检索结果-内蒙古大学图书馆

Joint vehicle detection and distance prediction via monocular depth estimation

IET INTELLIGENT TRANSPORT SYSTEMS 2020年第7期14卷 753-763页

作者： Shen, Chao Zhao, Xiangmo Liu, Zhanwen Gao, Tao Xu, Jiang Changan Univ Sch Informat Engn Xian 710064 Shaanxi Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China Univ Calif Berkeley Inst Transportat Studies Berkeley CA 94720 USA

Vehicle detection and distance estimation are critical components of driver assistance system and self-driving system, and considerable different frameworks have been investigated such as radar, laser and camera-based. Among them, camera-based vehicle detection and distance estimation have an obvious advantage over other systems in that it needs lower cost. However, existing camera-based methods are not robust enough under complex driving scenes. In this work, an end-to-end deep convolutional neural network framework is proposed to jointly detect vehicles and estimate vehicle distance efficiently. Specifically, a monocular depth estimation method is designed to transform the RGB appearance information into depth modality information. then the vehicle detection module takes the RGB and depth image as inputs to improve the detection performance. Finally, the distance estimation module employs the detection results and the estimated depth information to predict the distance more precisely. the whole network can be trained in an end-to-end manner with the multi-task loss function. the proposed framework is evaluated on the public vehicle detection benchmark KITTI to show the effectiveness of the proposed framework. Moreover, the performance of three proposed sub-modules are also analysed separately to give a more comprehensive evaluation of the designed framework.

关键词： computer vision traffic engineering computing driver information systems object detection image sensors image colour analysis road vehicles cameras convolutional neural nets joint vehicle detection critical components driver assistance system self-driving system camera-based vehicle detection complex driving scenes end-to-end deep convolutional neural network framework vehicle distance monocular depth estimation method RGB appearance information depth modality information vehicle detection module depth image detection performance distance estimation module estimated depth information public vehicle detection benchmark KITTI

来源：评论

学校读者我要写书评

暂无评论

Recovering Cloud Services Using Hybrid Clouds Under Power Outage 15th

Recovering Cloud Services Using Hybrid Clouds Under Power Ou...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Xia, Yu Xu, Xueyong Wang, Wanyuan He, Xiujun Wu, Weiwei Fang, Xiaolin School of Computer Science and Engineering Southeast University Nanjing China North Information Control Research Academy Group Co. Ltd Nanjing China

ISBN: (纸本)9783030642426

the rapid development of the Internet and cloud computing are giving people high quality online services, which are usually deployed in cloud data centers. While the clouds are not always failure-free, in case of a power failure in a cloud data center, it is important to reduce the cost of disaster recovery meanwhile ensuring cloud service performance. To solve the service recovery problem of cloud data center under a power outage, in this paper, we propose an online solution based on hybrid cloud framework, which resolves the service workload management optimization between private cloud and public one. By using Lyapunov optimization technology, the long-term online optimization problem can be transformed into a general one. Besides, we present a power-aware on-line control algorithm (POCA) which achieves a trade-off between power consumption and cost, and the simulation results show that the proposed POCA algorithm can give a better and efficient performance. © 2020, Springer Nature Switzerland AG.

关键词： Outages

来源：评论

学校读者我要写书评

暂无评论

Compiler optimizing for power efficiency of on-chip memory 13th

Compiler optimizing for power efficiency of on-chip memory

引用

13th Conference on Advanced computer architecture, ACA 2020

作者： Wu, Wei Zhu, Qi Wang, Fei Lin, Rong-Fen Qi, Feng-Bin Jiangnan Institute of Computing Technology Wuxi214083 China

ISBN: (纸本)9789811581342

As we all known, power constraint is the biggest challenge to build an exascale computing system. Among all parts of high performance processor, on-chip memory, including register, cache and so on, is accessed frequently and incurs high power consumption during program executing. Due to trivial overhead and good portability, compiling is a promising way to reduce power consumption and thermal dissipation of processor. In this paper, we focus on compiling to save power of on-chip memory access. A compiler optimizing on bypassing registers is proposed to reduce the number of register access in order to lower the power of the register files. Besides that, to save the power consumption of cache, another compiler optimizing is proposed to elegantly adjust loop transformation to make a better use of L0 cache. Finally, in order to evaluate the effectiveness of the above techniques, we build a systematic evaluation platform, named as GEAT, which consists of compiler, performance simulator and power simulator. Experiment results show that our proposed techniques can effectively reduce the power consumption of on-chip memory with trivial overhead of performance. © Springer Nature Singapore Pte Ltd 2020.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Host Bypassing: Direct Data Piping from the Network to the Hardware Accelerator

Host Bypassing: Direct Data Piping from the Network to the H...

