开放环境下基于视觉注意模型的烟雾检测技术研究
|
摘要
火灾是严重威胁社会安全的自然灾害之一。近年来，大型商场、社区、林区等场所火灾事故频繁发生，给人类社会生产生活带来了巨大损失。由于烟雾是火焰燃烧前呈现出的现象，因此可以通过检测烟雾及时地发出火灾报警，降低火灾损失。近三十年来，随着神经心理学、行为学对大脑视觉认知机制的研究进展，人工智能和机器视觉领域出现了研究生物视觉计算模型的热潮，视觉注意模型的研究为烟雾检测提供了崭新的发展方向。本文旨在探索开放环境下基于视觉显著性和小波分析的烟雾检测方法。
本文研究的重点是研究基于视觉注意模型的烟雾检测算法。其中包括改进传统的自下而上视觉注意模型，在烟雾检测中引入自上而下的任务驱动机制，提取可疑烟雾区域的动态特征以实现准确的烟雾在线识别。本文的主要工作可以概括为以下几个方面：
(1)在Itti视觉注意模型的基础上，提出将物体运动特征与图像静态特征融合，实现自下而上视觉注意模型的烟雾显著性检测。其中引入了一种运动优先的显著性图融合策略，使模型更加契合于人眼的视觉注意机制。
(2)建立自上而下的视觉注意模型对显著性区域进行控制。为了有效模拟人眼基于任务的显著性控制机理，本文针对烟雾这一检测目标，结合烟雾的边缘不规则性、区域灰色度等特征，利用区域相似性度量生成图像自上而下的显著性图，进一步控制显著性区域的受注意程度。
(3)构建了贝叶斯网络分类器，实现了烟雾最终识别。基于视觉注意模型的感兴趣区域提取是对类烟雾区域的粗略提取。为了最终识别区域是否是真实烟雾，本文针对烟雾特有的模糊性、边缘不规则性、区域灰色度、区域饱和度等特征进行了提取，训练贝叶斯网络分类器，实现烟雾的准确识别。
(4)在参加省重大科技专项“基于太阳能的森林火灾智能远程无线监测系统研制”过程中，独立开发完成了远程监控中心软件，实现了林区视频实时播放、录制、控制前端云台动作、响应报警信息等功能。另外，为了验证本文烟雾检测算法的有效性，本文从自下而上显著性分析、自上而下区域显著性控制、ROI提取及抗光照性检测等方面通过大量实验验证了算法的有效性，并对烟雾检测算法的完善进行了展望。
Fire is one of natural disasters which have serious threat to social security. In recent years,many places such as large shopping malls, community and so on have been the frequently firesoccurred places, and have bought much loss to the social security. Since the smoke is a presentphenomenon before burning flame ,so we can send the fire alarm by detecting smoke in time toreduce the loss, In the past 30 years, along with neuropsychology and behavior science research forthe brain vision cognitive mechanism, artificial intelligence and machine vision areas appearedgreat mass fervor on biological visual calculation model research. And the research on VisualAttention Model provides a new development direction for the smoke detection. This paper aims toexplore a new smoke detection methods based on visual significant and wavelet analysis under theopen environment.
The focus of this research is study on the smoke detection algorithm based on visual attentionmodel. Including improved traditional bottom-up visual attention model, bringing in top-downmission driving mechanism in smoke detection, extracting suspicious regional dynamic features ofsmoke in order to realize smoke on-line identification. This research can summarize in thefollowing respects:
(1) Proposed a bottom-up visual attention module used for smoke detection based on theanalysis and summary of the Itti visual attention model. In the stage of feature extraction weintroduce the movement feature of images; also we introduce an effective integration strategy forthe integration of significant maps, making Made the model more fit with the human visualattention mechanism.
(2) Establishing a top-down visual attention model to control the significant of bottom-upsignificant map. In order to simulate the task-based significant control mechanism of human eyes’,this paper combined the irregularity of smoke’s edge, using the regional image similarity togenerate the top-down significant map. This map used to control the bottom-up significant areas.
