Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)最新文献

Single image defogging with single and multiple hybrid scattering model 基于单、多混合散射模型的单幅图像去雾

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982693

Weijiang Feng, Naiyang Guan, Xiang Zhang, Xuhui Huang, Zhigang Luo

{"title":"Single image defogging with single and multiple hybrid scattering model","authors":"Weijiang Feng, Naiyang Guan, Xiang Zhang, Xuhui Huang, Zhigang Luo","doi":"10.1109/SPAC.2014.6982693","DOIUrl":"https://doi.org/10.1109/SPAC.2014.6982693","url":null,"abstract":"Image defogging (IDF) removes influences of fogs from an image to improve its quality. Since defogged images can significantly boost the performance of subsequent processing, IDF has attracted many attentions from the computer vision community. However, existing IDF algorithms are built on the assumption that light is scattered once by a grain. Since such assumption is violated if images are contaminated by dense haze or heavy fog, traditional IDF algorithms often fail in this situation. In this paper, we propose a hybrid image defogging (HIDF) algorithm to overcome this deficiency. In particular, HIDF applies the single scattering physics model (SSPM) to pixels dominated by single scattering of light, and applies the multiple scattering physics model (MSPM) to remaining pixels. To distinguish two types of pixels, HIDF utilizes the optical thickness of corresponding pixels. If optical thickness is smaller than a threshold that determines whether the single scattering or the multiple scattering dominates, HIDF applies the SSPM, and HIDF applies the MSPM otherwise. Experimental results on several popular foggy images demonstrate that HIDF competes with the state-of-the-art algorithms, and show the promise of HIDF for defogging heavily foggy images.","PeriodicalId":326246,"journal":{"name":"Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115405272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Correntropy induced metric based graph regularized non-negative matrix factorization 相关熵诱导的基于度量的图正则化非负矩阵分解

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982679

Bin Mao, Naiyang Guan, D. Tao, Xuhui Huang, Zhigang Luo

引用次数: 20

MPC and SADE for UAV real-time path planning in 3D environment 基于MPC和SADE的无人机三维实时路径规划

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982672

Qiang Wang, An Zhang, H. Sun

引用次数: 5

Artificial robot navigation based on gesture and speech recognition 基于手势和语音识别的人工机器人导航

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982708

Ze Lei, Zhaohui Gan, Min Jiang, Ke Dong

{"title":"Artificial robot navigation based on gesture and speech recognition","authors":"Ze Lei, Zhaohui Gan, Min Jiang, Ke Dong","doi":"10.1109/SPAC.2014.6982708","DOIUrl":"https://doi.org/10.1109/SPAC.2014.6982708","url":null,"abstract":"Human-computer interaction is a hot topic in artificial intelligence. Artificial navigation is an interesting application of human-computer interaction, which control the action of the target device by speech or gestures information. The main virtue of artificial navigation is that it can control target device within a distance without any remote control device. This technology can be used in the areas of robot navigation, vehicle navigation in the industrial site and virtual reality. This paper proposed an algorithm for robot navigation which combining gesture recognition with speech recognition. Firstly, use nine gesture instructions and nine voice commands to establish reference models. Secondly, extract real-time Skeleton information and the current speech messages by Kinect. Thirdly, evaluate the fitness of the current gesture and speech information of the reference model. Finally, deduce the navigation control instructions to command the robot's movement. Gestures and speech can compensate for each other's deficiencies, improve the recognition rate and robustness of the algorithm, reduce the computational complexity of algorithm, makes the human-computer interaction more simple, clear and natural.","PeriodicalId":326246,"journal":{"name":"Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122716889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Design and implementation of one vertical video search engine 一个垂直视频搜索引擎的设计与实现

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982660

Yingyi Liang, Zhenyu He, Yi Li

{"title":"Design and implementation of one vertical video search engine","authors":"Yingyi Liang, Zhenyu He, Yi Li","doi":"10.1109/SPAC.2014.6982660","DOIUrl":"https://doi.org/10.1109/SPAC.2014.6982660","url":null,"abstract":"In this paper, a video vertical search engine is designed and implemented based on the theory of vertical search engine. Firstly, we introduce the vertical search engine and its research situation at home and abroad, analyze the principle of implementing the vertical search engine, and introduce the key technology used in this paper, such as subject information acquisition method, Chinese segmentation algorithm, and the search result re-sorting. We provide the video resource acquisition process and the video resources storage, and repeat video resources exclusion. Then, we analyze an information retrieval tool library, Lucene, which is with a advanced design and superior performance. Based on this library, a Chinese segmentation algorithm and a result sorting method are added. Unlike current other studies, a variable length matching strategy is taken for designing Chinese word with bidirectional matching method for disambiguation. Compared with the latest open source word segmentation algorithm, our segmentation algorithm designed in this paper outperforms better. With the video resources fetching from the internet and the Chinese word segmentation of VKAnalyzer extending from Lucene designed and implemented in the paper, we design related video re-sorting methods by different ways, such as length, times and comments, and implement the sorting method for search results according to users' various requirements. The experiments shows that the recall rate of the search engine is 90% and the accuracy is 97%, as are satisfactory.","PeriodicalId":326246,"journal":{"name":"Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114054423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Improved genetic algorithm for emergency logistics distribution vehicle routing problems 改进遗传算法求解应急物流配送车辆路径问题

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982721

Minghua Chen

引用次数: 5

Laplacian-Hessian regularization for semi-supervised classification 半监督分类的laplace - hessian正则化

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982685

Hongli Liu, Weifeng Liu, Dapeng Tao, Yanjiang Wang

引用次数: 4

Robust visual tracking with spatial phase correlation 基于空间相位相关的鲁棒视觉跟踪

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982652

Yufei Zha, Lichao Zhang, Yuan Yang, Bing Qin, Hao Li, Huanyu Li

引用次数: 0

The online transportation problem with the sudden traffic congestions 突发性交通拥堵下的在线交通问题

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982707

Hu Mao-Lin

引用次数: 0

An improvement on approximate dynamic programming for multi-document summarization 多文档摘要的近似动态规划改进

Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2014-12-15 DOI: 10.1109/SPAC.2014.6982716

Yihui Luo, Shuchu Xiong

引用次数: 1