检索结果-内蒙古大学图书馆

Implicit curves and surfaces based on BP neural network

Journal of Information and Computational Science 2005年第2期2卷 259-271页

作者： Li, Daolun Lu, Detang Kong, Xiangyang Wu, Gang Laboratory of Software in Computing and Communication of Anhui Province University of Science and Technology of China Hefei 230026 China Institute of Engineering and Science Software University of Science and Technology of China Hefei 230026 China Nanjing University of Finance and Economics Nanjing 210012 China

Neural networks, combined with implicit polynomials, can be employed to represent 2D curves as well as 3D surfaces. The zero-set of a neural network can be used to describe data points constituting a 2D curve or 3D surface. The neural network fitting algorithms developed in this paper aim to reduce the learning time of neural network by selecting the exterior and interior constraint points simultaneously and improve the fitting performance by using the linear transfer function at the output layers. The neural network adopted so far is a multilayer feed-forward type. Simulation results show that the proposed algorithms provide a significant reduction in learning time, and good fitting results. This paper lays the bases of the neural network modeling approach.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

FACIAL ACTION UNIT RECOGNITION BY RELATION MODELING FROM BOTH QUALITATIVE KNOWLEDGE AND QUANTITATIVE DATA

FACIAL ACTION UNIT RECOGNITION BY RELATION MODELING FROM BOT...

引用

IEEE International Conference on Multimedia and Expo Workshops

作者： Zhen Gao Shangfei Wang Chongliang Wu Jun Wang Qiang Ji Key Lab of Computing and Communication Software of Anhui Province School of Computer Science and Technology University of Science and Technology of China Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute

ISBN: (纸本)9781479947164

In this paper, we propose to capture Action Unit (AU) relations existing in both qualitative knowledge and quantitative data through Credal Networks (CN). Each node of the CN represents an AU label, and the links and probability intervals capture the probabilistic dependencies among multiple AUs. The structure of CN is designed based on prior knowledge. The parameters of CN are learned from both knowledge and ground-truth AU labels. The AU preliminary estimations are obtained by an existing image-driven recognition method. With the learned credal network, we infer the true AU labels by combining the relationships among labels with the previous obtained estimations. Experimental results on the CK+ database and MMI database demonstrate that with complete AU labels, our CN model is slightly better than the Bayesian Network (BN) model, demonstrating that credal sets learned from data can capture uncertainty more reliably;With incomplete and error-prone AU annotations, our CN model outperforms the BN model, indicating that credal sets can successfully capture qualitative knowledge.

关键词： Prior knowledge Credal network AU recognition

来源：评论

学校读者我要写书评

暂无评论

A hybrid active contour model with local Gaussian distribution fitting energy for image segmentation

引用

Journal of Information and Computational Science 2015年第17期12卷 6515-6523页

作者： Zhang, Runru Huang, Zhangjin Gu, Naijie School of Computer Science and Technology University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Computing and Communication Software Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei China

Active contour models have been widely applied in image segmentation with promising results. However, many of them fail to segment images successfully due to intensity inhomogeneity. To address this problem, we propose a hybrid region-based active contour model which fully utilizes local intensity information. This model develops a localized active contour framework and incorporates a local Gaussian distribution fitting energy. In order to increase both the computational efficiency and stability of the proposed model, a multi-resolution strategy is employed and the active contour is evolved in a reinitialization-free way. Extensive experiments demonstrate that our model is effective and efficient in segmenting images with intensity inhomogeneity, and outperforms several state-of-the-art algorithms. © 2015 by Binary Information Press.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Performance research and optimization on CPython's interpreter

Performance research and optimization on CPython's interpret...

引用

Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Huaxiong Cao Naijie Gu Kaixin Ren Yi Li Anhui Province Key Laboratory of Computing and Communication Software Department of Computer Science and Technology University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781479967476

In this paper, the performance research on CPython's latest interpreter is presented, concluding that bytecode dispatching takes about 25 percent of total execution time on average. Based on this observation, a novel bytecode dispatching mechanism is proposed to reduce the time spent on this phase to a minimum. With this mechanism, the blocks associated with each kind of bytecodes are rewritten in hand-tuned assembly, their opcodes are renumbered, and their memory spaces are rescheduled. With these preparations, this new bytecode dispatching mechanism replaces the time-consuming memory reading operations with rapid operations on registers. This mechanism is implemented in CPython-3.3.0. Experiments on lots of benchmarks demonstrate its correctness and efficiency. The comparison between original CPython and optimized CPython shows that this new mechanism achieves about 8.5 percent performance improvement on average. For some particular benchmarks, the maximum improvement is up to 18 percentages.

关键词： Dispatching Benchmark testing Binary codes Switches Optimization Registers Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

A qualitative modeling and simulation method based on cloud model

A qualitative modeling and simulation method based on cloud ...

引用

International Conference on Modeling, Simulation and Applied Optimization (ICMSAO)

作者： Chenxi Shao Kelü Sun Zhenzhong Shao Computer Science and Technology Department University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Software in Computing and Communication Hefei China Jianghuai Automobile Company Limited Hefei China

ISBN: (纸本)9781467358125

Qualitative simulation is effective methods processing incomplete knowledge, how to represent qualitative knowledge and reduce spurious behaviors is its research emphasis. Contraposing the limitations of existing methods representing qualitative knowledge and filtering spurious behaviors, an approach is proposed to qualitatively model and simulate on the basis of normal cloud model. In this research, the cloud numeric characteristics and cloud measurement are introduced into this approach; consequently, it can more accurately assess the qualitative knowledge, and expand the variables expression and quantity space; meanwhile, it is constructed the means of modeling and simulation by adopting more amply portraying the system status, more intuitively transforming status and more accurately filtering spurious behaviors. Furthermore, in simulation algorithm, cloud measurement indices are employed to significantly select the successor status which can not be determined by existing constraint means. The results of simulation example demonstrate that our approach effectively improves the ability to filter spurious behaviors, and it is a feasible method.

