- 博客(388)
- 资源 (91)
- 收藏
- 关注
原创 ubuntu16.0.4 opencv4.0.0 GPU 版本的 SURF
opencv4.0.0 自带的 samples GPU surf_keypoint_matcher.cppsurf_keypoint_matcher.cpp#include <iostream>#include "opencv2/opencv_modules.hpp"#ifdef HAVE_OPENCV_XFEATURES2D#include "opencv2/c...
2018-12-21 15:06:52 1397
原创 ubuntu16.0.4 opencv4.0.0 yolov3测试
https://github.com/spmallick/learnopencv/tree/master/ObjectDetection-YOLO硬件信息8 Intel® Core™ i7-4790 CPU @ 3.60GHz每张图像检测时间约 280msopencv 中的GPU 目前只支持 intel GPUyolov3.cpp// This code is written at...
2018-12-21 14:22:02 1066
原创 ubuntu 16.0.4 opencv 4.0.0 + opencv_contrib 4.0.0 cmake-gui 安装
下载和添加依赖包1、首先更新 apt-get,在安装前最好先更新一下系统,不然有可能会安装失败。在终端输入:sudo apt-get updatesudo apt-get upgrade2、接着安装官方给的opencv依赖包,在终端输入:sudo apt-get install build-essentialsudo apt-get install cmake git libgtk2...
2018-12-21 10:28:02 5251 1
转载 ubuntu 16.0.4 opencv 3.4.1 + opencv_contrib 3.4.1 cmake-gui 安装
下载安装包:opencv 3.4.3 Source code(zip)https://github.com/opencv/opencv/releasesopencv_contrib 3.4.3https://github.com/opencv/opencv_contrib/releases 3.4.3.zip解压 两个压缩包,然后将 opencv_contrib 放到 ope...
2018-12-17 16:22:29 1432
转载 Ubuntu创建opencv工程并显示一张图片
https://blog.csdn.net/qq_30155503/article/details/79434863 基于上篇已安装好opencv库,现在开始创建第一个opencv工程,并编写显示图片的代码。一、创建工程目录,并进入目录&amp;amp;nbsp; &amp;amp;nbsp; $ mkdir example&amp;amp;nbsp; &
2018-12-13 14:40:48 683
转载 ubuntu16.04 opencv多版本管理与切换
https://blog.csdn.net/u012986684/article/details/77490824大家好,今天说说,OpenCV的多版本切换问题!其实总的来说很简单,说下方法!1 首先当然准备两个不同版本opencv (比如2.4.9和3.1.0)2 cmake-gui 设置 CMAKE_INSTALL_PREFIX2.4.9 安装路径:/usr/local/opencv...
2018-12-10 15:39:33 2190
原创 图像拼接--Fish-Eye Lenses-Based Camera Calibration and Panoramic Image Stitching
Fish-Eye Lenses-Based Camera Calibration and Panoramic Image Stitching2018 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)https://ieeexplore.ieee.org/abstract/document/8448987...
2018-12-06 15:51:23 1188
原创 图像拼接--Bird’s-Eye View Vision System for Vehicle Surrounding Monitoring
Bird’s-Eye View Vision System for Vehicle Surrounding MonitoringLiu YC., Lin KY., Chen YS. (2008) Bird’s-Eye View Vision System for Vehicle Surrounding Monitoring. In: Sommer G., Klette R. (eds) Robo...
2018-12-05 15:46:38 2806
原创 Image Stitching 代码
https://github.com/kushalvyas/Python-Multiple-Image-Stitchinghttps://github.com/AmazingZhen/ImageStitchinghttps://github.com/yihui-he/panoramahttps://github.com/nothinglo/NISwGSPhttps://github.com...
2018-12-05 14:12:04 3334
原创 Tensorflow 源码安装成功,导入报错 ImportError: cannot import name 'build_info'
ImportError: cannot import name ‘build_info’ImportError: Could not import tensorflow. Do not import tensorflow from its source directory; change directory to outside the TensorFlow source tree, and r...
