检索结果-内蒙古大学图书馆

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...

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Feiyu Qin Lumeng Cao Xuejin 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)9781728123455

ISBN: (纸本)9781728123462

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.

关键词：

Deep Scalable Image Compression via Hierarchical Feature Decorrelation

学校读者我要写书评

暂无评论

Deep Scalable Image Compression via Hierarchical Feature Dec...

Picture Coding Symposium, PCS

作者： Zongyu Guo Zhizheng Zhang Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

The following topics are dealt with: video coding; data compression; image coding; convolutional neural nets; decoding; learning (artificial intelligence); motion compensation; video codecs; image reconstruction; filt...

关键词：

InSAR DEM Reconstruction Based on Backprojection Algorithm in Two Converse Flights 6

学校读者我要写书评

暂无评论

InSAR DEM Reconstruction Based on Backprojection Algorithm i...

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Hu, Xiaoning Xiang, Maosheng Wang, Bingnan Fu, Xikai University of Chinese Academy of Sciences National Key Laboratory of Science and Technology on Microwave Imaging Institute of Electronics Chinese Academy of Sciences Beijing100190 China National Key Laboratory of Science and Technology on Microwave Imaging Institute of Electronics Chinese Academy of Sciences Beijing100190 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781728129129

Interferometric synthetic aperture radar (InSAR) can be used to extract digital elevation model (DEM) with high accuracy. However, the side looking geometry of synthetic aperture radar (SAR) may cause geometric distortions such as shadow and layover in the mountainous terrain, which will reduce the quality of generated DEM. Fusion of two or more different aspects of InSAR data can deal with this problem. We propose an InSAR DEM reconstruction method based on backprojection (BP) algorithm in two converse flights. This method utilizes the feature of BP algorithm that geocoding has been realized in imaging process to simplify the fusion process of multi-aspect InSAR data. In addition, an iterative DEM extraction method is introduced to improve DEM accuracy. Experimental results verify the effectiveness of the proposed method. © 2019 IEEE.

关键词： Synthetic aperture radar

A coarse-to-fine framework for learned color enhancement with non-local attention

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shan, Chaowei Zhang, Zhizheng Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Automatic color enhancement is aimed to adaptively adjust photos to expected styles and tones. For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously. To address this problem, we propose a coarse-tofine framework with non-local attention for color enhancement in this paper. Within our framework, we propose to divide enhancement process into channel-wise enhancement and pixel-wise refinement performed by two cascaded Convolutional Neural Networks (CNNs). In channel-wise enhancement, our model predicts a global linear mapping for RGB channels of input images to perform global style adjustment. In pixel-wise refinement, we learn a refining mapping using residual learning for local adjustment. Further, we adopt a non-local attention block to capture the long-range dependencies from global information for subsequent fine-grained local refinement. We evaluate our proposed framework on the commonly using benchmark and conduct sufficient experiments to demonstrate each technical component within it. Copyright © 2019, The Authors. All rights reserved.

关键词： Pixels

No-reference light field image quality assessment based on micro-lens image

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Luo, Ziyuan Zhou, Wei Shi, Likun Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Light field image quality assessment (LF-IQA) plays a significant role due to its guidance to Light Field (LF) contents acquisition, processing and application. The LF can be represented as 4-D signal, and its quality depends on both angular consistency and spatial quality. However, few existing LF-IQA methods concentrate on effects caused by angular inconsistency. Especially, no-reference methods lack effective utilization of 2-D angular information. In this paper, we focus on measuring the 2-D angular consistency for LF-IQA. The Micro-Lens Image (MLI) refers to the angular domain of the LF image, which can simultaneously record the angular information in both horizontal and vertical directions. Since the MLI contains 2-D angular information, we propose a No-Reference Light Field image Quality assessment model based on MLI (LF-QMLI). Specifically, we first utilize Global Entropy Distribution (GED) and Uniform Local Binary Pattern descriptor (ULBP) to extract features from the MLI, and then pool them together to measure angular consistency. In addition, the information entropy of Sub-Aperture Image (SAI) is adopted to measure spatial quality. Extensive experimental results show that LF-QMLI achieves the state-of-the-art performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Image quality

RC-CNN: Representation-Consistent Convolutional Neural Networks for Achieving Transformation Invariance

学校读者我要写书评

暂无评论

RC-CNN: Representation-Consistent Convolutional Neural Netwo...

IEEE International Conference on systems, Man and Cybernetics

作者： Jun Gu Anfeng He Xinmei Tian CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China

Convolutional neural networks (CNNs) are powerful and have achieved state-of-the-art performance in many visual recognition tasks. Despite their impressive performance, CNNs are still unable to remain invariant while some spatial transformations are applied on images. Herein, we propose representation-consistent neural networks to solve this problem. By introducing consistent losses between the representations in different layers of transformed images, the recognition performance of transformed images is significantly improved. This model not only learns to map from the transformed images to the pre-defined labels but each layer also learns to generate invariant representations when the input images are transformed. All the characteristics of transformation invariance are embedded in the model, which means that no extra parameters or computations are introduced in the well-trained model. Comparative experiments demonstrate the superiority of our model when learning invariance to rotation, translation, and scaling on large-scale image recognition and retrieval tasks.

