检索结果-内蒙古大学图书馆

27th British Machine vision Conference, BMVC 2016

作者： Nimisha, T.M. Arun, M. Rajagopalan, A.N. Image Processing and Computer Vision Lab Indian Institute of Technology Madras Chennai India

In this paper, we address the problem of jointly estimating the latent image and the depth/blur map from a single space-variantly blurred image using dictionary learning. The approach taken is based on the central idea of dictionary replacement viz. the sparse representation of a blurred image over a blurred dictionary is equivalent to that over a clean dictionary. While most of the dictionary-based deblurring methods consider planar scenes with space-invariant blur, we handle 3D scenes with space-variant blur caused by either camera motion or optical defocus. For a given blurred image, the dictionary blurred with the corresponding blur kernel provides the best representation with the least error. We formulate our problem of blur map and latent image estimation as a multi-label MRF and solve it using graph-cut. Experimental results on defocus as well as motion blur depict the effectiveness of our scheme. © 2016. The copyright of this document resides with its authors.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Random number generators: Metrics and tests for uniformity and randomness

引用

Journal of Combinatorial Mathematics and Combinatorial Computing 2010年 74卷 161-180页

作者： Yfantis, E.A. Pedersen, J.B. Image Processing Computer Vision and Machine Intelligence Lab College of Engineering 4505 Maryland Parkway Las Vegas NV 89154-4019 United States

Random number generators are a small part of any computer simulation project. Yet they are the heart and the engine that drives the project. Often times software houses fail to understand the complexity involved in building a random number generator that will satisfy the project requirements and will be able to produce realistic results. Building a random number generator with a desirable periodicity, that is uniform, that produces all the random permutations with equal probability, and at random, is not an easy task. In this paper we provide tests and metrics for testing random number generators for uniformity and randomness. These tests are in addition to the already existing tests for uniformity and randomness, which we modify by running each test a large number of times on sub-sequences of random numbers, each of length n. The test result obtained each time is used to determine the probability distribution function. This eliminates the random number generator misclassification error. We also provide new tests for uniformity and randomness, the new tests for uniformity test the skewness of each one of the subgroups as well as the kurtosis. The tests for randomness, which include the Fourier spectrum, the phase spectrum, the discrete cosine transform spectrum, and the orthogonal wavelet domain, test for patterns not detected in the row data space. Finally we provide visual and acoustic tests.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Contourlet transform based moving object segmentation

Contourlet transform based moving object segmentation

引用

2013 IEEE Conference on Information and Communication Technologies, ICT 2013

作者： Khare, Manish Nigam, Swati Srivastava, Rajneesh Kumar Khare, Ashish Image Processing and Computer Vision Lab Department of Electronics and Communication University of Allahabad Allahabad India

ISBN: (纸本)9781467357586

Moving object segmentation is an important step toward development of any computer vision systems. In the present work, we have proposed a new method for segmentation of moving objects, which is based on single change detection method applied on Contourlet coefficients of two consecutive frames. We have chosen contourlet transform as it has high directionality and represents salient features of image such as edges, curves and contours in better way as compared with wavelet transform. The proposed method is simple and does not require any other parameter except contourlet coefficients. Results after applying the proposed method for segmentation of moving objects are compared with other state-of-the-art methods in terms of visual as well as quantitative performance measures viz. Average difference, Normalized absolute error and Pixel classification based measure. The proposed method is found to be better than other methods. © 2013 IEEE.

关键词： Contourlet transform

来源：评论

学校读者我要写书评

暂无评论

Efficient geometric matching with higher-order features

Efficient geometric matching with higher-order features

引用

作者： Paramanand, C. Rajagopalan, A.N. Image Processing and Computer Vision Lab. Department of Electrical Engineering IIT Madras India

ISBN: (纸本)9781424421756

We propose a new technique in which line segments and elliptical arcs are used as features for recognizing image patterns. By using this approach, the process of locating a model in a given image is efficient since the number of features to be compared is few. We propose distance measures to evaluate the similarity between the features of the model and that of the image. The model transformation parameters are found by searching the transformation space using cell decomposition. © 2008 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Attention Approach in Multimodal Emotion Recognition for Human Robot Interaction 36

Hierarchical Attention Approach in Multimodal Emotion Recogn...

引用

36th International Technical Conference on Circuits/Systems, computers and Communications, ITC-CSCC 2021

作者： Abdullah, Muhammad Ahmad, Mobeen Han, Dongil Vision and Image Processing Lab Sejong University Department of Computer Engineering Seoul Korea Republic of

ISBN: (纸本)9781665435536

The ability to perceive human emotions is one of the key elements that may promise a natural, genuine and more reliable human robot interaction. Though emotional perception in human robot interaction has been challenged by many difficulties, the lack of contextual understanding is can be attributed as the biggest hurdle in this regard. Most of the literature refers to the datasets developed in controlled environment to validate the performance of their systems which happens to be really good. Still those systems are very far from achieving that kind of performance in real-life scenarios. In this paper a multimodal emotion recognition strategy is presented, that uses voice features in addition to the facial expressions to determine the emotional state of the user. A hierarchical attention layer is used to for feature fusion purpose. The final system is end-to-end trainable, multimodal approach makes it more resilient to the changes in environment. The achieved 76.3% accuracy for eNterface05 video dataset, which is higher than the any single modality approach in the comparison. © 2021 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Deskewing by space-variant deblurring 27

Deskewing by space-variant deblurring

引用

27th British Machine vision Conference, BMVC 2016

作者： Seemakurthy, Karthik Vasu, Subeesh Rajagopalan, A.N. Image Processing and Computer Vision Lab Department of Electrical Engineering IIT Madras Chennai India

