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

Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Zexi Chen, Xiaoming Wing, Henry Yeung, Fung Chung, Yuk Ying Chen, Zhibo School of Computer Science University of Sydney Australia School of Computer Science and Engineering Beijing Technology and Business University China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China China

Despite the recent progress in light field super-resolution (LFSR) achieved by convolutional neural networks, the correlation information of light field (LF) images has not been sufficiently studied and exploited due to the complexity of 4D LF data. To cope with such high-dimensional LF data, most of the existing LFSR methods resorted to decomposing it into lower dimensions and subsequently performing optimization on the decomposed sub-spaces. However, these methods are inherently limited as they neglected the characteristics of the decomposition operations and only utilized a limited set of LF sub-spaces ending up failing to sufficiently extract spatio-angular features and leading to a performance bottleneck. To overcome these limitations, in this paper, we comprehensively discover the potentials of LF decomposition and propose a novel concept of decomposition kernels. In particular, we systematically unify the decomposition operations of various sub-spaces into a series of such decomposition kernels, which are incorporated into our proposed Decomposition Kernel Network (DKNet) for comprehensive spatio-angular feature extraction. The proposed DKNet is experimentally verified to achieve considerable improvements compared with the state-of-the-art methods. To further improve DKNet in producing more visually pleasing LFSR results, based on the VGG network, we propose a LFVGG loss to guide the Texture-Enhanced DKNet (TE-DKNet) to generate rich authentic textures and enhance LF images’ visual quality significantly. We also propose an indirect evaluation metric by taking advantage of LF material recognition to objectively assess the perceptual enhancement brought by the LFVGG loss. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical resolving power

3D Point Cloud Reconstruction of Vehicle using Inversely Mapping and Voting from CSAR Images

学校读者我要写书评

暂无评论

3D Point Cloud Reconstruction of Vehicle using Inversely Map...

IEEE International Conference on Radar

作者： Shanshan Feng Yun Lin Fei Teng Wen Hong Key Laboratory of Technology in Geospatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences University of Chinese Academy of Sciences Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Information Engineering North China University of Technology Beijing China

ISBN: (纸本)9781665468893

3D reconstruction of object has raised much interest in the field of SAR. The feature of target at multi aspect angles can be obtained from sub-aperture images provided by circular SAR(CSAR), which is conducive to 3D reconstruction. Radargrammetric method is a conventional way to extract DEM while its performance for 3D reconstruction is limited by the image registration. It is difficult to find corresponding points in different sub-aperture images. In this paper, we proposed a method for 3D reconstruction of vehicle based on projections in sub-aperture images. According to the imaging mechanism of CSAR, different targets located on the same iso-range line in the zero doppler plane fall into the same cell. For a projection point, given a series of offsets, the projection point will be mapped inversely to the 3D mesh along the iso-range line. We can obtain candidates of the target. The intersection of iso-range lines can be regarded as voting process. For a candidate, the more times of intersection, the higher the number of votes, and the candidate point will be reserved. This fully excavates the information contained in the angle dimension of CSAR. The proposed approach is verified by the Gotcha Volumetric SAR Data Set.

关键词： Point cloud compression Space vehicles Image registration Three-dimensional displays Imaging Radar imaging Feature extraction

MSight: An Edge-Cloud Infrastructure-based Perception system for Connected Automated Vehicles

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Rusheng Meng, Depu Shen, Shengyin Zou, Zhengxia Li, Houqiang Liu, Henry X. The Department of Civil and Environmental Engineering University of Michigan Ann ArborMI48109 United States The University of Michigan Transportation Research Institude 2901 Baxer Rd Ann ArborMI48109 United States The Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China 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 Hefei China Mcity University of Michigan Ann ArborMI48109 United States

As vehicular communication and networking technologies continue to advance, infrastructure-based roadside perception emerges as a pivotal tool for connected automated vehicle (CAV) applications. Due to their elevated positioning, roadside sensors, including cameras and lidars, often enjoy unobstructed views with diminished object occlusion. This provides them a distinct advantage over onboard perception, enabling more robust and accurate detection of road objects. This paper presents MSight, a cutting-edge roadside perception system specifically designed for CAVs. MSight offers real-time vehicle detection, localization, tracking, and short-term trajectory prediction. Evaluations underscore the system’s capability to uphold lane-level accuracy with minimal latency, revealing a range of potential applications to enhance CAV safety and efficiency. Presently, MSight operates 24/7 at a two-lane roundabout in the City of Ann Arbor, Michigan. Copyright © 2023, The Authors. All rights reserved.

关键词： Roadsides

Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics

学校读者我要写书评

暂无评论

Reinforced Bit Allocation under Task-Driven Semantic Distort...