(3)Building a Bayesian classifier achieved the smoke identification. The region of interestdetected based on the visual attention module is the preliminary detection of smoke. In order toidentify whether the region is smoke region or not, this paper extracted the region’s irregularity,wavelet high frequency energy, gray degree and other dynamic feature. Training a Bayesianclassifier and achieving the smoke identification accurately.
(4) In the "Intelligent forest fires detection system in open areas”, I completed the developmentof remote monitoring center software. It has different functions such as real-time video playback, recording, PTZ control, alarm response and so on. Also in order to verification the effectiveness ofthe smoke detection algorithm proposed in this paper, we did the image’s bottom-up visualsignificance analysis, top-down control of regional significance and so on. At last we raised theoutlook of fire detection.
本文研究的重点是研究基于视觉注意模型的烟雾检测算法。其中包括改进传统的自下而上视觉注意模型，在烟雾检测中引入自上而下的任务驱动机制，提取可疑烟雾区域的动态特征以实现准确的烟雾在线识别。本文的主要工作可以概括为以下几个方面：
(1)在Itti视觉注意模型的基础上，提出将物体运动特征与图像静态特征融合，实现自下而上视觉注意模型的烟雾显著性检测。其中引入了一种运动优先的显著性图融合策略，使模型更加契合于人眼的视觉注意机制。
(2)建立自上而下的视觉注意模型对显著性区域进行控制。为了有效模拟人眼基于任务的显著性控制机理，本文针对烟雾这一检测目标，结合烟雾的边缘不规则性、区域灰色度等特征，利用区域相似性度量生成图像自上而下的显著性图，进一步控制显著性区域的受注意程度。
(3)构建了贝叶斯网络分类器，实现了烟雾最终识别。基于视觉注意模型的感兴趣区域提取是对类烟雾区域的粗略提取。为了最终识别区域是否是真实烟雾，本文针对烟雾特有的模糊性、边缘不规则性、区域灰色度、区域饱和度等特征进行了提取，训练贝叶斯网络分类器，实现烟雾的准确识别。
(4)在参加省重大科技专项“基于太阳能的森林火灾智能远程无线监测系统研制”过程中，独立开发完成了远程监控中心软件，实现了林区视频实时播放、录制、控制前端云台动作、响应报警信息等功能。另外，为了验证本文烟雾检测算法的有效性，本文从自下而上显著性分析、自上而下区域显著性控制、ROI提取及抗光照性检测等方面通过大量实验验证了算法的有效性，并对烟雾检测算法的完善进行了展望。
Fire is one of natural disasters which have serious threat to social security. In recent years,many places such as large shopping malls, community and so on have been the frequently firesoccurred places, and have bought much loss to the social security. Since the smoke is a presentphenomenon before burning flame ,so we can send the fire alarm by detecting smoke in time toreduce the loss, In the past 30 years, along with neuropsychology and behavior science research forthe brain vision cognitive mechanism, artificial intelligence and machine vision areas appearedgreat mass fervor on biological visual calculation model research. And the research on VisualAttention Model provides a new development direction for the smoke detection. This paper aims toexplore a new smoke detection methods based on visual significant and wavelet analysis under theopen environment.
The focus of this research is study on the smoke detection algorithm based on visual attentionmodel. Including improved traditional bottom-up visual attention model, bringing in top-downmission driving mechanism in smoke detection, extracting suspicious regional dynamic features ofsmoke in order to realize smoke on-line identification. This research can summarize in thefollowing respects:
(1) Proposed a bottom-up visual attention module used for smoke detection based on theanalysis and summary of the Itti visual attention model. In the stage of feature extraction weintroduce the movement feature of images; also we introduce an effective integration strategy forthe integration of significant maps, making Made the model more fit with the human visualattention mechanism.
(2) Establishing a top-down visual attention model to control the significant of bottom-upsignificant map. In order to simulate the task-based significant control mechanism of human eyes’,this paper combined the irregularity of smoke’s edge, using the regional image similarity togenerate the top-down significant map. This map used to control the bottom-up significant areas.