Skew and motion blur are significant challenges when camera and scene of interest are in two different media. Skew occurs due to spatially varying refraction on a dynamic water surface, whereas motion blur results from multiple intensities impinging on the imaging sensor during camera exposure time due to time varying refraction. In this paper, we introduce the notion of virtual depth map which we assign to a planar scene when observed through a dynamic water surface and transform the deskewing problem into one of space-variant deblurring from a single image within an alternating minimization framework. Since the nature of the virtual depth map can change during exposure due to change in wind properties, we also propose a shot detection framework to identify segments of frames from the captured video which conform to a single virtual depth map. While the overall wave motion can be arbitrary, within each segment the nature of wave is modeled as an exponentially decaying periodic wave. © 2016. The copyright of this document resides with its authors.

关键词： Refraction

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 Algorithm for Small Object Detection in Drone images 12th

Improved YOLOv5 Algorithm for Small Object Detection in Dr...

引用

12th International Conference on Computational Visual Media, CVM 2024

作者： Lin, Yitong Liu, Yiguang Vision and Image Processing Lab College of Computer Science Sichuan University Chengdu610065 China

ISBN: (纸本)9789819720910

The object detection in the context of drone is a hot topic in the field of computer vision in recent years. In response to the challenge of limited image feature information and the presence of numerous small and densely packed objects in drone-captured images, this paper proposes a novel feature fusion detection model, HTH-YOLOv5, based on YOLOv5. Firstly, we enhance the detection capability of small objects by adding a detection channel from high-resolution feature maps and propose a Hybrid Transformer Head (HTH) that incorporates a hybrid Transformer module, aiming to improve the network’s focus on small objects by fusing global and local feature information. Secondly, we introduce a Convolutional Attention Feature Fusion module (CA-FF) based on CBAM. This module dynamically adjusts attention weights for the allocation of original feature maps in both channel and spatial dimensions, aiming to enhance the feature extraction capability for small objects. Finally, to better capture global and contextual information, we introduce the Hybrid Transformer module into the backbone and enhance its original feature fusion method using the CA-FF module. Experiments on the Vis-Drone 2021 dataset demonstrate that, compared to the baseline YOLOv5s model, the improved model shows an increase of 7.2% in mAP50 and 6.3% in mAP75. The model trained with an input resolution of 1540×1540 achieves an mAP50 of 57.1%, marking a 12.4% improvement over YOLOv5. The improved HTH-YOLOv5 achieves increased accuracy while maintaining a detection speed of 45 FPS, making it more suitable for small object detection in drone scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Inpainting large missing regions in range images

Inpainting large missing regions in range images

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Bhavsar, Arnav V. Rajagopalan, A.N. Image Processing and Computer Vision Lab. Indian Institute of Technology Madras Chennai India

ISBN: (纸本)9780769541099

We propose a technique to inpaint large missing regions in range images. Such a technique can be used to restore degraded/occluded range maps. It can also serve to reconstruct dense depth maps from sparse measurements which can speed up the acquisition. Our method uses the visual cue from segmentation of an intensity image registered to the range image. Our approach enforces that pixels in the same segment should have similar range. Our simple strategy involves plane-fitting and local medians over segments to compute local energies for labeling unknown pixels. Our results exhibit high quality inpainting with very low errors. © 2010 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation on segmentation methods for medical images 11

Performance evaluation on segmentation methods for medical i...

引用

Proceedings of the International Conference on Advances in Computing and Artificial Intelligence

作者： Khare, Manish Srivastava, Rajneesh Kumar Khare, Ashish Image Processing and Computer Vision Lab. Department of Electronics and Communication University of Allahabad India

ISBN: (纸本)9781450306355

This paper presents the performance evaluation of different segmentation algorithms for medical images. Accuracy and clarity are very important issues for medical imaging and same in the case with segmentation. In this paper, we have proposed a level set method without reinitialization with some specific shapes for segmentation and compared our proposed approach for segmentation with three other approaches where the first approach is based on region splitting based region growing category, second is based on region merging based region growing category and third is based on level set. This comparison is based on six different performance parameters namely Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Maximum Difference (MD), Normalized Cross Correlation (NCC), Normalized Absolute Error (NAE) and Structural Content (SC). We have compared the proposed approach with three above mentioned approaches for several images, out of which results for four images are provided in this paper, and we find that the approach is better than the other one. © 2011 ACM.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Depth estimation with a practical camera

Depth estimation with a practical camera

引用

2009 20th British Machine vision Conference, BMVC 2009

作者： Bhavsar, Arnav V. Rajagopalan, A.N. Image Processing and Computer Vision Lab. Indian Institute of Technology Madras Chennai India

ISBN: (纸本)1901725391

Given an off-the-shelf camera, one has the freedom to move the camera or play around with its intrinsic parameters such as zoom or aperture settings. We propose a framework for depth estimation from a set of calibrated images, captured under general camera motion and parameter variation. Our framework considers the practical trade-offs in a camera and hence essentially generalizes the more constrained areas such as lateral or axial stereo, shape from defocus/focus etc. We discuss practical issues where such an approach becomes important. We pose the problem in a MAP framework and compute the depth estimates efficiently using belief propagation (BP). We also incorporate the visibility consideration to handle occlusions. Moreover, we use the vital cue from color image segmentation to constrain the estimation process. Our results demonstrate the effectiveness of our approach to localize discontinuities and handle low-textured regions. © 2009. The copyright of this document resides with its authors.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：