IEEE International Symposium on Circuits and systems (IScas)

作者： Jun Shi Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc. Some learning-based frameworks have been proposed for this purpose due to their inherent end-to-end optimization mechanisms. However, it is still quite challenging to integrate these task-driven metrics seamlessly into traditional hybrid coding framework. To the best of our knowledge, this paper is the first work trying to solve this challenge based on reinforcement learning (RL) approach. Specifically, we formulate the bit allocation problem as a Markovian Decision Process (MDP) and train RL agents to automatically decide the quantization parameter (QP) of each coding tree unit (CTU) for HEVC intra coding, according to the task-driven semantic distortion metrics. This bit allocation scheme can maximize the semantic level fidelity of the task, such as classification accuracy, while minimizing the bit-rate. We also employ gradient class activation map (Grad-CAM) and Mask R-CNN tools to extract task-related importance maps to help the agents make decisions. Extensive experimental results demonstrate the superior performance of our approach by achieving 43.1% to 73.2% bit-rate saving over the anchor of HEVC under the equivalent task-related distortions.

关键词： Task analysis Distortion Bit rate Image coding Semantics Encoding

Human Machine Joint Decision Making in Distorted Surveillance Scenario 2

学校读者我要写书评

暂无评论

Human Machine Joint Decision Making in Distorted Surveillanc...

2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Liu, Sen Zhao, Shuxin Pang, Yingxue Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728140919

There is plenty of human-machine joint decision-making scenarios in the real world applications, such as driving assistant, suspect identification, medical diagnosis, etc. Existing algorithms propose that machine should give a rejection option when having a high risk or uncertainty score so that the input can be passed to human to make the decision. This is an interesting algorithmic model of human-machine collaboration, but implicitly assumes that humans are more trustworthy than machines. Such an assumption ignores the bias and inconsistency of human, especially in scenarios where machines have superior recognition ability than humans. In this work, we investigate the human-machine joint decision-making problem in distorted surveillance videos, where machines experimentally prove to be comparable to human beings in tolerance to distortion, sometimes even stronger. We propose a new human-machine joint decision-making framework by considering both the confidences of machine and human. To obtain the confidence of human, we build a real-life human decision-making database and propose a deep neural network to estimate human's confidence. Then, confidence alignment method and decision rule are proposed to further output the final decision. Experiments demonstrate that the proposed framework can make less human intervention and more accurate decisions in several human-machine joint decision-making scenarios. © 2019 IEEE.

关键词： Deep neural networks

Deep Local and Global Spatiotemporal Feature Aggregation for Blind Video Quality Assessment

学校读者我要写书评

暂无评论

Deep Local and Global Spatiotemporal Feature Aggregation for...

IEEE Visual Communications and Image processing (VCIP)

作者： Wei Zhou Zhibo Chen CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In recent years, deep learning has achieved promising success for multimedia quality assessment, especially for image quality assessment (IQA). However, since there exist more complex temporal characteristics in videos, very little work has been done on video quality assessment (VQA) by exploiting powerful deep convolutional neural networks (DCNNs). In this paper, we propose an efficient VQA method named Deep SpatioTemporal video Quality assessor (DeepSTQ) to predict the perceptual quality of various distorted videos in a no-reference manner. In the proposed DeepSTQ, we first extract local and global spatiotemporal features by pre-trained deep learning models without fine-tuning or training from scratch. The composited features consider distorted video frames as well as frame difference maps from both global and local views. Then, the feature aggregation is conducted by the regression model to predict the perceptual video quality. Finally, experimental results demonstrate that our proposed DeepSTQ outperforms state-of-the-art quality assessment algorithms.

关键词： Quality assessment Video recording Feature extraction Spatiotemporal phenomena Databases Indexes Deep learning

M-LVC: Multiple frames prediction for learned video compression

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lin, Jianping Liu, Dong Li, Houqiang Wu, Feng Cas Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respec-tively. To compensate for the compression error of the autoencoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple ref-erence frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss func-tion. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available. Copyright © 2020, The Authors. All rights reserved.

关键词： Image compression

Improving Semantic Segmentation via Label Propagation and Temporal Consistency

学校读者我要写书评

暂无评论

Improving Semantic Segmentation via Label Propagation and Te...

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Qin, Feiyu Cao, Lumeng Chen, Xuejin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728123455

Semantic segmentation is a fundamental task in indoor scene understanding. Most previous supervised approaches rely on densely annotated image data sets. Due to the limited amount of images with segmentation labels, the performance of existing networks is greatly limited. In this paper, we exploit temporal correlation in video frames to improve the performance and robustness of segmentation networks. Two effective learning strategies are proposed to propagate the information from a few labeled frames to their immediate neighbor frames. First, we scale up training dataset for supervised semantic segmentation networks by generating pseudo ground-truth for neighboring frames from a labeled frame using filtered homography transformation. Furthermore, we introduce a self-supervised loss function to ensure temporal consistency between the segmentation results of adjacent frames. The experimental results demonstrate that our proposed method outperforms state-of-the-art techniques for semantic segmentation on NYU-Depth V2 dataset. © 2019 IEEE.

关键词： Semantic Segmentation