(3)Building a Bayesian classifier achieved the smoke identification. The region of interestdetected based on the visual attention module is the preliminary detection of smoke. In order toidentify whether the region is smoke region or not, this paper extracted the region’s irregularity,wavelet high frequency energy, gray degree and other dynamic feature. Training a Bayesianclassifier and achieving the smoke identification accurately.
(4) In the "Intelligent forest fires detection system in open areas”, I completed the developmentof remote monitoring center software. It has different functions such as real-time video playback, recording, PTZ control, alarm response and so on. Also in order to verification the effectiveness ofthe smoke detection algorithm proposed in this paper, we did the image’s bottom-up visualsignificance analysis, top-down control of regional significance and so on. At last we raised theoutlook of fire detection.
引文
[1]林宏,陈旭,强振平.视频火灾自动预警中烟雾检测的研究[J].人工智能及识别技术.2009,8(2):81-83.
[2]梁志明.加强森林防火教育的重要性及措施[J].科技资讯.2009,20(18):22-25.
[3] Yu Chunyu, Zhang Yongming, Fang Jun, Wang Jinjun .Texture analysis of smoke for real-time fire detection[J]. Computer Science and Engineering.2009,511-515.
[4] Chen-Yu Lee, Chin-Teng Lin, Fellow, IEEE, and Chao-Ting Hong. Spatio-Temporal Analysis in Smoke Detection[C].2009 IEEE International Conference on Signal and Image Processing Applications,2009:80-83.
[5] Hidenori Maruta, Yasuharu Katot , Akihiro Nakamural .Smoke detection in open areas using its texture features and time series properties.In the 2009 IEEE International Symposium on Industrial Electronics(ISlE). 2009:1904-1908.
[6]闫建强.基于DM642和图像分析的林火烟雾检测系统研究[J].杭州电子科技大学, 2011,27(9):32-36.
[7] Luo Qinjuan,Han Ning,Kan Jiangming,Wang Zheng.Effective dynamic object detecting for video-based forest fire smog recognition[J].Image and Signal Processing, 2005,3(7):1-5.
[8]赵建华,方俊,疏学明.基于神经网络的火灾烟雾识别方法[J].光学学报,2001,23(9):1086-1089.
[9]夏文德,练秋生.基于视频处理的烟雾检测快速算法[J].电子技术,2007,34(11):135-138.
[10] Dong Keun Kim,Yuan-Fang Wang. Smoke Detection in Video[C].India:2009 World Congress on Computer Science and Information Engineering, 2009:759-763.
[11]邓彬,刘辉,连国云,陈静.基于视频的烟雾检测[J].长沙大学学报, 2007,21(5):87-89.
[12] Thou-Ho (Chao-Ho) Chen, Yen-Hui Yin, Shi-Feng Huang. The Smoke Detection for Early Fire-Alarming System Base on Video Processing[C]. San Francisco: the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2006,427-430.
[13]杨猛,赵春晖,潘泉,张绍武.基于小波分析的烟雾多特征融合和空间精度补偿森林火情检测算法[J].中国图像图形学报,2009,14(4):694-700.
[14] Hidenori Maruta, Yasuharu Katot , Akihiro Nakamural.Smoke detection in open areas using its texture features and time series properties.In the 2009 IEEE International Symposium on Industrial Electronics(ISlE), 2009,1904-1908.
[15] B.Ugur Toreyin, Yigithan Dedeoglu, and A. Enis Cetin.Contour based smoke detection in video using wavelets e[J].Muscle Network of Excellenc ,2005,27(6):1021-1025.
[16] Paolo Piccinini,Simone Calderara,Rita Cucchiara. Reliable smoke detection system in the domins of image energy and color[C].Proceedings - International Conference on Image Processing.,2008 ,1976-7979.