关键词： Computational modeling Feature extraction Training Image recognition Data models Task analysis Kernel

Learned fast HEVC intra coding

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Zhibo Shi, Jun Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

In High Efficiency Video Coding (HEVC), excellent rate-distortion (RD) performance is achieved in part by having a flexible quadtree coding unit (CU) partition and a large number of intra-prediction modes. Such an excellent RD performance is achieved at the expense of much higher computational complexity. In this paper, we propose a learned fast HEVC intra coding (LFHI) framework taking into account the comprehensive factors of fast intra coding to reach an improved configurable tradeoff between coding performance and computational complexity. First, we design a low-complex shallow asymmetric-kernel CNN (AK-CNN) to efficiently extract the local directional texture features of each block for both fast CU partition and fast intra-mode decision. Second, we introduce the concept of the minimum number of RDO candidates (MNRC) into fast mode decision, which utilizes AK-CNN to predict the minimum number of best candidates for RDO calculation to further reduce the computation of intra-mode selection. Third, an evolution optimized threshold decision (EOTD) scheme is designed to achieve configurable complexity-efficiency tradeoffs. Finally, we propose an interpolation-based prediction scheme that allows for our framework to be generalized to all quantization parameters (QPs) without the need for training the network on each QP. The experimental results demonstrate that the LFHI framework has a high degree of parallelism and achieves a much better complexity-efficiency tradeoff, achieving up to 75.2% intra-mode encoding complexity reduction with negligible rate-distortion performance degradation, superior to the existing fast intra-coding schemes. Copyright © 2019, The Authors. All rights reserved.

关键词： Signal distortion

3D reconstruction and error analysis of multi-view space-borne SAR images under different configurations

学校读者我要写书评

暂无评论

3D reconstruction and error analysis of multi-view space-bor...

IET International Radar Conference 2018, IRC 2018

作者： Wang, Chao Qiu, Xiaolan Li, Fangfang Lei, Bin University of the Chinese Academy of Sciences Beijing China Institute of Electrics Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electrics Chinese Academy of Sciences Beijing China

Synthetic aperture radar (SAR) has a good ability to detect the microwave scattering characteristics of the target and has a good capability of slant range Doppler positioning. Using multi-view SAR images in combination with image matching and positioning equations, the 3D position of the target can be obtained. In the past, multi-view 3D reconstruction mainly used side-looking images with parallel trajectories but different incident angles. That method is not universal for different configurations and lacks analysis of the relationship between solution and parameter error. This study aims at the problem of multi-view SAR 3D reconstruction. The authors establish general 3D reconstruction equations that can be used for non-parallel track and non-side-looking and the solution method is deduced. Based on this, an analysis method of error sensitivity is proposed and the dependence relationship between the reconstruction error and configuration, velocity, position, and slant range is analysed. The correctness of this method is verified by simulation experiments, which provides guidance for selection of configuration and sensor accuracy when applying 3D reconstruction. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

Deep learning-based video coding: A review and a case study

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Dong Li, Yue Lin, Jianping 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 China

The past decade has witnessed great success of deep learning technology in many disciplines, especially in computer vision and image processing. However, deep learning-based video coding remains in its infancy. This paper reviews the representative works about using deep learning for image/video coding, which has been an actively developing research area since the year of 2015. We divide the related works into two categories: new coding schemes that are built primarily upon deep networks (deep schemes), and deep network-based coding tools (deep tools) that shall be used within traditional coding schemes or together with traditional coding tools. For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively. For deep tools, there have been several proposed techniques using deep learning to perform intra-picture prediction, inter-picture prediction, cross-channel prediction, probability distribution prediction, transform, post- or in-loop filtering, down- and up-sampling, as well as encoding optimizations. According to the newest reports, deep schemes have achieved comparable or even higher compression efficiency than the state-of-the-art traditional schemes, such as High Efficiency Video Coding (HEVC) based scheme, for image coding;deep tools have demonstrated the compression capability beyond HEVC for video coding. However, deep schemes have not yet reached the current height of HEVC for video coding, and deep tools remain largely unexplored at many aspects including the tradeoff between compression efficiency and encoding/decoding complexity, the optimization for perceptual naturalness or semantic quality, the speciality and universality, the federated design of multiple deep tools, and so on. In the hope of advocating the research of deep learning-based video coding, we present a case study of our developed prototype video codec, namely Deep Learning Vi

关键词： Video signal processing