Describes application of scale-space clustering to the classification of a multispectral and polarimetric SAR image of an agricultural site. After polarimetric and radiometric calibration and noise cancellation, the authors extracted a 12-dimensional feature vector for each pixel from the scattering matrix. The algorithm was able to partition without supervision a set of unlabeled vectors from 13 selected sites, each site corresponding to a distinct crop, into 13 clusters. The cluster parameters were then used to classify the whole image. The classification map is much less noisy and more accurate than those obtained by hierarchical rules. The algorithm can handle variabilities in cluster densities, cluster sizes and ellipsoidal shapes.<>
{"title":"Scale-space clustering and classification of SAR images with numerous attributes and classes","authors":"Yiu-fai Wong, E. Posner","doi":"10.1109/ACV.1992.240325","DOIUrl":"https://doi.org/10.1109/ACV.1992.240325","url":null,"abstract":"Describes application of scale-space clustering to the classification of a multispectral and polarimetric SAR image of an agricultural site. After polarimetric and radiometric calibration and noise cancellation, the authors extracted a 12-dimensional feature vector for each pixel from the scattering matrix. The algorithm was able to partition without supervision a set of unlabeled vectors from 13 selected sites, each site corresponding to a distinct crop, into 13 clusters. The cluster parameters were then used to classify the whole image. The classification map is much less noisy and more accurate than those obtained by hierarchical rules. The algorithm can handle variabilities in cluster densities, cluster sizes and ellipsoidal shapes.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129487601","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}
The authors present an interactive map conversion system which combines a human operator's high level reasoning with machine perception under the Human-Machine Perceptual Cooperation (HMPC) paradigm. HMPC defines two channels of interaction: the focus of attention (FOA) by which the user directs the attention of machine perception, and context. As the user moves the FOA across a raster map display via a pointing device, a smart cursor operates proactively on the data highlighting objects for extraction. The FOA permits foveal emphasis, enabling the user to vary motor precision with map clutter. HMPC provides for contexts at four levels of abstraction. This permits the efficiency of the system to degrade gracefully as data quality worsens. They also present a boundary-based line follower which computes line thickness, and an isolated symbol extractor based on feature-vectors.<>
{"title":"Interactive map conversion: combining machine vision and human input","authors":"F. Quek, Michael C. Petro","doi":"10.1109/ACV.1992.240304","DOIUrl":"https://doi.org/10.1109/ACV.1992.240304","url":null,"abstract":"The authors present an interactive map conversion system which combines a human operator's high level reasoning with machine perception under the Human-Machine Perceptual Cooperation (HMPC) paradigm. HMPC defines two channels of interaction: the focus of attention (FOA) by which the user directs the attention of machine perception, and context. As the user moves the FOA across a raster map display via a pointing device, a smart cursor operates proactively on the data highlighting objects for extraction. The FOA permits foveal emphasis, enabling the user to vary motor precision with map clutter. HMPC provides for contexts at four levels of abstraction. This permits the efficiency of the system to degrade gracefully as data quality worsens. They also present a boundary-based line follower which computes line thickness, and an isolated symbol extractor based on feature-vectors.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130249510","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}
Describes a visual processing algorithm that supports autonomous road following. The algorithm requires that lane markings be present and attempts to track the lane markings on both lane boundaries. There are three stages of computation: extracting edges; matching extracted edge points with a geometric model of the road, and updating the geometric road model. All processing is confined to the 2-D image plane. No information about the motion of the vehicle is used. This algorithm has been implemented and tested using video taped road scenes. It performs robustly for both highways and rural roads. The algorithm runs at a sampling rate of 15 Hz and has a worst case latency of 139 milliseconds (ms). The algorithm is implemented under the NASA/NBS Standard Reference Model for Telerobotic Control System Architecture (NASREM) architecture and runs on a dedicated vision processing engine and a VME-based microprocessor system.<>
{"title":"Visual processing for autonomous driving","authors":"Henry Schneiderman, M. Nashman","doi":"10.1109/ACV.1992.240315","DOIUrl":"https://doi.org/10.1109/ACV.1992.240315","url":null,"abstract":"Describes a visual processing algorithm that supports autonomous road following. The algorithm requires that lane markings be present and attempts to track the lane markings on both lane boundaries. There are three stages of computation: extracting edges; matching extracted edge points with a geometric model of the road, and updating the geometric road model. All processing is confined to the 2-D image plane. No information about the motion of the vehicle is used. This algorithm has been implemented and tested using video taped road scenes. It performs robustly for both highways and rural roads. The algorithm runs at a sampling rate of 15 Hz and has a worst case latency of 139 milliseconds (ms). The algorithm is implemented under the NASA/NBS Standard Reference Model for Telerobotic Control System Architecture (NASREM) architecture and runs on a dedicated vision processing engine and a VME-based microprocessor system.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130098025","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}