[17]李刚,邱尚斌,林凌,曾锐利.基于背景差法和帧间差法的运动目标检测方法[J].仪器仪表学报,2006,8:124-129.
[18]王成儒.顾广华.一种采用背景统计技术的视频对象分割算法[J].光电工程,2004,19(8):68-73.
[19] Jerome Vicente, Philippe Guillemant. An image processing technique for automatically detecting forest fire[J]. International Journal of Thermal Sciences,2002,41:1113-1120.
[20]练秋生,李党.融合多种特征的烟雾图像检测算法[J].光学技术, 2009,35(4):523-529.
[21] Chao-Chong Ho, Tzu-Hsin Kuo. Real-Time Video-Based Fire Smoke Detection System[C].Hong kong: 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2009,1845-1850.
[22] Vijay Mahadevan, Student Member. Spatiotemporal Saliency in Dynamic Scenes[J].Pattern Analysis and Machine Intelligence, 2010,32(1):171-177.
[23]帅师,周平,汪亚明,周维达.基于小波的实时烟雾检测[J].计算机应用研究, 2007,24(3):309-311.
[24] Khananian A , Fraser R H , Cihlar J . Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery[J].IEEE Transactions on Geoscience and Remote Sensing ,2001,39 (9) :1859 -1870 .
[25] Yu Chunyu,Zhang Yongming,Fang Jun,Wang Jinjun.Texture analysis of smoke for real-time fire detection[J].Computer Science and Engineering, 2009,511-515.
[26] Cheng Huiquan,Liu Liren,Li Guoqing.基于混合类间联想神经网络的光学模式识别[J]-光学学报1998,10:965-968.
[27] Chen Y,Serio M A,Athyamoorthy S. Development of a fire detection system using FT-IR spectroscopyand artificial neural networks [J]. Fire Safety Science, 1999,21(2):791-802.
[28] Jiao LiCheng.神经网络系统理论[D].西安:西安电子科技大学出版社,1996:1-223.
[29] Chen-Yu Lee, Chin-Teng Lin,Chao-Ting Hong.Spatio-Temporal Analysis in Smoke Detection[C]. Kildare :2009 IEEE International Conference on Signal and Image Processing Applications, 2009:80-83.
[30] Okayama Y. A primitive study of a fire detection method controlled by artificial neural net[J]. Computer Science and Engineering,1991,6:125-129.
[31] J.A. Driscoll, R.A. Peters II and K.R. Cave.A visual attention network for a humanoid robot, ICIRS, 1998.
[32] Y.-F. Ma and H.-J. Zhang. Contrast-based image attention analysis by using fuzzy growing[C]. Hong Kong : ACM MultimediaConf, 2003:374-381.
[33] G. Deco,J. Zihl.A neurodynamical model of visual attention: feedback enhancement of spatial resolution in a hierarchical system [J].Journal of Computational Neuro-science, 2001,10:231-253.
[34] Yuming Fang,Weisi Lin. A visual attention model combining top-down and botton-up mechanisms for salient object detection.IEEE International Conference on Acoustics, Speech and Signal Processing .2011,1293-1296.
[35]朱巨莲,霍宏.基于自顶向下视觉注意的遥感影像目标检测[J].计算机工程. 2011,5(37):126-129.
[36] Steven Yantis. The Neural basis of selective attention[J].Current directions in Psychological science,2008,17(2):86-90.
[37] Itti L, Koch C, N iebu r E. A model of saliency based visual attention for rapid scene analysis. IEEE Transact ions on Pattern Analysis and Machine Intelligence, 1998, 20( 11) : 1254-1259.
[38]于江波，陈后金，李居朋.视觉选择注意机制模型及其应用[J].电子测量与仪器学报. 2008,22(4)：100-103.
[39]邵静,高隽.基于协同感知的视觉选择注意计算模型[J].中国图象图形学报,2008,13(1):129-136.
[40]陈振学,刘成云,常发亮.基于生物视觉显著性的车辆车型识别[J].计算机科学,2010,37(2):207-209.
