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

Recurrent Generic Contour-based Instance Segmentation with Progressive Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Hao Zhou, keyi Zhou, Wengang Yin, Yufei Deng, Jiajun Sun, Qi Li, Houqiang 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 University of Adelaide Australian Institute for Machine Learning Australia

Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance with an iterative and progressive contour refinement strategy. Technically, PolySnake introduces a recurrent update operator to estimate the object contour iteratively. It maintains a single estimate of the contour that is progressively deformed toward the object boundary. At each iteration, PolySnake builds a semantic-rich representation for the current contour and feeds it to the recurrent operator for further contour adjustment. Through the iterative refinements, the contour progressively converges to a stable status that tightly encloses the object instance. Beyond the scope of general instance segmentation, extensive experiments are conducted to validate the effectiveness and generalizability of our PolySnake in two additional specific task scenarios, including scene text detection and lane detection. The results demonstrate that the proposed PolySnake outperforms the existing advanced methods on several multiple prevalent benchmarks across the three tasks. The codes and pre-trained models are available at https://***/fh2019ustc/PolySnake Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

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

A Novel Reconstruction Filter for the Azimuth Multi-Channel SAR

学校读者我要写书评

暂无评论

A Novel Reconstruction Filter for the Azimuth Multi-Channel ...

IEEE International Conference on Radar

作者： Mingyang Shang Xiaolan Qiu Junying Yang Lihua Zhong Yu Xin Chibiao Ding Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Aerospace Information Research Institute Chinese Academic of Sciences Beijing China Beijing Institute of Remote Sensing Information Beijing China

ISBN: (纸本)9781665468893

The compensation of channel imbalances plays a vital role in signal processing of the azimuth multi-channel (AMC) synthetic aperture radar (SAR). In the operational AMC SAR system, the channel imbalance is usually considered to be a constant in both the time and frequency domain for one image. However, since the antenna patterns of all channels cannot be strictly consistent, the channel imbalances may vary with the Doppler frequency. This paper establishes the signal model of AMC SAR with channel imbalances changing with Doppler frequency and proposes a novel compensation method during the reconstruction for the echo signals received by all channels. This method has been verified by simulations and real data acquired by Gaofen-3 (GF-3). The result shows that this method has excellent potential for improving the image quality for AMC SAR.

关键词： Image quality Antenna measurements Azimuth Filter banks Receiving antennas Channel estimation Signal processing

Model selection for high resolution InSAR coherence statistics over urban areas and its application in building detection

学校读者我要写书评

暂无评论

Model selection for high resolution InSAR coherence statisti...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Yue Zhang Xian Sun Wenhui Diao Chenyuan Wang Guangluan Xu Hongqi Wang Institute of Electronic Chinese Academy of Sciences Beijing China Key Laboratory of Spatial Information Processing and Application System Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781509033331

The interferometric coherence map is derived from the cross-correlation of two registered synthetic aperture radar (SAR) images. It can give additional information complementary to the intensity image, or act as an independent information source in many applications. Compared to the plenty of work on SAR intensity statistics, there are quite fewer researches on the statistical characters of interferometric SAR (InSAR) coherence. And to our knowledge, all of the existing work that related to InSAR coherence statistics, models the coherence with Gaussian distribution with no discrimination on data resolutions or scene types. Our main contribution is the investigation on the accuracies of several typical models for high resolution coherence statistics over urban areas. We select three typical land classes including trees, buildings, and shadow, as the representatives of urban areas. And different models including Gaussian, Weibull, Rayleigh, Nakagami and Beta are evaluated. Experiment results on TanDEM-X data illustrate that the Beta model reveals a better performance than other distributions. Finally, the Beta model is used in the detection of buildings.