Using active monocular vision for 3-D visual control tasks is difficult since the translational and the rotational degrees of freedom are strongly coupled. The paper addresses several issues in 3-D visual control and presents adaptive control schemes for the problem of robotic visual servoing (eye-in-hand configuration) around a static rigid target. The objective is to move the image projections of several feature points of the static rigid target to some desired image positions. The inverse perspective transformation is assumed partially unknown. The adaptive controllers compensate for the servoing errors, the partially unknown camera parameters, and the computational delays which are introduced by the time-consuming vision algorithms. The authors present a stability analysis along with a study of the conditions that the feature points must satisfy in order for the problem to be solvable. Finally, several experimental results are presented to verify the validity and the efficacy of the proposed algorithms.<>
{"title":"Adaptive control techniques for dynamic visual repositioning of hand-eye robotic systems","authors":"N. Papanikolopoulos, P. Khosla","doi":"10.1109/ACV.1992.240321","DOIUrl":"https://doi.org/10.1109/ACV.1992.240321","url":null,"abstract":"Using active monocular vision for 3-D visual control tasks is difficult since the translational and the rotational degrees of freedom are strongly coupled. The paper addresses several issues in 3-D visual control and presents adaptive control schemes for the problem of robotic visual servoing (eye-in-hand configuration) around a static rigid target. The objective is to move the image projections of several feature points of the static rigid target to some desired image positions. The inverse perspective transformation is assumed partially unknown. The adaptive controllers compensate for the servoing errors, the partially unknown camera parameters, and the computational delays which are introduced by the time-consuming vision algorithms. The authors present a stability analysis along with a study of the conditions that the feature points must satisfy in order for the problem to be solvable. Finally, several experimental results are presented to verify the validity and the efficacy of the proposed algorithms.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130268615","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}
A system for automatic data acquisition from topographic maps (PROMAP-Processing of Maps) is presented. Maps are an important source of information for efficient spatial data evaluation using Geographic Information Systems (GIS). At present a lot of relevant maps have still to be digitized manually, which is a time-consuming and error-prone process. To improve the situation, the authors developed the PROMAP-system which incorporates adequate image analyzing methods. The system is capable of generating a symbolic description of the map contents that may be imported into a GIS (e.g. ARC/INFO).<>
介绍了一种地形图数据自动采集系统(PROMAP-Processing of maps)。地图是利用地理信息系统(GIS)进行有效空间数据评估的重要信息来源。目前，很多相关地图还需要手工数字化，这是一个耗时且容易出错的过程。为了改善这种情况，作者开发了promap系统，其中包含了足够的图像分析方法。该系统能够生成可导入GIS(例如ARC/INFO)的地图内容的符号描述。
{"title":"PROMAP-a system for analysis of topographic maps","authors":"B. Lauterbach, N. Ebi, P. Besslich","doi":"10.1109/ACV.1992.240328","DOIUrl":"https://doi.org/10.1109/ACV.1992.240328","url":null,"abstract":"A system for automatic data acquisition from topographic maps (PROMAP-Processing of Maps) is presented. Maps are an important source of information for efficient spatial data evaluation using Geographic Information Systems (GIS). At present a lot of relevant maps have still to be digitized manually, which is a time-consuming and error-prone process. To improve the situation, the authors developed the PROMAP-system which incorporates adequate image analyzing methods. The system is capable of generating a symbolic description of the map contents that may be imported into a GIS (e.g. ARC/INFO).<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122889536","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}
Presents a new algorithm for interframe interpolation of cinematic sequences. The authors demonstrate its applicability to video data compression of pedestrian traffic and data compression for video conferencing. In both of these applications it is assumed that the background is nearly stationary and that there are no interobject occlusions. The interpolation algorithm makes use of estimates of optical flow to compensate for the motion of objects between two frames. We describe three major problems associated with motion compensated cinematic interpolation: interframe occlusion, interframe zooming and figure-ground ambiguity. Our algorithm suppresses artifacts caused by all three of these problems.<>
{"title":"Interpolation of cinematic sequences","authors":"Jordi Ribas-Corbera, J. Sklansky","doi":"10.1109/ACV.1992.240329","DOIUrl":"https://doi.org/10.1109/ACV.1992.240329","url":null,"abstract":"Presents a new algorithm for interframe interpolation of cinematic sequences. The authors demonstrate its applicability to video data compression of pedestrian traffic and data compression for video conferencing. In both of these applications it is assumed that the background is nearly stationary and that there are no interobject occlusions. The interpolation algorithm makes use of estimates of optical flow to compensate for the motion of objects between two frames. We describe three major problems associated with motion compensated cinematic interpolation: interframe occlusion, interframe zooming and figure-ground ambiguity. Our algorithm suppresses artifacts caused by all three of these problems.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131512752","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}