2018-12-04 08:50:56 6829 1
原创 CNN模型 int8量化实现方式(二)
这里介绍一个完全基于 Tensorflow 的模型量化方法,以 yolo v3 为例1)利用现有yolo v3 模型 生成 Tensorflow pb 模型基于 https://github.com/mystic123/tensorflow-yolo-v3Run python ./convert_weights.py and python ./convert_weights_pb.py...
2018-12-03 09:09:33 7484 1
原创 CNN模型 INT8 量化实现方式(一)
当前CNN模型基本都是 float32,将其转换为 INT8 可以降低模型大小,提升速度,精度降低的也不太多。那么在实际中如何实现这个量化了?在网上找到了两种实践方法,这里先介绍其中的一种。这里主要涉及两个问题:1)就是 int8量化;2)就是 int8 模型的使用基于Caffe-Int8-Convert-Tools进行caffe模型转int8量化 在 NCNN 框架上运行https://b...
2018-11-27 11:05:30 17418 2
原创 Tensorflow mnist 数据集测试代码 + 自己下载数据
https://blog.csdn.net/weixin_39673686/article/details/81068582import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data# 自己下载 MNIST_data 数据集, csdn 上下载很快mnist_data_folde...
2018-11-21 14:28:54 842 1
原创 ubunu16.04 TensorFlow object detection API 应用配置
TensorFlow object detection API应用–配置主要参考 :https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.mdhttps://www.cnblogs.com/zongfa/p/9662832.html1) 首先下载 Tenso...
2018-11-20 16:23:22 318
原创 ubuntu16.04 cuda9.0 cudnn Tensorflow GPU 1.10.0
Ubuntu14.04升级到Ubuntu16.04查看目前版本lsb_release -aapt-get update &amp;amp;amp;amp;amp;amp;amp;&amp;amp;amp;amp;amp;amp;amp; apt-get dist-upgraderebootdo-release-upgradelsb_release -ahttps://blog.csdn.net/qq_35523593/article/details
2018-11-19 14:02:28 926
转载 ubuntu 14.04 16.04 18.04使用阿里源
https://blog.csdn.net/bin_zhang1/article/details/81008645首先备份一下原来的sources.listcp /etc/apt/sources.list /etc/apt/sources.list.bak然后修改sources.listsudo vi /etc/apt/sources.list然后根据你的版本将sources.lis...
2018-11-16 09:21:46 594
原创 模型加速--Slimmable neural networks
Slimmable neural networksICLR2019Code and models will be released可瘦身的神经网络,针对不同硬件和运行环境,可以快速提供与之相适应的CNN模型来完成任务。硬件配置好的,给一个大模型,硬件配置差的,给一个小点的模型。同一个模型,设置一下参数就可以了At runtime, the network can adjust its w...
2018-11-07 15:40:40 2313
原创 图像拼接--Seam Carving for Content-Aware Image Resizing
Seam Carving for Content-Aware Image Resizing智能图像缩放ACM Transactions on graphics (TOG). Vol. 26. No. 3. ACM, 2007https://github.com/danasilver/seam-carvinghttps://github.com/vivianhylee/seam-carvin...
2018-11-07 14:42:13 2733
原创 模型加速--CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-QuantizationCVPR2018http://www.sfu.ca/~ftung/裁剪和量化一体化框架本文的思路比较简单,裁剪+量化一体训练模型分三个步骤:1) Clipping 裁剪,将网络中的权重系数值接近0 的权重全部置零,当然这种置零是临时...
2018-11-05 14:37:42 1696
原创 模型加速--LCNN: Lookup-based Convolutional Neural Network
LCNN: Lookup-based Convolutional Neural NetworkCVPR2017https://github.com/ildoonet/tf-lcnnhttps://github.com/hessamb/lcnn本文使用查表法加速CNN网络训练和计算,可以在嵌入式设备终端进行CNN网络训练本文对每个网络层构建一个 字典 Dictionary,每个 weig...
