
转载 opencv 凹凸性检测 和 缺陷分析
版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。 ...
2019-10-29 15:17:39
1974
转载 c++ 类文件的动态库生成及调用例子
https://blog.csdn.net/josiechen/article/details/70174445 ...
2019-07-01 16:45:44
788
原创 多尺度目标检测--Scale-Aware Trident Networks for Object Detection
Scale-Aware Trident Networks for Object Detectionhttps://github.com/TuSimple/simpledet/tree/master/models/tridentnet本文将 Dilated convolution 用于多尺度目标检测,Dilated convolution 最先用于语义分割。多尺度目标检测的几个常见策略fe...
2019-06-21 11:48:20
515
原创 快速目标检测--YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computershttps://github.com/reu2018DL/YOLO-LITEhttps://github.com/Stinky-Tofu/Stronger-yoloYOLO-LITE runs at about 21 FPS on ...
2019-06-20 14:40:25
903
原创 快速目标检测--Object detection at 200 Frames Per Second
Object detection at 200 Frames Per Second本文在 Tiny Yolo 的基础上设计了一个目标检测网络,在 Nvidia 1080ti 上可以达到 100帧每秒。本文主要成果有三点:1)网络结构上的设计改进;2) Distillation loss for Training,使用 teacher network 辅助训练;3)Effectiveness...
2019-06-14 16:46:20
717
转载 一文弄懂神经网络中的反向传播法——BackPropagation
https://www.cnblogs.com/charlotte77/p/5629865.html 最近在看深度学习的东西,一开始看的吴恩达的UFLDL教程,有中文版就直接看了,后来发现有些地方总是不是很明确,又去看英文版,然后又找了些资料看,才发现,中文版的译者在翻译的时候会对省略的公式推导过程进行补充,但是补充的又是错的,难怪觉得有问题。反向传播法其实是神经网络的基础了,但是很多人在学的...
2019-06-12 11:43:14
1204
转载 卷积网络基础知识---Group Convolution分组卷积
Group Convolution分组卷积,以及Depthwise Convolution和Global Depthwise Convolutionhttps://www.cnblogs.com/shine-lee/p/10243114.html写在前面Group Convolution分组卷积,最早见于AlexNet——2012年Imagenet的冠军方法,Group Convolutio...
2019-06-04 09:38:20
4331
转载 卷积网络基础知识---Depthwise Convolution && Pointwise Convolution && Separable Convolution
https://yinguobing.com/separable-convolution/#fn2 卷积神经网络在图像处理中的地位已然毋庸置疑。卷积运算具备强大的特征提取能力、相比全连接又消耗更少的参数,应用在图像这样的二维结构数据中有着先天优势。然而受限于目前移动端设备硬件条件,显著降低神经网络的运算量依旧是网络结构优化的目标之一。本文所述的Separable Convolution就是降低...
2019-06-04 08:58:07
861
转载 机器学习--多标签softmax + cross-entropy交叉熵损失函数详解及反向传播中的梯度求导
https://blog.csdn.net/oBrightLamp/article/details/84069835正文在大多数教程中, softmax 和 cross-entropy 总是一起出现, 求梯度的时候也是一起考虑.softmax 和 cross-entropy 的梯度, 已经在上面的两篇文章中分别给出.1 题目考虑一个输入向量 x, 经 softmax 函数归一化处理后...
2019-06-03 16:48:10
1566
原创 目标检测---Segmentation Is All You Need
Segmentation Is All You Needhttps://www.jiqizhixin.com/articles/2019-06-02-2目前目标检测算法中有两个模块比较重要: region proposal networks (RPNs) 和 non-maximum suppression (NMS) ,虽然这两个模块解决目标检测中的一些问题,但是它们也引入了一些难以克服的问...
2019-06-03 13:29:09
1471
转载 脚崴了!又肿又疼怎么办?
罗大伦频道https://mp.weixin.qq.com/s?__biz=MzI1MjAyNDMwNw==&mid=2650718754&idx=1&sn=832f192593ae9ad9ca0e3d304997f093&chksm=f1e066bec697efa8ed439b987466ea73aa316d14ff90c92fbf04d33e23452bb30...
2019-05-31 08:37:29
423
1
转载 openGL 入门4 --- Following the data
Example 1.2. Buffer Object Initializationvoid InitializeVertexBuffer(){ glGenBuffers(1, &positionBufferObject); // 生成缓存对象,没有分配内存 glBindBuffer(GL_ARRAY_BUFFER, positionBufferObject); // 绑定对象 g...
2019-05-30 15:56:50
67
转载 OpenGL ---渲染流水线之世界矩阵,相机变换矩阵,透视投影变换矩阵
https://blog.csdn.net/qq_29523119/article/details/78577246OpenGL的渲染流水线:OpenGL的坐标系在3D图形学里,OpenGL为右手坐标系(准确来说,OpenGL的世界空间和相机空间是右手坐标系)。随便提一下,D3D11为左手坐标系。(1) 右手坐标系(2) 左手坐标系OpenGL的矩阵和向量结合方式...
