In this paper, we describe our recent efforts in grouping sensory data into meaningful entities. Our grouping philosophy is based on perceptual organization principles using gestalt hypotheses where we impose structural regularity on sensory primitives stemming from a common underlying cause. We present results using field data from UGVs and outline the utility of our research in object recognition and tracking for autonomous vehicle navigation. In addition, we show how the grouping efforts can be useful for constructing symbolic topological maps when data from different sensing modalities are fused in a bottom-up and top-down fashion
{"title":"Grouping sensory primitives for object recognition and tracking","authors":"R. Madhavan, Mike Foedisch, Tommy Chang, T. Hong","doi":"10.1109/AIPR.2005.29","DOIUrl":"https://doi.org/10.1109/AIPR.2005.29","url":null,"abstract":"In this paper, we describe our recent efforts in grouping sensory data into meaningful entities. Our grouping philosophy is based on perceptual organization principles using gestalt hypotheses where we impose structural regularity on sensory primitives stemming from a common underlying cause. We present results using field data from UGVs and outline the utility of our research in object recognition and tracking for autonomous vehicle navigation. In addition, we show how the grouping efforts can be useful for constructing symbolic topological maps when data from different sensing modalities are fused in a bottom-up and top-down fashion","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132928580","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}
We are proposing a new electromagnetic (EM) solution for concealed weapons detection at a distance. Our proposed approach exploits the fact that the weapons of interest for detection, whether they are a hand gun, knife, box cutter, etc, each have a unique set of EM characteristics. The particular novelty of our technical solution for concealed weapons detection at a distance lies in the use of millimeter-wave (mm-wave) signals over a wide frequency band (26-40 GHz or Ka-band) to excite natural resonances in the weapon and create a unique spectral signature that can be used to characterize the object. By using such excitation signals in the mm-wave frequency band, benefits such as increased resolution and reduced component size can be realized. In addition, the use of a wideband mm-wave excitation signal provides an enhanced EM signature for the target that exhibits more features available for classifying the object
{"title":"Millimeter-wave weapons detection system","authors":"D. Novak, R. Waterhouse, A. Farnham","doi":"10.1109/AIPR.2005.34","DOIUrl":"https://doi.org/10.1109/AIPR.2005.34","url":null,"abstract":"We are proposing a new electromagnetic (EM) solution for concealed weapons detection at a distance. Our proposed approach exploits the fact that the weapons of interest for detection, whether they are a hand gun, knife, box cutter, etc, each have a unique set of EM characteristics. The particular novelty of our technical solution for concealed weapons detection at a distance lies in the use of millimeter-wave (mm-wave) signals over a wide frequency band (26-40 GHz or Ka-band) to excite natural resonances in the weapon and create a unique spectral signature that can be used to characterize the object. By using such excitation signals in the mm-wave frequency band, benefits such as increased resolution and reduced component size can be realized. In addition, the use of a wideband mm-wave excitation signal provides an enhanced EM signature for the target that exhibits more features available for classifying the object","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134032081","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}
Diffuse optical tomography (DOT) poses a typical ill-posed inverse problem with limited number of measurements and inherently low spatial resolution. In this paper, we propose a hierarchical Bayesian approach to improve spatial resolution and quantitative accuracy by using a priori information provided by a secondary high resolution anatomical imaging modality, such as magnetic resonance (MR) or X-ray. The proposed hierarchical Bayesian approach allows incorporation of partial a priori knowledge about the noise and unknown optical image models, thereby capturing the function-anatomy correlation effectively. Numerical simulations demonstrate that the proposed method avoids undesirable bias towards anatomical prior information and leads to significantly improved spatial resolution and quantitative accuracy
{"title":"Hierarchical Bayesian algorithm for diffuse optical tomography","authors":"M. Guven, B. Yazıcı, X. Intes, B. Chance","doi":"10.1109/AIPR.2005.30","DOIUrl":"https://doi.org/10.1109/AIPR.2005.30","url":null,"abstract":"Diffuse optical tomography (DOT) poses a typical ill-posed inverse problem with limited number of measurements and inherently low spatial resolution. In this paper, we propose a hierarchical Bayesian approach to improve spatial resolution and quantitative accuracy by using a priori information provided by a secondary high resolution anatomical imaging modality, such as magnetic resonance (MR) or X-ray. The proposed hierarchical Bayesian approach allows incorporation of partial a priori knowledge about the noise and unknown optical image models, thereby capturing the function-anatomy correlation effectively. Numerical simulations demonstrate that the proposed method avoids undesirable bias towards anatomical prior information and leads to significantly improved spatial resolution and quantitative accuracy","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126022364","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}
There is an immediate requirement for law enforcement and homeland security to identify concealed weapons which may present a threat to official personnel and the general public. This involves suicide bomb vests, handguns, knife blades, and other threatening weapons. The weapons may be composed of a large range of materials such as metals, nonmetals, plastics and explosives. The Homeland Security Advanced Research Projects Agency (HSARPA) and the National Institute of Justice (NIJ) are presently funding programs collectively covering all relevant portions of the electromagnetic spectrum and ultrasound in order to detect these weapons through the various materials that may be used to conceal these weapons This paper outlines the various imaging techniques being investigated and present results where available
{"title":"An overview of concealed weapons detection for homeland security","authors":"Peter J. Costianes","doi":"10.1109/AIPR.2005.17","DOIUrl":"https://doi.org/10.1109/AIPR.2005.17","url":null,"abstract":"There is an immediate requirement for law enforcement and homeland security to identify concealed weapons which may present a threat to official personnel and the general public. This involves suicide bomb vests, handguns, knife blades, and other threatening weapons. The weapons may be composed of a large range of materials such as metals, nonmetals, plastics and explosives. The Homeland Security Advanced Research Projects Agency (HSARPA) and the National Institute of Justice (NIJ) are presently funding programs collectively covering all relevant portions of the electromagnetic spectrum and ultrasound in order to detect these weapons through the various materials that may be used to conceal these weapons This paper outlines the various imaging techniques being investigated and present results where available","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123301488","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}
E. Uzgiris, Deborah Lee, A. Sood, Kathleen Bove, Stephen J. Lomnes
The multimodal polymeric contrast agents for MRI and fluorescence imaging in the management of cancer are discussed. The paper presents preliminary data that suggest that a simple experimental protocol can provide at least an index of the permeability parameter if not the absolute permeability itself.
{"title":"Multimodal polymeric contrast agents for MRI and fluorescence imaging in the management of cancer","authors":"E. Uzgiris, Deborah Lee, A. Sood, Kathleen Bove, Stephen J. Lomnes","doi":"10.1109/AIPR.2005.36","DOIUrl":"https://doi.org/10.1109/AIPR.2005.36","url":null,"abstract":"The multimodal polymeric contrast agents for MRI and fluorescence imaging in the management of cancer are discussed. The paper presents preliminary data that suggest that a simple experimental protocol can provide at least an index of the permeability parameter if not the absolute permeability itself.","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125348849","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：