2018-11-02 16:13:31 1074
原创 模型量化--TBN:Convolutional Neural Network with Ternary Inputs and Binary Weights
TBN:Convolutional Neural Network with Ternary Inputs and Binary WeightsECCV_2018 paperTBN 用 高效的 XOR, AND 及位运算 代替 传统CNN 中的 算术运算TBN replaces the arithmetical operations in standard CNNs with efficie...
2018-11-01 16:12:18 649
原创 模型裁剪--Rethinking the Value of Network Pruning
Rethinking the Value of Network Pruninghttps://github.com/Eric-mingjie/rethinking-network-pruning网络模型裁剪价值的重新思考当前的深度学习网络模型一般都是 heavy computational cost,如何降低其计算量而尽可能保持网络性能是一个重要的研究课题。标准的模型裁剪三部曲是:1)训...
2018-10-29 16:28:44 6417 1
原创 实时目标检测--Pelee: A Real-Time Object Detection System on Mobile Devices
Pelee: A Real-Time Object Detection System on Mobile DevicesICLR 2018Code: https://github.com/Robert-JunWang/PeleeCNN模型在嵌入式设备中运行成为一种趋势,为此提出了一些模型如 MobileNet, ShuffleNet, and NASNet-A,他们主要依赖于 depth...
2018-10-26 16:29:10 2667
原创 图像拼接--Robust image stitching with multiple registrations
Robust image stitching with multiple registrationsECCV2018本文使用多个 registrations 来增强图像拼接的效果标准的图像拼接流程一般为:1)得到一个 single registration(这里我们使用 registration for an arbitrary (potentially non-rigid) image t...
2018-10-18 15:15:39 1735 1
原创 图像拼接--Construction and Refinement of Panoramic Mosaics with Global and Local Alignment
Construction and Refinement of Panoramic Mosaics with Global and Local AlignmentInternational Conference on Computer Vision , 1998 , 48 (2) :953本文针对图像序列做全景拼接1) 这里我们没有使用 cylindrical or spherical coo...
2018-10-17 14:23:27 978
原创 图像拼接--Automatic Panoramic Image Stitching using Invariant Features
Automatic Panoramic Image Stitching using Invariant Features《International Journal of Computer Vision》 , 2007 , 74 (1) :59-73本文提出使用 SIFT 做特征点匹配,然后用 bundle adjustment 计算图像坐标转换参数(类似 Homography),最后使用 ...
2018-10-16 15:19:24 5588 1
原创 图像拼接--A multiresolution spline with application to image mosaics
A multiresolution spline with application to image mosaics《Acm Trans on Graphics》 , 1983 , 2 (4) :217-236本文主要介绍使用 Multiresolution Spline算法来消除图像拼接之间的痕迹A technical problem common to all applications ...
2018-10-16 13:35:26 1559 1
原创 图像拼接--Creating full view panoramic image mosaics and environment maps
Creating Full View Panoramic Image Mosaics and Environment MapsIn ACM SIGGRAPH, pages 251–258, 1997Proceeding SIGGRAPH '97 Proceedings of the 24th annual conference on Computer graphics and interact...
2018-10-16 09:40:30 1014
原创 图像拼接--Parallax-tolerant Image Stitching
Parallax-tolerant Image StitchingCVPR2014图像拼接是一个被深入研究的课题。通常第一步是输入图像的对应。早期的方法是对两个输入图像估计一个 2D映射,通常是一个 homography, 然后用它来对齐图像。因为 homography 不能考虑 parallax,所以这些方法要求输入图像拍摄的角度是一样的或者场景大致应该是位于同一平面内的。否则就不在这个...
2018-10-15 14:38:10 6289 12
转载 Opencv中Homography
转自 https://blog.csdn.net/datase/article/details/78420251 什么是Homography 在图1中有两张书的平面图,两张图分别有四个相对位置相同的点,Homography就是一个变换(3*3矩阵),将一张图中的点映射到另一张图中对应的点 因为Homography是一个3*3矩阵,所以可以...
2018-10-12 15:46:06 912
原创 图像拼接--Coarse-to-fine Seam Estimation for Image Stitching
Coarse-to-fine Seam Estimation for Image Stitchinghttps://arxiv.org/abs/1805.09578本文主要针对图像拼接中的缝合线选择的改进。以前的缝合线选择主要 measure the average performanceof the pixels on the seam without considering the ...
2018-10-12 13:59:54 959
原创 图像拼接--Seam-Driven Image Stitching
缝合线驱动的图像拼接Seam-Driven Image StitchingEurographics (EG) 2013上图对比了 传统图像拼接方法 和 缝合线驱动的图像拼接Traditional image stitching:传统图像拼接方法流程如下:首先对输入图像进行特征点提取,然后是特征点匹配,因为 non-planar scene geometry 和 误匹配问题,我们使用...
2018-10-11 16:52:50 3326 2
原创 重温目标检测--SSD
SSD: Single Shot MultiBox DetectorECCV2016https://github.com/weiliu89/caffe/tree/ssd针对目标检测问题,本文侧重的是 速度+精度对于 300×300 图像,SSD achieves 74.3% mAP 1 on VOC2007 test at 59 FPS on a Nvidia Titan XSSD ...
2018-09-30 15:50:47 537
原创 重温目标检测--YOLO v3
YOLOv3: An Incremental Improvementhttps://pjreddie.com/yolo/本文是对 YOLO系列的进一步完善。先上和其他检测算法的 COCO 对比结果2.1. Bounding Box Prediction和 YOLO v2 一样,这里我们采用了 dimension clusters as anchor boxes 来预测矩形框坐标,这一...
2018-09-20 14:24:27 1143
原创 重温目标检测--YOLO v2 -- YOLO9000
YOLO9000:Better, Faster, StrongerCVPR 2017, Best Paper Honorable Mentionhttps://pjreddie.com/darknet/yolo/本文是对 YOLO v1 的改进。2 BetterYOLO v1 主要问题有两个:1)localization error 较高;2)relatively low recall...
2018-09-20 10:35:14 469
原创 重温目标检测--YOLO v1
You Only Look Once:Unified, Real-Time Object Detection CVPR2016 https://pjreddie.com/darknet/yolo/YOLO 提出的背景是 基于CNN目标检测的速度太慢了,主要目的就是提速。We reframe object detection as a single regression problem,...
2018-09-17 16:01:31 571
原创 重温目标检测--Faster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks NIPS2015 https://github.com/ShaoqingRen/faster_rcnn本文针对目标检测问题,在 Fast R-CNN 的基础上,提出 RPN 来改进候选区域提取,较大提升检测速度 Faster R-C...
2018-09-14 16:14:40 379
原创 重温目标检测--Fast R-CNN
Fast R-CNN ICCV 2015 https://github.com/rbgirshick/fast-rcnn本文在目标检测中起到一个承上启下的作用,从 R-CNN 经由 Fast R-CNN 过渡到 完美的 Faster R-CNN, 最大的提升还是速度方面的提升。Fast R-CNN architecture Fast R-CNN 的输入时 整个图像 和 一组矩形...
2018-09-13 10:45:14 402 1
原创 车牌识别--Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline
Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline ECCV2018 https://github.com/detectRecog/CCPD本文使用 CNN 网络端对端解决 车牌识别问题。 首先针对车牌识别问题,我们建立了一个比较大的数据库 CCPD ,这是目前为...
2018-09-11 16:17:22 7109 3
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
Corner Detection Algorithms for Digital Images in Last Three Decades
2011-02-22
Application of Shape Analysis Techniques for the Classification of Vehicles
2011-02-22
Solving the process of hysteresis without determining the optimal thresholds
2011-02-22
百面机器学习.pdf
2019-06-01
CLIP-Q CVPR2018 code
2018-10-30
Vehicle Detection and Tracking in Car Video Based on Motion Model
2011-10-15
Projection and Least Square Fitting
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
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