[41]田明辉,万寿红,岳丽华.自然场景中的视觉显著对象检测[J].中国图象图形学报,2010,15(11) : 1650-1657.
[42] A. Oliva, A. Torralba, M. Castelhano, J. Henderson.Top-down control of visual attention in object detection[C]. Internat:Conf. on Image Processing, 2003,253-256.
[43] Fred H. Hamker.Modeling feature-based attention as an active top-down inference process.2006,86(1-3):91-99.
[44]邵静.一种基于视觉注意机制的感知物体提取算法[J].现代电子技术,2010,33(20) : 71-74.
[45] NAVALPAKKAM, V.,ITTI, L..Modeling the influence of task on attention[J].Vision Research,2005,45(2):205–231.
[46] Jin-Kui Chu,Rong-Hua Li,Qing-Ying Li,Hong-Qing Wang. A Visual Attention Model for Robot Object Tracking[J]. International journal of automation and computing,2010,7(1):39-46.
[47] Fahad Shahbaz Khan, Joost van de Weijer, Maria Vanrell.Top-Down Color Attention for Object Recognition[J]. Computer Vision.2009:979-986.
[48]于江波,陈后金,李居朋.视觉选择注意机制模型及其应用[J].电子测量与仪器学报,2008,22(4):100-103.
[49]邵静.一种基于视觉注意机制的感知物体提取算法[J].现代电子技术,2010,33(20) : 71-74.
[50]张杰,魏维.基于视觉注意力模型的显著性提取[J].计算机技术与发展,2010,20( 11) : 109-113.
[51]田明辉,万寿红,岳丽华.自然场景中的视觉显著对象检测[J].中国图象图形学报,2010,15(11) : 1650-1657.
[52]孙瑾秋,张艳宁,周军.基于选择性视觉注意机制和曲线发现法的弱小目标检测[J].吉林大学学报(工学版),2010,40( 6) : 1683-1687.
[53] Fahad Shahbaz Khan, Joost van de Weijer, Maria Vanrell.Top-Down Color Attention for Object Recognition[J]. Computer Vision.2009,38(3):979-986.
[54]张剑飞.贝叶斯网络学习方法和算法研究[D].东北师范大学, 2005.
[55]胡玉胜,涂序彦,崔晓瑜,程乾生.基于贝叶斯网络的不确定性知识的推理方法[J].计算机集成制造系统,2001, 7(12):65-68.
[56]黄可杰.基于DSP/IP模块的林区火焰监控系统关键技术研究[D].杭州电子科技大学, 2011.
[2]梁志明.加强森林防火教育的重要性及措施[J].科技资讯.2009,20(18):22-25.
[3] Yu Chunyu, Zhang Yongming, Fang Jun, Wang Jinjun .Texture analysis of smoke for real-time fire detection[J]. Computer Science and Engineering.2009,511-515.
[4] Chen-Yu Lee, Chin-Teng Lin, Fellow, IEEE, and Chao-Ting Hong. Spatio-Temporal Analysis in Smoke Detection[C].2009 IEEE International Conference on Signal and Image Processing Applications,2009:80-83.
[5] Hidenori Maruta, Yasuharu Katot , Akihiro Nakamural .Smoke detection in open areas using its texture features and time series properties.In the 2009 IEEE International Symposium on Industrial Electronics(ISlE). 2009:1904-1908.
[6]闫建强.基于DM642和图像分析的林火烟雾检测系统研究[J].杭州电子科技大学, 2011,27(9):32-36.
[7] Luo Qinjuan,Han Ning,Kan Jiangming,Wang Zheng.Effective dynamic object detecting for video-based forest fire smog recognition[J].Image and Signal Processing, 2005,3(7):1-5.
[8]赵建华,方俊,疏学明.基于神经网络的火灾烟雾识别方法[J].光学学报,2001,23(9):1086-1089.
[9]夏文德,练秋生.基于视频处理的烟雾检测快速算法[J].电子技术,2007,34(11):135-138.
[10] Dong Keun Kim,Yuan-Fang Wang. Smoke Detection in Video[C].India:2009 World Congress on Computer Science and Information Engineering, 2009:759-763.
[11]邓彬,刘辉,连国云,陈静.基于视频的烟雾检测[J].长沙大学学报, 2007,21(5):87-89.
[12] Thou-Ho (Chao-Ho) Chen, Yen-Hui Yin, Shi-Feng Huang. The Smoke Detection for Early Fire-Alarming System Base on Video Processing[C]. San Francisco: the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2006,427-430.
[13]杨猛,赵春晖,潘泉,张绍武.基于小波分析的烟雾多特征融合和空间精度补偿森林火情检测算法[J].中国图像图形学报,2009,14(4):694-700.
[14] Hidenori Maruta, Yasuharu Katot , Akihiro Nakamural.Smoke detection in open areas using its texture features and time series properties.In the 2009 IEEE International Symposium on Industrial Electronics(ISlE), 2009,1904-1908.
[15] B.Ugur Toreyin, Yigithan Dedeoglu, and A. Enis Cetin.Contour based smoke detection in video using wavelets e[J].Muscle Network of Excellenc ,2005,27(6):1021-1025.
[16] Paolo Piccinini,Simone Calderara,Rita Cucchiara. Reliable smoke detection system in the domins of image energy and color[C].Proceedings - International Conference on Image Processing.,2008 ,1976-7979.
[17]李刚,邱尚斌,林凌,曾锐利.基于背景差法和帧间差法的运动目标检测方法[J].仪器仪表学报,2006,8:124-129.
[18]王成儒.顾广华.一种采用背景统计技术的视频对象分割算法[J].光电工程,2004,19(8):68-73.
[19] Jerome Vicente, Philippe Guillemant. An image processing technique for automatically detecting forest fire[J]. International Journal of Thermal Sciences,2002,41:1113-1120.
[20]练秋生,李党.融合多种特征的烟雾图像检测算法[J].光学技术, 2009,35(4):523-529.
[21] Chao-Chong Ho, Tzu-Hsin Kuo. Real-Time Video-Based Fire Smoke Detection System[C].Hong kong: 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2009,1845-1850.
[22] Vijay Mahadevan, Student Member. Spatiotemporal Saliency in Dynamic Scenes[J].Pattern Analysis and Machine Intelligence, 2010,32(1):171-177.
[23]帅师,周平,汪亚明,周维达.基于小波的实时烟雾检测[J].计算机应用研究, 2007,24(3):309-311.
[24] Khananian A , Fraser R H , Cihlar J . Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery[J].IEEE Transactions on Geoscience and Remote Sensing ,2001,39 (9) :1859 -1870 .
[25] Yu Chunyu,Zhang Yongming,Fang Jun,Wang Jinjun.Texture analysis of smoke for real-time fire detection[J].Computer Science and Engineering, 2009,511-515.
[26] Cheng Huiquan,Liu Liren,Li Guoqing.基于混合类间联想神经网络的光学模式识别[J]-光学学报1998,10:965-968.
[27] Chen Y,Serio M A,Athyamoorthy S. Development of a fire detection system using FT-IR spectroscopyand artificial neural networks [J]. Fire Safety Science, 1999,21(2):791-802.
[28] Jiao LiCheng.神经网络系统理论[D].西安:西安电子科技大学出版社,1996:1-223.
[29] Chen-Yu Lee, Chin-Teng Lin,Chao-Ting Hong.Spatio-Temporal Analysis in Smoke Detection[C]. Kildare :2009 IEEE International Conference on Signal and Image Processing Applications, 2009:80-83.
[30] Okayama Y. A primitive study of a fire detection method controlled by artificial neural net[J]. Computer Science and Engineering,1991,6:125-129.
[31] J.A. Driscoll, R.A. Peters II and K.R. Cave.A visual attention network for a humanoid robot, ICIRS, 1998.
[32] Y.-F. Ma and H.-J. Zhang. Contrast-based image attention analysis by using fuzzy growing[C]. Hong Kong : ACM MultimediaConf, 2003:374-381.
[33] G. Deco,J. Zihl.A neurodynamical model of visual attention: feedback enhancement of spatial resolution in a hierarchical system [J].Journal of Computational Neuro-science, 2001,10:231-253.
[34] Yuming Fang,Weisi Lin. A visual attention model combining top-down and botton-up mechanisms for salient object detection.IEEE International Conference on Acoustics, Speech and Signal Processing .2011,1293-1296.
[35]朱巨莲,霍宏.基于自顶向下视觉注意的遥感影像目标检测[J].计算机工程. 2011,5(37):126-129.
[36] Steven Yantis. The Neural basis of selective attention[J].Current directions in Psychological science,2008,17(2):86-90.
[37] Itti L, Koch C, N iebu r E. A model of saliency based visual attention for rapid scene analysis. IEEE Transact ions on Pattern Analysis and Machine Intelligence, 1998, 20( 11) : 1254-1259.
[38]于江波，陈后金，李居朋.视觉选择注意机制模型及其应用[J].电子测量与仪器学报. 2008,22(4)：100-103.
[39]邵静,高隽.基于协同感知的视觉选择注意计算模型[J].中国图象图形学报,2008,13(1):129-136.
[40]陈振学,刘成云,常发亮.基于生物视觉显著性的车辆车型识别[J].计算机科学,2010,37(2):207-209.
[41]田明辉,万寿红,岳丽华.自然场景中的视觉显著对象检测[J].中国图象图形学报,2010,15(11) : 1650-1657.
[42] A. Oliva, A. Torralba, M. Castelhano, J. Henderson.Top-down control of visual attention in object detection[C]. Internat:Conf. on Image Processing, 2003,253-256.
[43] Fred H. Hamker.Modeling feature-based attention as an active top-down inference process.2006,86(1-3):91-99.
[44]邵静.一种基于视觉注意机制的感知物体提取算法[J].现代电子技术,2010,33(20) : 71-74.
[45] NAVALPAKKAM, V.,ITTI, L..Modeling the influence of task on attention[J].Vision Research,2005,45(2):205–231.
[46] Jin-Kui Chu,Rong-Hua Li,Qing-Ying Li,Hong-Qing Wang. A Visual Attention Model for Robot Object Tracking[J]. International journal of automation and computing,2010,7(1):39-46.
[47] Fahad Shahbaz Khan, Joost van de Weijer, Maria Vanrell.Top-Down Color Attention for Object Recognition[J]. Computer Vision.2009:979-986.
[48]于江波,陈后金,李居朋.视觉选择注意机制模型及其应用[J].电子测量与仪器学报,2008,22(4):100-103.
[49]邵静.一种基于视觉注意机制的感知物体提取算法[J].现代电子技术,2010,33(20) : 71-74.
[50]张杰,魏维.基于视觉注意力模型的显著性提取[J].计算机技术与发展,2010,20( 11) : 109-113.
[51]田明辉,万寿红,岳丽华.自然场景中的视觉显著对象检测[J].中国图象图形学报,2010,15(11) : 1650-1657.
[52]孙瑾秋,张艳宁,周军.基于选择性视觉注意机制和曲线发现法的弱小目标检测[J].吉林大学学报(工学版),2010,40( 6) : 1683-1687.
[53] Fahad Shahbaz Khan, Joost van de Weijer, Maria Vanrell.Top-Down Color Attention for Object Recognition[J]. Computer Vision.2009,38(3):979-986.
[54]张剑飞.贝叶斯网络学习方法和算法研究[D].东北师范大学, 2005.
[55]胡玉胜,涂序彦,崔晓瑜,程乾生.基于贝叶斯网络的不确定性知识的推理方法[J].计算机集成制造系统,2001, 7(12):65-68.
[56]黄可杰.基于DSP/IP模块的林区火焰监控系统关键技术研究[D].杭州电子科技大学, 2011.