- 博客(39)
- 资源 (91)
- 收藏
- 关注
原创 卫星图像中的车辆分析--A Large Contextual Dataset for Classification, Detection and Counting of Cars
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning ECCV2016 https://gdo-datasci.ucllnl.org/cowc/本文针对卫星图像中的车辆分析建立了一个新的数据库:Cars Overhead with Context (COWC
2017-09-30 15:03:43 1861 1
原创 人车密度估计--Towards perspective-free object counting with deep learning
Towards perspective-free object counting with deep learning ECCV2016 https://github.com/gramuah/ccnn本文针对人车密度估计问题,主要做了两个工作:1)提出了一个 novel convolutional neural network:Counting CNN (CCNN),将图像块回归到密度图,2)
2017-09-30 10:26:47 3156
原创 快速去阴影--Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network https://arxiv.org/abs/1709.09283本文主要解决快速去阴影问题,这里使用的策略是 SVM+CNNA. Computing Shadow Prior 首先使用 mean shift 算法对输入图像进
2017-09-30 08:56:09 1812 1
原创 快速人群密度估计--Multi-scale Convolutional Neural Networks for Crowd Counting
Multi-scale Convolutional Neural Networks for Crowd Countinghttps://arxiv.org/abs/1702.02359对于人群密度估计问题,由于图像中 scale variations problem,所以提出使用多个CNN来解决 Multi-column/network。使用多个CNN网络导致 网络的参数数量增加,计算量增加,不利于
2017-09-29 16:15:19 3822 1
原创 人群计数--Mixture of Counting CNNs
Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting https://arxiv.org/abs/1703.09393本文是人群计数的,不是人群密度估计。所以网络结构比较比较简单。这里主要的思路是针对不同场景的 scale and c
2017-09-29 14:15:54 2753
原创 人群密度估计--Fully Convolutional Crowd Counting On Highly Congested Scenes
Fully Convolutional Crowd Counting On Highly Congested Scenes The 12th International Conference on Computer Vision Theory and Applications (VISAPP) VISAPP 2017本文使用 FCN 来做人群密度估计,主要参考 Single-image cro
2017-09-29 09:25:26 2354
原创 人群密度估计--CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting published in the proceedings of ACM Conference on Multimedia (ACMMM) - 2016 http://val.serc.iisc.ernet.in/CrowdNet/ Caffe: https://g
2017-09-28 14:26:20 5067 2
原创 人群密度估计--Learning to Count with CNN Boosting
Learning to Count with CNN Boosting ECCV2016本文使用CNN来进行人群密度估计,主要有两个改进地方:layered boosting and selective samplingBoosting deep networks : Boosting 在组合学习中是一种知名的贪婪技术。基本的思想就是对前一个分类器的误差训练一个新的分类器来矫正。广义上,当使用多个
2017-09-28 10:02:32 3058
原创 人群分析--ResnetCrowd: A Residual Deep Learning Architecture
ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification (AVSS 2017) 2017 14th IEEE International Conference on Advance
2017-09-27 16:25:39 1841
原创 人群密度估计--CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting International Conference on Advanced Video and Signal Based Surveillance (AVSS) 2017 Torch: http
2017-09-27 11:10:32 2856 1
原创 视频物体分割--One-Shot Video Object Segmentation
One-Shot Video Object Segmentation CVPR2017 http://www.vision.ee.ethz.ch/~cvlsegmentation/osvos/One-Shot Video Object Segmentation,基于单帧标记的视频物体分割,对于一个视频中的某一个物体,我们只提供一张训练样本,怎么把视频里所有的该物体分割出来? 上图第一张图像
2017-09-26 16:17:28 9660
原创 运动相机检测无人机-- Detecting Flying Objects using a Single Moving Camera
Detecting Flying Objects using a Single Moving Camera PAMI 2017 http://cvlab.epfl.ch/research/unmanned/detection https://drive.switch.ch/index.php/s/3b3bdbd6f8fb61e05d8b0560667ea992Flying Objects De
2017-09-21 09:40:54 1879 1
原创 视频动作识别--Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition ECCV2016 https://github.com/yjxiong/temporal-segment-networks本文侧重于从更长的视频中提取 long-range temporal structure,因为某些动作的过程较长,
2017-09-20 15:45:33 1786
原创 嵌入式目标检测--Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection
Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video针对在嵌入式设备使用CNN进行目标检测,本文对 YOLOv2进行改进,在稍微降低精度的情况下,减少模型的参数量,提高运算速度。在视频处理中,相对 YOLOv2 平均加速 ∼3.3X, run an average o
2017-09-20 14:06:22 7237 4
原创 无人驾驶中的目标检测--MODNet: Moving Object Detection Network for Autonomous Driving
MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving这里讲视频动作识别中的 two stream networks 框架应用于无人驾驶中的目标检测,视频分析中的 motion and appearance cues 本文的 contributions 主要以下三点: 1
2017-09-20 09:28:20 6223
原创 快速小目标检测--Feature-Fused SSD: Fast Detection for Small Objects
Feature-Fused SSD: Fast Detection for Small Objects本文针对小目标检测问题,对 SSD 模型进行了一个小的改进,将 contextual information 引入到 SSD 中 帮助SSD检测小目标。 contextual information 对于小目标的检测 重要性是不言而喻的。小目标在图像中 limited resolution and
2017-09-19 16:22:07 16678 27
原创 人群密度估计--Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs
Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs ICCV2017针对人群密度估计问题,本文主要从 incorporating global and local contextual information 来降低人群密度估计误差 使用多个CNN网络来估计不同尺度的 context 来帮助人群密度估
2017-09-19 13:51:18 4760 2
原创 人群密度估计--Spatiotemporal Modeling for Crowd Counting in Videos
Spatiotemporal Modeling for Crowd Counting in Videos ICCV2017针对视频人群密度估计问题,这里主要侧重视频中的 temporal information,使用 convolutionalLSTM(ConvLSTM) 的一个变体 a bidirectional ConvLSTM model 来提取当前帧的前后帧信息提升人群密度估计当前基于回
2017-09-19 09:23:09 2929 2
原创 人群行为分类数据库--Novel Dataset for Fine-grained Abnormal Behavior Understanding in Crowd
Novel Dataset for Fine-grained Abnormal Behavior Understanding in Crowd 数据库:https://github.com/hosseinm/med本文针对人群行为分类建立了一个数据库,这里有5类:Panic,Fight,Congestion,Obstacle ,Neutral目前已有的数据库情况: 2 Proposed Data
2017-09-18 13:59:57 1785
原创 人群行为分类数据库--Crowd-11: A Dataset for Fine Grained Crowd Behaviour Analysis
Crowd-11: A Dataset for Fine Grained Crowd Behaviour Analysis CVPRW2017这个数据库目前貌似没有公开,以后应该公开吧。针对人群行为分析方面的研究,本文主要的工作有以下三点: 1)针对人群行为细分,我们建立了一个较大的数据库 Crowd-11, 11 crowd motion patterns and it is compose
2017-09-18 11:15:12 3805 1
原创 人群分割--Fully Convolutional Neural Networks for Crowd Segmentation
Fully Convolutional Neural Networks for Crowd Segmentation https://arxiv.org/abs/1411.4464这里设计了一个全卷积网络用于视频中的人群分割,主要考虑三个信息:Apperance、 Motion 、Structure,思路还是很原始的。 主要的难度在于 静态的人群我们也想分割出来,再就是当人群的纹理和背景相似的时
2017-09-18 10:08:54 2214
原创 视频动作识别--Convolutional Two-Stream Network Fusion for Video Action Recognition
Convolutional Two-Stream Network Fusion for Video Action Recognition CVPR2016http://www.robots.ox.ac.uk/~vgg/software/two_stream_action/ https://github.com/feichtenhofer/twostreamfusion对视频动作识别 采用 two
2017-09-15 16:27:30 4711 5
原创 视频动作识别--Towards Good Practices for Very Deep Two-Stream ConvNets
Towards Good Practices for Very Deep Two-stream ConvNets http://yjxiong.me/others/action_recog/ https://github.com/yjxiong/caffe/tree/action_recog本文首先指出对于静态图像分类,CNN已经取得很大进步,但是对于视频动作分类,CNN网络表现的不是很好。这里
2017-09-15 15:48:26 1669
原创 视频动作识别--Two-Stream Convolutional Networks for Action Recognition in Videos
Two-Stream Convolutional Networks for Action Recognition in Videos NIPS2014 http://www.robots.ox.ac.uk/~vgg/software/two_stream_action/本文针对视频中的动作分类问题,这里使用 两个独立的CNN来分开处理 视频中的空间信息和时间信息 spatial 和 tempal
2017-09-15 14:11:58 7210
原创 时空特征--Learning Spatiotemporal Features with 3D Convolutional Networks
Learning Spatiotemporal Features with 3D Convolutional Networks ICCV 2015 http://vlg.cs.dartmouth.edu/c3d/ https://github.com/facebook/C3D本文使用 3D CNN 来分析视频序列,学习到的时空特征称之为 C3D,主要寻找3D CNN 中的最优3D滤波器结构
2017-09-15 10:05:23 6657
原创 人群场景分析--Slicing Convolutional Neural Network for Crowd Video Understanding
Slicing Convolutional Neural Network for Crowd Video Understanding CVPR2016 http://www.ee.cuhk.edu.hk/~jshao/SCNN.html Caffe code: https://github.com/amandajshao/Slicing-CNN本文也是使用CNN网络对一段视频进行分析,网络输出