2019-05-30 15:51:57
410
2
转载 OpenGL--- 坐标系变换
下面这篇文章详细讲述了OpenGL里的坐标转换,清晰,明了。但是其所谓的渲染管线只包括modelview 转换 和 投影变换,我觉得不是这样的。这只是从坐标角度吧。比如什么顶点着色、光栅化、送至帧缓存都没有涉及到。原文地址:http://blog.csdn.net/zhulin...
2019-05-30 15:39:37
295
转载 openGL--透视投影的原理和实现
https://blog.csdn.net/wong_judy/article/details/6283019#t2 透视投影的原理和实现by Goncely 摘 要 :透视投影是3D渲染的基本概念,也是3D程序设...
2019-05-30 14:21:54
1329
转载 OpenGL坐标系及坐标转换
https://blog.csdn.net/shimazhuge/article/details/25135009 OpenGL通过相机模拟、可以实现计算机图形学中最基本的三维变换,即几何变换(模型变换—视图变换(两者合称几何变换))、投影变换、裁剪变换、视口变换等,同时,OpenGL还实现了矩阵堆栈等。理解掌握了有关坐标变换的内容,就算真正走进了精彩地三维世界。...
2019-05-30 11:33:05
206
原创 openGL入门3 --- rasterization pipeline
Learning Modern 3D Graphics ProgrammingRasterization Overview这里简单介绍一下 rasterization 光栅化流程1)裁剪空间变换,归一化坐标系 transform the vertices of each triangle into normalized device coordinates2)窗口变换 from norm...
2019-05-29 08:52:54
404
转载 中医点滴 2 --- 保和丸 + 口气重
口气重的两大原因https://mp.weixin.qq.com/s?__biz=MzI1MjAyNDMwNw==&mid=2650718736&idx=1&sn=c9d90360b73a7d9d365688102ad8d14d&chksm=f1e0668cc697ef9af47b112d1adc90d43ee0bc779b34189d787a78f6069864...
2019-05-29 08:36:34
316
转载 中医点滴 1 --- 冬季外感喉咙痛 寒性荨麻疹
喉咙肿痛会有两种情况: 一是扁桃体发炎,肿痛实在两腮之下,我们能够摸到扁桃体的地方。这个地方肿,一般是细菌感染,一定要用解毒的药物,西药抗生素也可以。 另一种疼痛,是在喉咙附近,在喉咙上下,咽吐沫的时候会感觉明显,就在喉结那里疼痛。有细菌感染,更可能有病毒感染,可能病毒居多。丹栀射郁汤: 牡丹花瓣6克,栀子花9克,射干9克,郁金9克,琵琶页9克,生甘草3克,赤茯苓9克, 牡丹皮 生栀子代替 ...
2019-05-29 08:29:37
169
原创 openGL 入门 2--顶点数组对象 VAO 和 缓存对象 VBO
用户输入的数据 以 顶点数组对象表示 Vertex Array Object,VAOvoid glGenVertexArrays(GLsizei n, GLuint *arrays);返回 n个 顶点数组对象 的名称,这些名称存放与数组 arrays 中Returns n currently unused names for use as vertex-array objects in th...
2019-05-24 11:49:52
288
原创 OpenGL入门 (一)
什么是 openGL?OpenGL is an application programming interface—‘‘API’’ for short—which is merely a software library for accessing features in graphics hardwareOpenGL is designed as a streamlined, hardwar...
2019-05-24 11:49:35
1046
原创 二值网络训练--A Empirical Study of Binary Neural Networks' Optimisation
A Empirical Study of Binary Neural Networks’ OptimisationICLR2019https://github.com/mi-lad/studying-binary-neural-networksADAM for optimising the objective, (2) not using early stopping, (3) spli...
2019-05-22 09:36:18
465
转载 函数参数传递常用的三种方式
https://www.runoob.com/cprogramming/c-functions.html示例程序均以交换两个整数为例。值传递#include <stdio.h>void swap(int x, int y);void swap(int x, int y){ int temp; temp = x; x = y; y = t...
2019-05-21 13:30:28
768
原创 二值网络训练--Training Competitive Binary Neural Networks from Scratch
Training Competitive Binary Neural Networks from Scratchhttps://github.com/hpi-xnor/BMXNet-v2 MXNet framework本文主要讨论了从零开始训练二值网络的一些情况以及 ResNet 和 DenseNet 二值网络的一些情况这里采用符号函数进行二值化二值梯度如何求导反向传播Strai...
2019-05-20 14:18:20
409
转载 CNN 常用网络结构解析 && 1x1 卷积运算 示意图
AlexNet 网络结构:VGG :conv3x3、conv5x5、conv7x7、conv9x9和conv11x11,在224x224x3的RGB图上(设置pad=1,stride=4,output_channel=96)做卷积,卷积层的参数规模和得到的feature map的大小如下:卷积神经网络基本计算原理http://m.elecfans.com/article/691826....
