检索结果-内蒙古大学图书馆

End-to-End Facial Image Compression with Integrated Semantic Distortion Metric

学校读者我要写书评

暂无评论

End-to-End Facial Image Compression with Integrated Semantic...

IEEE Visual Communications and Image processing (VCIP)

作者： Tianyu He 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: (纸本)9781538644591;9781538644584

High efficient facial image compression is broadly required and challenging for surveillance and security scenarios, while either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose an End-to-End Facial Image Compression (E2EFIC) framework with a novel variable block size Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated semantic distortion metrics, including a successful exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework's efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate E2EFIC's superior performance gain compared with latest specific facial image codecs.

关键词： Image coding Distortion Semantics Face Bit rate Codecs

Learning based Facial Image Compression with Semantic Fidelity Metric

学校读者我要写书评

暂无评论

arXiv 2018年

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

Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose a Learning based Facial Image Compression (LFIC) framework with a novel Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated hybrid semantic fidelity metric, including a successfully exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework’s efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate LFIC’s superior performance gain compared with latest specific facial image codecs. Visual experiments also show some interesting insight on how LFIC can automatically capture the information in critical areas based on semantic distortion metrics for optimized compression, which is quite different from the heuristic way of optimization in traditional image compression algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression

Corrigendum to “Introducing a Chaotic Component in the Control System of Soil Respiration”

学校读者我要写书评

暂无评论

Complexity 2022年第1期2022卷

作者： Peng An Wen-Feng Wang Xi Chen Jing Qian Yunzhu Pan Laboratory of Pattern Analysis and Machine Intelligence School of Electronic and Information Engineering Ningbo University of Technology Ningbo 315211 *** Research Institute of Intelligent Engineering and Data Applications School of Electronic and Electrical Engineering Shanghai Institute of Technology Shanghai 200235 *** State Key Laboratory of Desert and Oasis Ecology Xinjiang Institute of Ecology and Geography Chinese Academy of Sciences Urumqi 830011 *** University of Chinese Academy of Sciences Beijing 100049 *** Sino-Belgian Joint Laboratory of Geo-information Urumqi 830011 China CAS Research Centre for Ecology and Environment of Central Asia Urumqi 830011 *** Center for Geo-Spatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 *** School of Management Cranfield University Cranfield MK43 0AL UKcranfield.ac.uk

Learning for video compression

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Chen, Zhibo He, Tianyu Jin, Xin Wu, Feng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experimental results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning-based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression

Parameter prediction method of SAR target simulation based on convolutional neural networks 12

学校读者我要写书评

暂无评论

Parameter prediction method of SAR target simulation based o...

12th European Conference on Synthetic Aperture Radar, EUSAR 2018

作者： Shengren, Niu Xiaolan, Qiu Lingxiao, Peng Bin, Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute ofElectronics Chinese Academy of Sciences University of Chinese Academy of Sciences China Suzhou Institute Institute of Electronics Chinese Academy of Sciences China

ISBN: (纸本)9783800746361

SAR image simulation plays a useful role in SAR target interpretation and recognition. The current SAR target simulation methods require high precision of models and simulation parameters, and are only forward processes which lack the feedback adjustment of real image. In this paper, a method of predicting simulation parameters from real images is proposed, which is based on convolutional neural networks(CNN). The architecture and the loss function of the CNN are modified to obtain better performance of the parameter inversion. From the simulation results, the predicted parameters improve the similarity between the simulation images and the real images. © VDE VERLAG GMBH Â Berlin Â Offenbach.

关键词： Synthetic aperture radar

InSAR DEM Reconstruction Based on Backprojection Algorithm in Two Converse Flights

学校读者我要写书评

暂无评论

InSAR DEM Reconstruction Based on Backprojection Algorithm i...

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

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

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

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.

关键词：

Towards a better match in siamese network based visual object tracker

学校读者我要写书评

暂无评论

arXiv 2018年

作者： He, Anfeng Luo, Chong Tian, Xinmei Zeng, Wenjun CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China Microsoft Research Beijing China

Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limitations. First, it cannot properly handle large object rotation. Second, tracking gets easily distracted when the background contains salient objects. In this paper, we propose two simple yet effective mechanisms, namely angle estimation and spatial masking, to address these issues. The objective is to extract more representative features so that a better match can be obtained between the same object from different frames. The resulting tracker, named Siam-BM, not only significantly improves the tracking performance, but more importantly maintains the realtime capability. Evaluations on the VOT2017 dataset show that Siam-BM achieves an EAO of 0.335, which makes it the best-performing realtime tracker to date. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

COOPERATIVE HYBRID DIGITAL-ANALOG VIDEO TRANSMISSION IN D2D NETWORKS

学校读者我要写书评

暂无评论

COOPERATIVE HYBRID DIGITAL-ANALOG VIDEO TRANSMISSION IN D2D ...

IEEE International Conference on Image processing

作者： Jian Shen Fei Liang Chong Luo Houqiang Li Wenjun Zeng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China

In this paper, we propose a cooperative video transmission scheme in D2D networks. This research is motivated by the growing interests in hybrid digital-analog video transmissions and device-to-device (D2D) communications. The framework of D2D communications can be generally modeled as a three-node network. In this network, coset coding is used to allow the destination to exploit the correlations between the video signals received in two phases. We have done some work of further optimization to improve the video quality at destination in this network. First, we derive a closed form of the reconstruction error at the destination. This provides a theoretical foundation for finding the optimal quantization step size in coset coding. Then, based on the accurate analysis on the coset coding we design a new power allocation algorithm. Experimental results verify that our scheme outperforms the recently proposed WCVC and DCVC.

关键词： Encoding Resource management Relays Distortion Quantization (signal) Device-to-device communication Decoding

A twofold siamese network for real-time object tracking

学校读者我要写书评

暂无评论

arXiv 2018年

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC [3] allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics