自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+

AI小作坊 的博客

大道至简,天人合一

  • 博客(16)
  • 资源 (91)
  • 收藏
  • 关注

原创 深度摄影风格转换--Deep Photo Style Transfer

Deep Photo Style Transfer https://arxiv.org/abs/1703.07511Code: https://github.com/luanfujun/deep-photo-styletransfer本文使用深度卷积网络来进行 摄影风格转换,在 Neural Style algorithm [5] 的基础上进行改进的,主要是在目标函数进行了修改,加了一项 Pho

2017-04-27 11:02:12 8820 2

原创 GAN人脸修复--Generative Face Completion

Generative Face Completion CVPR 2017 https://arxiv.org/abs/1704.05838Code: https://github.com/Yijunmaverick/GenerativeFaceCompletion首先来直观的认识一下人脸修复是什么? 本文算法训练流程图如下: 主要由三个模块构成:Generator,Discriminato

2017-04-26 09:59:13 15787 12

原创 训练样本制作--Annotating Object Instances with a Polygon-RNN

Annotating Object Instances with a Polygon-RNN CVPR2017 project page: http://www.cs.toronto.edu/polyrnn/这里主要提出一个制作真值数据的工具。如下图所示:这里我们使用VGG网络提取特征,使用一个 Convolutional LSTM 进行物体轮廓的提取。我们的模型之所以是 RNN,是因为它每次

2017-04-25 15:52:42 4428 2

原创 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization

Deep Self-Taught Learning for Weakly Supervised Object Localization CVPR 2017https://arxiv.org/abs/1704.05188什么是 Weakly Supervised Object Localization,refers to learning to localize objects within ima

2017-04-25 10:15:16 4778

原创 目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution

Accurate Single Stage Detector Using Recurrent Rolling Convolution CVPR 2017 商汤科技关于目标检测的文献Code: https://github.com/xiaohaoChen/rrc_detection本文直观的理解就是对SSD 嵌入 contextualinformation 使其可以同时检测大目标和小目标。这里

2017-04-24 16:57:53 6024 3

原创 大角度人脸转正--Towards Large-Pose Face Frontalization in the Wild

Towards Large-Pose Face Frontalization in the Wildhttps://www.arxiv.org/abs/1704.06244本文结合 3D Morphable Model (3DMM) 和 GAN 来进行人脸转正。大的框架如下图所示: 3DMM Coefficients 得到输入人脸的姿态信息,通过3D模型可以得到大概信息,没有细节信息 因为原始输

2017-04-24 14:33:40 7892 3

原创 行人姿态估计--Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields CVPR 2017 Code: https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation 效果演示视频: https://youtu.be/pW6nZXeWlGM 如果可以看youtu 的话多

2017-04-21 10:03:08 19325

原创 目标检测--Improving Object Detection With One Line of Code

Improving Object Detection With One Line of Code https://arxiv.org/abs/1704.04503Code: https://github.com/bharatsingh430/soft-nms本文针对目标检测,对非极大值抑制这个环节进行了改善,可以检测出两个相邻的相同物体。 对于目标检测问题,我们目前主流的方法过程如下: 如果两

2017-04-20 16:00:50 3071 2

原创 手机CNN网络模型--MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationshttps://arxiv.org/abs/1704.04861本文是 Google 针对手机等嵌入式设备提出的一个小网络模型,叫 MobileNets,主要侧重于简单有效。这个 MobileNets 可以干什么了? 目标检测、细分

2017-04-20 12:26:40 12463

原创 行人检索--Beyond triplet loss: a deep quadruplet network for person re-identification

Beyond triplet loss: a deep quadruplet network for person re-identification CVPR2017 https://arxiv.org/abs/1704.01719本文使用深度学习进行行人检索,侧重点主要在损失函数的改进,提出了 quadruplet loss 用于减小类内方差 和 增加类间方差上图显示,在我们新的 quadr

2017-04-19 14:27:11 4978 2

原创 多视角图像生成--Multi-View Image Generation from a Single-View

Multi-View Image Generation from a Single-Viewhttps://www.arxiv.org/pdf/1704.04886本文使用对抗网络将单视角图像转出多视角图像。和 Beyond Face Rotation 类似,都是 coarse to fine,只不过网络结构一个是并联一个是串联。网络结构如下所示: 效果图如下: 由图像结果可以看出,细节还是有些

2017-04-19 09:40:28 7358 2

原创 对抗网络用于人脸转正--Beyond Face Rotation

Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesishttps://www.arxiv.org/abs/1704.04086本文主要解决的问题是把一张侧脸照片变成正脸照片,可以用这种照片进行人脸特征分析如人脸识别。

2017-04-18 16:57:19 7862 4

原创 目标检测--Beyond Skip Connections: Top-Down Modulation for Object Detection

Beyond Skip Connections: Top-Down Modulation for Object Detection CVPR2017 under review code :(coming soon) 可以结合 Feature Pyramid Networks for Object Detection 阅读大牛 Jitendra Malik 竟然都去 Google Resea

2017-04-17 15:55:43 4994

原创 膨胀卷积--Multi-scale context aggregation by dilated convolutions

Multi-scale context aggregation by dilated convolutions ICLR 2016https://arxiv.org/abs/1511.07122Code: https://github.com/fyu/dilation https://github.com/bordesf/dilation针对语义分割问题 semantic segmenta

2017-04-13 15:24:25 17953 2

原创 对抗学习用于目标检测--A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection CVPR 2017 Caffe code : https://github.com/xiaolonw/adversarial-frcnn本文将对抗学习引入到目标检测问题中,通过对抗网络生成一下遮挡和变形的训练样本来训练检测网络,从而使得网络能够对遮挡和

2017-04-12 16:51:43 12554 4

原创 目标检测--SqueezeDet 用于自动驾驶的实时目标检测网络

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving https://arxiv.org/abs/1612.01051 tensorflow code: https://github.com/Bi

2017-04-07 16:11:50 6071 7

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

Approach of vehicle segmentation based on texture character

2011-04-01

Method of removing moving shadow based on texture

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

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

High Performance Implementation of License Plate Recognition in Image Sequences

2011-02-22

Vs-star-- A visual interpretation system for visual surveillance

Vs-star-- A visual interpretation system for visual surveillance

2011-02-22

Robust fragments-based tracking with adaptive feature selection

Robust fragments-based tracking with adaptive feature selection

2011-02-22

Robust and automated unimodal histogram thresholding and potential applications

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

Extracting Straight Lines

Extracting Straight Lines---line detection edge detection

2011-02-22

Corner Detection Algorithms for Digital Images in Last Three Decades

Corner Detection Algorithms for Digital Images in Last Three Decades

2011-02-22

Application of Shape Analysis Techniques for the Classification of Vehicles

Application of Shape Analysis Techniques for the Classification of Vehicles

2011-02-22

Solving the process of hysteresis without determining the optimal thresholds

Solving the process of hysteresis without determining the optimal thresholds

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 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

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

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

提示
确定要删除当前文章?
取消 删除