引用

IEEE International symposium on Embedded Multicore Socs (MCSoC)

作者： Ralf Kundel Kadir Eryigit Jonas Markussen Carsten Griwodz Osama Abboud Rhaban Hark Ralf Steinmetz Multimedia Communications Lab Technical University of Darmstadt Germany Zoi TechCon GmbH Stuttgart Germany University of Oslo Norway Dolphin Interconnect Solutions AS Oslo Norway Huawei Technologies Munich Germany

ISBN: (纸本)9781728187525

computer networks have become very important and influential over the last years for many common services such as Internet connectivity as well as time-sensitive applications such as videotelephony. Furthermore, approaches like in-network computing enable the offloading of latency-critical and high-performance network functions into the network, e.g. 5G network functions, to enable such time-sensitive applications. In this work, we show how FPGAs in PCIe-based systems, which are typically used as hardware accelerators for latency-critical in-network functions, can be integrated into the data path. Our approach, named host bypassing, allows direct data transfer from the network interface to the accelerator and accomplishes substantial performance benefits over existing state-of-the-art approaches. Our detailed evaluation results demonstrate the possibility of achieving deterministic low latency while operating under heavy load without any packet loss. In addition, fewer CPU resources are required.

关键词： performance evaluation architecture Memory management Packet loss throughput Peer-to-peer computing Network interfaces

来源：评论

学校读者我要写书评

暂无评论

A Novel Ant Colony Optimization Algorithm with Dynamic Control Population for Community Detecting 15th

A Novel Ant Colony Optimization Algorithm with Dynamic Contr...

引用

15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft computing and Applications, ICHSA 2019

作者： Chen, Jianjun Gao, Shupeng Su, Zhen Chen, Siqi Li, Xianghua College of Computer and Information Science Southwest University Chongqing400715 China School of Mechanical Engineering Northwestern Polytechnical University Shanxi710072 China College of Intelligence and Computing Tianjin University Tianjin300072 China

ISBN: (纸本)9783030324551

Nowadays, complex networks have driven great interests of scholars. As a special characteristic of a network, the community structure has wide research prospects. Many current algorithms are adopted for detecting the potential community structure, in which the ant colony algorithm is a typical one. However, the computational cost of the ant colony is too high which limits its performance. In this paper, we propose a novel ant colony optimization algorithm with dynamic control population. In the proposed algorithm, when a certain condition is reached, the number of ants starts to decrease based on the proposed rules. the efficiency of the proposed algorithm is estimated through comparing with the classical ant colony algorithm in real-world networks. Experiments show that the proposed algorithm has apparently lower computational cost, while the quality of the division is reserved relatively. © Springer Nature Switzerland AG, 2020.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Neural Network architecture for LLR Computation in 5G Systems and Related Business Aspects

Neural Network Architecture for LLR Computation in 5G System...

引用

International symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Satya Kumar Vankayala Swaraj Kumar Konchady Gautam Shenoy D thirumulanathan Seungil Yoon Issaac Kommineni Networks S/W R&D Group Samsung R&D Institute Bengaluru India IISc Bengaluru India Indian Institute of Technology Kanpur India Network Business Samsung Electronics Suwon South Korea

ISBN: (纸本)9781665427616

Log likelihood ratio (LLR) computations are an integral part of the communication decoder design. Soft decoding, the most accurate method of computing LLR, is computationally very expensive. Industries are thus using approximations that are designed keeping in mind the hardware complexity involved in the optimization process. In this paper, we propose a neural network based computation scheme that is trained to mimic the performance of soft decoding with high accuracy. Besides training, we further reduce the computational complexity by disabling the weak edges in the neural network and by approximating the activation function. the degree to which the weak connections are disabled varies according to the quality of service (QoS) and QoS class identifier (QCI) tables. Our scheme thus offers a three-fold benefit to a firm in terms of commercialization: the design of a near-optimal low-complex LLR computation scheme that performs well in a 5G setting that demand high speed and accuracy, implementability using state-of-the-art technologies, and the flexibility of design on the basis of the QoS requirements of the customer application.

关键词： Wireless communication Training 5G mobile communication Neural networks Modulation Quality of service computer architecture

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Person Re-Identification with Few and Unlabeled Target Data 15th

Unsupervised Domain Adaptation for Person Re-Identification ...

引用

15th International symposium on Visual computing, ISVC 2020

作者： Galanakis, George Zabulis, Xenophon Argyros, Antonis A. Computer Science Department University of Crete Rethymno Greece Institute of Computer Science FORTH Heraklion Greece

ISBN: (纸本)9783030645588

Existing, fully supervised methods for person re-identification (ReID) require annotated data acquired in the target domain in which the method is expected to operate. this includes the IDs as well as images of persons in that domain. this is an obstacle in the deployment of ReID methods in novel settings. For solving this problem, semi-supervised or even unsupervised ReID methods have been proposed. Still, due to their assumptions and operational requirements, such methods are not easily deployable and/or prove less performant to novel domains/settings, especially those related to small person galleries. In this paper, we propose a novel approach for person ReID that alleviates these problems. this is achieved by proposing a completely unsupervised method for fine tuning the ReID performance of models learned in prior, auxiliary domains, to new, completely different ones. the proposed model adaptation is achieved based on only few and unlabeled target persons’ data. Extensive experiments investigate several aspects of the proposed method in an ablative study. Moreover, we show that the proposed method is able to improve considerably the performance of state-of-the-art ReID methods in state-of-the-art datasets. © 2020, Springer Nature Switzerland AG.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Bphoton-CNN: An ultrafast photonic backpropagation accelerator for deep learning 20

Bphoton-CNN: An ultrafast photonic backpropagation accelerat...