2019-05-18 16:43:36
663
转载 opencv相机标定示例代码
https://blog.csdn.net/dcrmg/article/details/52939318#include "opencv2/core/core.hpp"#include "opencv2/imgproc/imgproc.hpp"#include "opencv2/calib3d/calib3d.hpp"#include "opencv2/highgui/highgui.hp...
2019-05-15 14:45:47
1866
原创 二值网络--Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Optimize Deep Convolutional Neural Network with Ternarized Weights and High AccuracyIEEE Winter Conference on Applications of Computer Vision (WACV) 2019https://github.com/elliothe/Ternarized_Neura...
2019-05-10 16:06:05
292
原创 二值网络--TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights
TBN: Convolutional Neural Network with Ternary Inputs and Binary WeightsECCV2018本文的思路就是: 对 weight 进行二值量化+ scaling factor α , 对于 网络层的输入 进行 ternary value {−1,0,1} without the scaling factor3 Ternar...
2019-05-10 11:32:47
290
原创 三值网络--Trained Ternary Quantization
Trained Ternary QuantizationICLR 2017https://github.com/TropComplique/trained-ternary-quantization pytorchhttps://github.com/buaabai/Ternary-Weights-Network pytorch传统的二值网络将权重 W 量化为 +1、-1; 三值网络 ...
2019-05-08 14:16:21
732
1
原创 二值网络--Training Binary Weight Networks via Semi-Binary Decomposition
Training Binary Weight Networks via Semi-Binary DecompositionECCV2018CNN模型的压缩或加速总体上分为三类: pruning-based methods, low-rank decomposition based methods, and quantization-based methods本文属于 low-rank dec...
2019-05-07 10:17:13
654
原创 二值网络--Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentationhttps://arxiv.org/abs/1811.10413Binary Ensemble Neural Network 的思路就是将 若干个独立的二值网络组合起来近似 实数值网络,本文提出的 Struct...
2019-05-06 10:40:33
756
原创 实时车道检测--A Novel Vision-Based Framework for Real-Time Lane Detection and Tracking
A Novel Vision-Based Framework for Real-Time Lane Detection and TrackingSAE Technical Paper 2019-01-0690, 2019本文提出将传统方法和 CNN结合起来实现实时车道检测基于传统算法的车道检测方法依赖于strict assumptions ,只能在有限的场景中可以正常工作,速度快基于CNN...
2019-05-05 10:41:24
742
2
原创 车道线检测--End-to-end Lane Detection through Differentiable Least-Squares Fitting
End-to-end Lane Detection through Differentiable Least-Squares Fittinghttps://github.com/wvangansbeke/LaneDetection_End2End本文使用 CNN网络来检测车道线,end-to-end 就是输入图像,输出拟合出的车道线参数,一步到位,不用后续处理什么的。传统的车道线检测是分步骤...
2019-04-30 15:51:15
1128
A Review of Computer Vision Techniques for the Analysis of Urban Traffic
2011-10-15
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
Accuracy of Laplacian Edge Detectors
2011-10-12
A discrete expression of Canny's criteria for step
2011-10-11
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
The Canny Edge Detector Revisited
2011-08-11
OpenCV 2 Computer Vision Application Programming Cookbook
2011-06-24
Intensity and Edge-Based Symmetry Detection Applied to Car-Following
2011-04-11
Accurate Robust Symmetry Estimation
2011-04-11
Learning based Symmetric Features Selection for Vehicle Detection
2011-04-11
Method of removing moving shadow based on texture
2011-04-01
Approach of vehicle segmentation based on texture character
2011-04-01
A Background Reconstruction Method Based on Double-background
2011-03-17
Statistical Change Detection by the Pool Adjacent Violators Algorithm
2011-03-17
Optimal multi-level thresholding using a two-stage Otsu optimization approach
2011-03-17
Environmentally Robust Motion Detection for Video Surveillance
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
Love, 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
Video Tracking -- Theory and Practice
2011-02-22
Computational Vision and Medical Image Processing Recent Trends
2011-02-22
Digital Image Processing for Medical Applications (Cambridge, 2009)
2011-02-22
Robust threshold estimation for images with unimodal histograms
2011-02-22
Application of Shape Analysis Techniques for the Classification of Vehicles
2011-02-22
Simple Low Level Features for Image Analysis
2011-02-22
Solving the process of hysteresis without determining the optimal thresholds
2011-02-22
On candidates selection for hysteresis thresholds in edge detection
2011-02-22
Robust fragments-based tracking with adaptive feature selection
2011-02-22
Corner Detection Algorithms for Digital Images in Last Three Decades
2011-02-22
A high performance edge detector based on fuzzy inference rules
2011-02-22
O天涯海阁O的留言板
发表于 2020-01-02 最后回复 2020-01-02
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人 TA的粉丝