检索结果-内蒙古大学图书馆

From multi-view to hollow-3D: Hallucinated hollow-3D R-CNN for 3D object detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Deng, Jiajun Zhou, Wengang Zhang, Yanyong Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230026 China The Department of Computer Science University of Science and Technology of China Hefei230026 China

As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely distributed in the 3D space, and with unstructured storage, which makes it difficult to represent them for effective 3D object detection. To this end, in this work, we regard point clouds as hollow-3D data and propose a new architecture, namely Hallucinated Hollow-3D R-CNN (H23D R-CNN), to address the problem of 3D object detection. In our approach, we first extract the multi-view features by sequentially projecting the point clouds into the perspective view and the bird-eye view. Then, we hallucinate the 3D representation by a novel bilaterally guided multi-view fusion block. Finally, the 3D objects are detected via a box refinement module with a novel Hierarchical Voxel RoI Pooling operation. The proposed H23D R-CNN provides a new angle to take full advantage of complementary information in the perspective view and the bird-eye view with an efficient framework. We evaluate our approach on the public KITTI Dataset and Waymo Open Dataset. Extensive experiments demonstrate the superiority of our method over the state-of-the-art algorithms with respect to both effectiveness and efficiency. The code will be made available at https://***/djiajunustc/H-23D_R-CNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Object recognition

Deep Unrestricted Document Image Rectification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Hao Liu, Shaokai Deng, Jiajun Zhou, Wengang Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Zhangjiang Laboratory Shanghai China The University of Adelaide Australian Institute for Machine Learning Australia

In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the input images must incorporate a complete document. Once the captured image merely involves a local text region, its rectification quality is degraded and unsatisfactory. Our previously proposed DocTr, a transformer-assisted network for document image rectification, also suffers from this limitation. In this work, we present DocTr++, a novel unified framework for document image rectification, without any restrictions on the input distorted images. Our major technical improvements can be concluded in three aspects. Firstly, we upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. Secondly, we reformulate the pixel-wise mapping relationship between the unrestricted distorted document images and the distortion-free counterparts. The obtained data is used to train our DocTr++ for unrestricted document image rectification. Thirdly, we contribute a real-world test set and metrics applicable for evaluating the rectification quality. To our best knowledge, this is the first learning-based method for the rectification of unrestricted document images. Extensive experiments are conducted, and the results demonstrate the effectiveness and superiority of our method. We hope our DocTr++ will serve as a strong baseline for generic document image rectification, prompting the further advancement and application of learning-based algorithms. The source code and the proposed dataset are publicly available at https://***/fh2019ustc/DocTr-Plus. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

GLOBAL PATCH MATCHING

学校读者我要写书评

暂无评论

GLOBAL PATCH MATCHING

ISPRS geospatial Week 2017

作者： Huang, X. Hu, K. Ling, X. Zhang, Y. Lu, Z. Zhou, G. Wuhan Engineering Science and Technology Institute Jiangda Road 30 Wuhan China Wuhan Sense Tour Tecnhonogy Company Luoshi South Road 320 Wuhan China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China School of Remote Sensing and Information Engineering Wuhan University China

This paper introduces a novel global patch matching method that focuses on how to remove fronto-parallel bias and obtain continuous smooth surfaces with assuming that the scenes covered by stereos are piecewise continuous. Firstly, simple linear iterative cluster method (SLIC) is used to segment the base image into a series of patches. Then, a global energy function, which consists of a data term and a smoothness term, is built on the patches. The data term is the second-order Taylor expansion of correlation coefficients, and the smoothness term is built by combing connectivity constraints and the coplanarity constraints are combined to construct the smoothness term. Finally, the global energy function can be built by combining the data term and the smoothness term. We rewrite the global energy function in a quadratic matrix function, and use least square methods to obtain the optimal solution. Experiments on Adirondack stereo and Motorcycle stereo of Middlebury benchmark show that the proposed method can remove fronto-parallel bias effectively, and produce continuous smooth surfaces. © Authors 2017.

关键词： 3D Label Algorithm Fronto-parallel Bias Global Optimization Matrix Energy Function Patch Matching

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xue, Dongmei Ma, Haichuan Li, Li Liu, Dong Xiong, Zhiwei The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the number of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy coding module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities;2) when adding a context module to remove signal redundancy further, aiWave can achieve a much better performance than HEVC. Copyright © 2022, The Authors. All rights reserved.