引用

30th Great Lakes symposium on VLSI, GLSVLSI 2020

作者： Dang, Dharanidhar Khansama, Aurosmita Mahapatra, Rabi Sahoo, Debashis University of California San Diego United States Texas A&M University United States

ISBN: (纸本)9781450379441

Training deep learning networks involves continuous weight updates across its many using a backpropagation algorithm (BP). this results in expensive computation and energy overheads during training. Consequently, most deep learning accelerators today employ pre-trained weights and focus only on improving the design of the inference phase. the recent trend is to develop a complete deep learning accelerator by incorporating the training module. Such efforts require an ultra-fast chip architecture for executing the BP algorithm. In this paper, we introduce a novel photonics-based backpropagation accelerator for high performance deep learning training. We present the design for a convolutional neural network, BPhoton-CNN, which incorporates the silicon photonics-based backpropagation accelerator. BPhoton-CNN is a first-of-its-kind photonic and memristor-based CNN architecture for end-to-end training and prediction. We evaluate BPhoton-CNN using a commercial CAD framework (IPKISS) on deep learning benchmark models including LeNet and VGG-Net. the proposed design achieves at least 35× acceleration in training time, 31× improvement in computational efficiency, and 45× energy savings compared to the state-of-the-art designs, without any loss of accuracy. © 2020 Association for computing Machinery.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

MULTIthREADED RENDERING FOR CROSS-PLATFORM 3D VISUALIZATION BASED ON VULKAN API 3

MULTITHREADED RENDERING FOR CROSS-PLATFORM 3D VISUALIZATION ...

引用

3rd BIM/GIS Integration Workshop / 15th 3D GeoInfo Conference

作者： Ioannidis, C. Boutsi, A. -M. Natl Tech Univ Athens Sch Rural & Surveying Engn Lab Photogrammetry Athens Greece

the visualization of large-sized 3D geospatial models is a graphics intensive task. With ever increasing size and complexity, more computing resources are needed to attain speed and visual quality. Exploiting the parallelism and the multi-core performance of the Graphics Processing Unit (GPU), a cross-platform 3D viewer is developed based on the Vulkan API and modern C++. the proposed prototype aims at the visualization of a textured 3D mesh of the Cultural Heritage by enabling a multi-threaded rendering pipeline. the rendering workload is distributed across many CPU threads by recording multiple command buffers in parallel and coordinating the host and the GPU rendering phases. To ensure efficient multi-threading behavior and a minimum overhead, synchronization primitives are exploiting for ordering the execution of queues and command buffers. Furthermore, push-constants are used to send uniform data to the GPU and render passes to adapt to the tile-based rendering of the mobile devices. the proposed methodology and technical solution are designed, implemented and tested for Windows, MacOS and Android on Vulkan-compatible GPU hardware by compiling the same codebase. the benchmarking on multiple hardware, architectures and platforms explores the performance improvement for the different approaches compared to one-thread and showcase the potential of the 3D viewer to handle large datasets at no expense of visual quality and geometric fidelity in the absence of high-end technological resources.

关键词： computer graphics 3D visualization graphics API Vulkan geospatial data

来源：评论

学校读者我要写书评

暂无评论

Active-Routing: Compute on the Way for Near-Data Processing 25

Active-Routing: Compute on the Way for Near-Data Processing

引用

25th IEEE International symposium on high performance computer architecture (HPCA)

作者： Huang, Jiayi Puli, Ramprakash Reddy Majumder, Pritam Kim, Sungkeun Boyapati, Rahul Yum, Ki Hwan Kim, Eun Jung Texas A&M Univ College Stn TX 77843 USA NVIDIA Santa Clara CA USA Intel Corp Santa Clara CA 95051 USA

ISBN: (纸本)9781728114446

the explosion of data availability and the demand for faster data analysis have led to the emergence of applications exhibiting large memory footprint and low data reuse rate. these workloads, ranging from neural networks to graph processing, expose compute kernels that operate over myriads of data. Significant data movement requirements of these kernels impose heavy stress on modern memory subsystems and communication fabrics. To mitigate the worsening gap between high CPU computation density and deficient memory bandwidth, solutions like memory networks and near-data processing designs are being architected to improve system performance substantially. In this work, we examine the idea of mapping compute kernels to the memory network so as to leverage in-network computing in data-flow style, by means of near-data processing. We propose Active-Routing, an in-network compute architecture that enables computation on the way for near-data processing by exploiting patterns of aggregation over intermediate results of arithmetic operators. the proposed architecture leverages the massive memory-level parallelism and network concurrency to optimize the aggregation operations along a dynamically built Active-Routing Tree. Our evaluations show that Active-Routing can achieve upto 7x speedup with an average of 60% performance improvement, and reduce the energy-delay product by 80% across various benchmarks compared to the state-of-the-art processing-in-memory architecture.

关键词： memory network data-flow in-network computing near-data processing processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：