2017-09-14 16:36:11 2071
原创 人群行为分析--Understanding Pedestrian Behaviors from Stationary Crowd Groups
Understanding Pedestrian Behaviors from Stationary Crowd Groups CVPR2015本文主要探讨 静态人群对行人行为的影响 人群行为的建模以前主要考虑的因素有:scene layout (e.g. entrances, exits, walls, and obstacles), pedestrian beliefs (the choic
2017-09-14 11:16:59 2351 2
原创 人群场景的属性--Deeply Learned Attributes for Crowded Scene Understandin
Deeply Learned Attributes for Crowded Scene Understanding CVPR2015 http://www.ee.cuhk.edu.hk/~jshao/WWWCrowdDataset.html https://github.com/amandajshao/www_deep_crowd本文要解决的问题是什么了? 给你一段人群场景的视频,算法能否给出
2017-09-13 15:21:20 1014
原创 人群运动--Scene-Independent Group Profiling in Crowd
Scene-Independent Group Profiling in Crowd CVPR2014 http://www.ee.cuhk.edu.hk/~jshao/CUHKcrowd.html https://github.com/amiltonwong/crowd_group_profilecrowd 由 groups 组成,这里我们对 groups 属性进行分析,提出几个可以定量分析的
2017-09-13 13:58:30 1234
原创 群体运动度量--Measuring Crowd Collectiveness
Measuring Crowd Collectiveness CVPR2013 http://mmlab.ie.cuhk.edu.hk/projects/collectiveness/ https://github.com/metalbubble/collectiveness本文针对人群运动的藐视 Collective motions 定义了一个描述子 collectiveness descr
2017-09-13 09:36:41 1879
原创 人群计数--Cross-scene Crowd Counting via Deep Convolutional Neural Networks
Cross-scene Crowd Counting via Deep Convolutional Neural Networks CVPR2015本文主要使用深度学习来完成跨场景人群计数 cross-scene crowd counting,简单的说就是在多个场景训练,在没有训练过的场景测试。 我们建立了一个新的人群计数方面的数据库 http://www.ee.cuhk.edu.hk/~xg
2017-09-12 14:21:20 6538 7
原创 视频中的运动特征--Learning Motion Patterns in Videos
Learning Motion Patterns in Videos CVPR2017 Torch code: http://thoth.inrialpes.fr/research/mpnet 本文要解决的问题是 determining whether an object is in motion, irrespective of camera motion, 注意这里的相机是可以运动
2017-09-11 15:36:10 2906
原创 弱监督语义分割--Object Region Mining with Adversarial Erasing
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach CVPR2017怎么将只有图像标签的训练图像用于语义分割的训练,这里我们提出使用一个分类网络来讲训练图像中的物体进行分割,得到像素标记的训练图像,同时提出一个 online prohibi
2017-09-08 15:17:33 7979 5
原创 特征匹配--GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence
GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence CVPR2017 c++ code: https://github.com/JiawangBian/GMS-Feature-Matcher主要本要针对特征匹配问题,提出了一个简单的基于统计的解决方法,可以快速区分出正确的匹配和错误的匹
2017-09-08 10:59:33 12723 2
原创 网络模型--Squeeze-and-Excitation Networks
Squeeze-and-Excitation Networks https://arxiv.org/abs/1709.01507ILSVRC 2017 image classification winner https://github.com/hujie-frank/SENet本文主要提出了一个新的网络模块 Squeeze-and-Excitation block,作用就是对不同 channe
2017-09-07 15:41:58 5003
原创 卫星图像分割--Effective Use of Dilated Convolutions for Segmenting Small Object Instances
Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery https://arxiv.org/abs/1709.00179针对卫星图像中的小目标分割问题,本文从 dilated convolution 的有效使用给出了解决方法,主要是 先 increa
2017-09-07 11:12:57 3991 5
原创 人群计数--Switching Convolutional Neural Network for Crowd Counting
Switching Convolutional Neural Network for Crowd Counting CVPR2017 Code for SCNN is based on Lasagne\Theano :https://github.com/val-iisc/crowd-counting-scnn 针对人群密度估计问题提出了一个 Switch-CNN网络,大的思路...
2017-09-06 11:40:54 8882 1
原创 人群计数--Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network CVPR2016 https://github.com/svishwa/crowdcount-mcnn https://github.com/leeyeehoo/Reduplication-of-Single-Image-Crowd-Countin
2017-09-05 15:57:35 4503 3
原创 目标检测-- DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling ICCV2017 An easily extendedTheanobased code: https://github.com/lachlants/denet本文针对候选区域提取这个步骤进行加速: 使用角点提取来初步过滤大部分候选区域我们提出的
2017-09-05 10:42:33 5387 2
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