关键词： Image compression

Improved calibration method of the airborne polarimetric SAR

学校读者我要写书评

暂无评论

Improved calibration method of the airborne polarimetric SAR

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Feng Ming Jun Hong Lintao Zhang Institute of Electronics Chinese Academy of Sciences (CAS) Beijing China Graduate University of Chinese Academy of Sciences Beijing China Key Laboratory of Geo-spatial Information Processing and Application System Technology Chinese Academy of Sciences (CAS) Beijing China

The PolSAR system must be calibrated before obtain effective polarimetric information. The airplane attitude is unstable during the PolSAR measurement, which will impact the polarimetric calibration precision. This paper improved the polarimetric calibration method proposed by Whitt considering the impact of airplane attitude. The improved method is proved by polarimetric experiment using a PolSAR system developed by IEcas (Institute of electronics, Chinese Academy of Sciences).

关键词： Calibration Airplanes Mathematical model Equations Radar polarimetry Scattering

Detect Any Shadow: Segment Anything for Video Shadow Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yonghui Zhou, Wengang Mao, Yunyao Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Segment anything model (SAM) has achieved great success in the field of natural image segmentation. Nevertheless, SAM tends to consider shadows as background and therefore does not perform segmentation on them. In this paper, we propose ShadowSAM, a simple yet effective framework for fine-tuning SAM to detect shadows. Besides, by combining it with long short-term attention mechanism, we extend its capability for efficient video shadow detection. Specifically, we first fine-tune SAM on ViSha training dataset by utilizing the bounding boxes obtained from the ground truth shadow mask. Then during the inference stage, we simulate user interaction by providing bounding boxes to detect a specific frame (e.g., the first frame). Subsequently, using the detected shadow mask as a prior, we employ a long short-term network to learn spatial correlations between distant frames and temporal consistency between adjacent frames, thereby achieving precise shadow information propagation across video frames. Extensive experimental results demonstrate the effectiveness of our method, with notable margin over the state-of-the-art approaches in terms of MAE and IoU metrics. Moreover, our method exhibits accelerated inference speed compared to previous video shadow detection approaches, validating the effectiveness and efficiency of our method. The source code is now publicly available at https://***/harrytea/Detect-AnyShadow. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yonghui Zhou, Wengang Feng, Hao Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Over the past few years, the advancement of Multimodal Large Language Models (MLLMs) has captured the wide interest of researchers, leading to numerous innovations to enhance MLLMs’ comprehension. In this paper, we present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We hypothesize that the requisite number of visual tokens for the model is contingent upon both the resolution and content of the input image. Generally, natural images with a lower information density can be effectively interpreted by the model using fewer visual tokens at reduced resolutions. In contrast, images containing textual content, such as documents with rich text, necessitate a higher number of visual tokens for accurate text interpretation due to their higher information density. Building on this insight, we devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. This method mitigates distortion effects that arise from resizing images to a uniform resolution and dynamically optimizing the visual tokens input to the LLMs. Our model is capable of processing images with resolutions up to 1008 × 1008. Extensive experiments across various datasets demonstrate that our method achieves impressive performance in handling vision-language tasks in both natural and text-related scenes. The source code and dataset are now publicly available at https://***/harrytea/AdaptVision. Copyright © 2024, The Authors. All rights reserved.

关键词： Modeling languages

A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with applications in Tomographic SAR Imaging

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Ruizhe Zhang, Zhe Qiu, Xiaolan Ding, Chibiao School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China Suzhou Aerospace Information Research Institute Suzhou Key Laboratory of Intelligent Aerospace Big Data Application Technology Jiangsu Suzhou215123 China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing100190 China

This paper presents a novel efficient method for gridless line spectrum estimation problem with single snapshot, namely the gradient descent least squares (GDLS) method. Conventional single snapshot (a.k.a. single measure vector or SMV) line spectrum estimation methods either rely on smoothing techniques that sacrifice the array aperture, or adopt the sparsity constraint and utilize compressed sensing (CS) method by defining prior grids and resulting in the off-grid problem. Recently emerged atomic norm minimization (ANM) methods achieved gridless SMV line spectrum estimation, but its computational complexity is extremely high;thus it is practically infeasible in real applications with large problem scales. Our proposed GDLS method reformulates the line spectrum estimations problem into a least squares (LS) estimation problem and solves the corresponding objective function via gradient descent algorithm in an iterative fashion with efficiency. The convergence guarantee, computational complexity, as well as performance analysis are discussed in this paper. Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e.g., CS and ANM, in terms of estimation performances. It can completely avoid the off-grid problem, and its computational complexity is significantly lower than ANM. Our method has been tested in tomographic SAR (TomoSAR) imaging applications via simulated and real experiment data. Results show great potential of the proposed method in terms of better cloud point performance and eliminating the gridding effect. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectrum analysis

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation & Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https: ACM ISBN 978-1-4503-2138-9. Copyright © 2019, The Authors. All rights reserved.

关键词： Image recognition