关键词： Uncertainty Coordinate measuring machines Computational modeling Entropy Measurement uncertainty Numerical models Size measurement

来源：评论

学校读者我要写书评

暂无评论

Airborne moving vehicle detection for urban traffic surveillance

Airborne moving vehicle detection for urban traffic surveill...

引用

International Conference on Intelligent Transportation

作者： Renjun Lin Xianbin Cao Yanwu Xu Chuangxian Wei Hong Qiao Anhui Province Key Laboratory of Software Computing and Communication University of Science and Technology Hefei China University of Manchester Institute of Science and Technology UK Institute of Automation Chinese Academy and Sciences Beijing China

At present, moving vehicle detection on airborne platform has been an important technology for urban traffic surveillance. In such a situation, most commonly used methods (e.g. image subtraction) could hardly work well because of some additional difficulties such as slow movement of vehicles and jam. This paper proposed a new moving vehicle detection method named MVD-RD for airborne urban traffic surveillance. First, the non-road regions are extracted using road detection technique. Secondly, the non-road regions with no vehicles are removed according to their size. As a result of this two-stage regions shrinkage, the detection area reduces a lot. Finally, to the reduced area, image subtraction is used to get all moving regions and then moving vehicles can be accurately filtered in a simple way. The experimental results show that, compared with traditional image subtraction methods used in airborne moving vehicle detection, the proposed MVD-RD method achieves much better performance in detection rate, false alarm rate, and detection speed.

关键词： Vehicle detection Surveillance Road vehicles Cameras Road transportation Layout Intelligent transportation systems Optical filters Intelligent vehicles Air transportation

来源：评论

学校读者我要写书评

暂无评论

Constructing the Voronoi Diagram of Planar Point Set in Parallel

Constructing the Voronoi Diagram of Planar Point Set in Para...

引用

International Conference on Computational Intelligence and software engineering (CiSE)

作者： Lanfang Dong Yuan Wu Shanhai Zhou Anhui Province Key Laboratory of Software In Computing and Communication College of computer science and technology University of Science and Technology Hefei China College of computer science & technology University of Science and Technology Hefei China

By researching Voronoi diagram, parallel algorithm, and divide-and-conquer method, we present a special data structure(change doubly-connected list little) for Voronoi diagram generation in parallel. In this paper we also present two proposal, they are one processor gradually to merge and 22-merger on the parallel machine, the experiment results show that the present algorithm runs faster than the serial program. By analyzing the various results, we should choose the most suitable number of processors according to the point set scale. At last, we can conclude that gradually merger with one processor is better proposal for Voronoi diagram parallel generation.

关键词： Data structures Educational institutions Computer science Parallel algorithms Proposals Switches Merging Concurrent computing Parallel machines Geography

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Support Vector Machines Classifier for Pedestrian Detection

An Evolutionary Support Vector Machines Classifier for Pedes...

引用

2006 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： D. Chen X.b. Cao Y.w. Xu H. Qiao Department of Computer Science and Technology University of Science and Technology Hefei China Anhui Province Key Laboratory Software Computing and Communication Hefei China Institute of Automation Chinese Academy and Sciences Beijing China

In a pedestrian detection system, a classifier is usually designed to recognize whether a candidate is a pedestrian. Support vector machines (SVM) has become a primary technique to train a classifier for pedestrian detection. However, it is hard to give the best training model which has a tremendous effect to the performance of a SVM classifier. In this paper, we design special code/decode scheme and evaluation function for a training model firstly; and then use genetic algorithm to optimize key parameters which represent the SVM training model. Therefore a most suitable SVM classifier can be obtained for pedestrian detection. Experiments have been carried out in a single camera based pedestrian detection system. The results show that the evolutionary SVM classifier has a better detection rate; moreover, RBF kernel is more suitable than polynomial kernel when chosen in an evolutionary SVM classifier for pedestrian detection

关键词： Support vector machines Support vector machine classification Kernel Genetic algorithms Decoding Design optimization Cameras Intelligent robots Computer science Laboratories

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Genetic Algorithm for Vehicle Routing Problems with Dynamic Requests

A Hybrid Genetic Algorithm for Vehicle Routing Problems with...

引用

IEEE Symposium Series on Computational Intelligence

作者： Ruikang Yi Wenjian Luo Chenyang Bu Xin Lin Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei Anhui China

In this paper, a hybrid Genetic Algorithm (GA) is proposed to solve the Vehicle Routing Problems with Dynamic Requests (VRPDR). The proposed hybrid GA primarily involves the following parts. First, a greedy split is introduced, which is fit for the VRPDR. Second, the adjacent-exchange-based local search is proposed. Third, a novel mutation operator, named the insert mutation, is proposed. The experimental results show that the proposed hybrid GA is effective.

关键词： Dynamic Vehicle Routing Genetic Algorithm Split Algorithm Local Search

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：