关键词： Coherence Buildings Synthetic aperture radar Urban areas Probability density function Data models Nakagami distribution

A new method for attitude refinement of earth observation satellite with asynchronous images

学校读者我要写书评

暂无评论

A new method for attitude refinement of earth observation sa...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Tao Sun Li Huang Hui Long Bao-Cheng Liu Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing P. R. China TH-Centre of China Beijing P. R. China

The accuracy of attitude observation is always the main contributor to geometric performance of earth observation satellites (EOSs). Given the ground process requirement, linear pushbroom and asynchronous imaging sensors are widely used in EOSs, such as multispectral sensor with sequential line arrays, three-line array sensor in stereo mapping satellite, panchromatic sensor with multiple non-collinear CCD chip in some high-resolution optical satellite. By using the images of those sensors, this paper proposes a method, which is based on image registration approach, rigorous forward intersection and bundle adjustment technology, to refine attitude data of satellite for improving geometric performance of images. Preliminary experiments, which used multi-sensors asynchronous images of Chinese Mapping Satellite-1-02, demonstrate that the proposed method is capable of improving internally coincident precision of attitude data without ground control points. In particular, relative positioning accuracy of images can be directly improved, and absolute positioning accuracy can consequently be improved via additionally using a few GCPs in the stripe image data.

关键词： Satellites Sensor arrays Calibration Mathematical model Remote sensing Image sensors

Two-Step Bistatic Spaceborne Sliding-Spotlight SAR Imaging Agorithm Based on Accurate Range Model

学校读者我要写书评

暂无评论

Two-Step Bistatic Spaceborne Sliding-Spotlight SAR Imaging A...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Jianbing Xiang Xiaolei Lv Xikai Fu Ye Yun University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

The slant range errors caused by traditional hyperbolic range equation (THRE) with stop-and-go assumption will lead to image defocusing in high resolution spaceborne sliding-spotlight Bistatic SAR system (ST-BiSAR). In this paper, an accurate bistatic slant range model based on uniform acceleration curve motion (UARM) is proposed, which is precisely fitted with the actual range history. Then, a two-step imaging algorithm based on UARM and method of reversion series (MSR) is introduced to eliminate aliasing phenomenon and realize focus. Finally, simulation results verify the correctness and effectives of the proposed range model and imaging algorithms.

关键词： Mathematical model Imaging Satellites Synthetic aperture radar Acceleration Manganese Azimuth

HIGH RESOLUTION SAR IMAGE CLASSIFICATION WITH DEEPER CONVOLUTIONAL NEURAL NETWORK

学校读者我要写书评

暂无评论

HIGH RESOLUTION SAR IMAGE CLASSIFICATION WITH DEEPER CONVOLU...

IEEE International geoscience and Remote Sensing Symposium

作者： Yue Zhang Xian Sun Hao Sun Zequn Zhang Wenhui Diao Kun Fu Key Laboratory of Spatial Information Processing and Application System Technology Chinese Academy of Sciences Beijing China Institute of Electronic Chinese Academy of Sciences Beijing China

Deeper architectures are proven to be beneficial for the classification performance obviously in computer vision field. Inspired by this, deep CNNs are expected to make progress in the SAR target classification problem as well. However, it is hard to train deeper CNNs for SAR images. Such CNNs have millions of parameters to be determined in the network (for example the VGGNet has more than 130 million parameters), hence large-scale dataset is indispensable when training a deep CNN. But there is no large-scale annotated SAR target dataset, and data acquisition and annotation is much more costly for SAR images. With inadequate data, the network is easy to be overfitting. Several methods based on deep learning have been proposed for SAR image classifications, but they cannot get rid of the aforementioned data limitation of labelled SAR images. To solve this problem, this paper proposes a microarchitecture called CompressUnit (CU). With CU, we design a deeper CNN. Compared with the network with the fewest parameters for SAR image classification in literature so far, our network is 2X deeper with only about 10% of parameters. In this way, we get a deeper network with much fewer parameters. This network is easier to be trained with limited SAR data and is more likely to get rid of overfitting.

关键词： Deeper CNN SAR images CompressUnit

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