Gin-Shu Young, T. Hong, M. Herman, Jackson C. S. Yang
To operate autonomous vehicles safely, obstacles must be detected before any path planning and obstacle avoidance activity is undertaken. In the paper, a novel approach to obstacle detection is developed. New visual linear invariants based on optical flow have been developed. Employing the linear invariance property, obstacles an be directly detected by using a reference flow line obtained from measured optical flow. This method can be used for ground vehicles to navigate through man-made roadways or natural outdoor terrain or for air vehicles to land on known or unknown terrain.<>
{"title":"New visual invariants for obstacle detection using optical flow induced from general motion","authors":"Gin-Shu Young, T. Hong, M. Herman, Jackson C. S. Yang","doi":"10.1109/ACV.1992.240322","DOIUrl":"https://doi.org/10.1109/ACV.1992.240322","url":null,"abstract":"To operate autonomous vehicles safely, obstacles must be detected before any path planning and obstacle avoidance activity is undertaken. In the paper, a novel approach to obstacle detection is developed. New visual linear invariants based on optical flow have been developed. Employing the linear invariance property, obstacles an be directly detected by using a reference flow line obtained from measured optical flow. This method can be used for ground vehicles to navigate through man-made roadways or natural outdoor terrain or for air vehicles to land on known or unknown terrain.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131757970","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}
The paper reports on the development of a machine vision system for assessing targeting accuracy of ballistic, projectile-firing weapon systems. Current techniques rely on either manual optical sighting or acoustic signature to locate the point of impact. Optical sighting, still the predominant method in many events, is manual and imprecise. Acoustic-based approaches automate the process but require multiple sensor placements. The machine vision system described is able to continuously monitor the target, report precise quantitative targeting information and simultaneously provide a color-coded display of impacts. Special provisions have been built-in to account for target plane motion and overlapping impacts phenomenon.<>
{"title":"Projectile impact detection and performance evaluation using machine vision","authors":"B. Mobasseri","doi":"10.1109/ACV.1992.240309","DOIUrl":"https://doi.org/10.1109/ACV.1992.240309","url":null,"abstract":"The paper reports on the development of a machine vision system for assessing targeting accuracy of ballistic, projectile-firing weapon systems. Current techniques rely on either manual optical sighting or acoustic signature to locate the point of impact. Optical sighting, still the predominant method in many events, is manual and imprecise. Acoustic-based approaches automate the process but require multiple sensor placements. The machine vision system described is able to continuously monitor the target, report precise quantitative targeting information and simultaneously provide a color-coded display of impacts. Special provisions have been built-in to account for target plane motion and overlapping impacts phenomenon.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114697969","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}
A video-based system for traffic monitoring is presented. The objective of the system is to set up a high-level description of the traffic scene comprising the position, speed and class of the vehicles. Algorithms for detecting moving objects, separating the vehicles from their shadows, tracking and classification are presented. The classification of vehicles under sunny conditions is very difficult, if the shadow isn't separated from the vehicles. This approach for classification runs in real-time on low-cost hardware. the shadow can be separated from the vehicle and the knowledge about the shape of the shadow can be efficiently used. The shadow analysis algorithm itself uses high-level knowledge about the geometry of the scene (heading of the observed road) and about global data (date and time).<>
{"title":"A shadow handler in a video-based real-time traffic monitoring system","authors":"M. Kilger","doi":"10.1109/ACV.1992.240332","DOIUrl":"https://doi.org/10.1109/ACV.1992.240332","url":null,"abstract":"A video-based system for traffic monitoring is presented. The objective of the system is to set up a high-level description of the traffic scene comprising the position, speed and class of the vehicles. Algorithms for detecting moving objects, separating the vehicles from their shadows, tracking and classification are presented. The classification of vehicles under sunny conditions is very difficult, if the shadow isn't separated from the vehicles. This approach for classification runs in real-time on low-cost hardware. the shadow can be separated from the vehicle and the knowledge about the shape of the shadow can be efficiently used. The shadow analysis algorithm itself uses high-level knowledge about the geometry of the scene (heading of the observed road) and about global data (date and time).<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131112316","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}
An automatic particle segmentation system is developed for calculating the size distribution of rock fragments created by blasting. A rock composite due to blasting is often fully multi-connected in which individual particles cannot be delineated by the existing segmentation algorithms. Two algorithms are proposed to approach this multi-connected segmentation problem. The first algorithm analyzes the shape of each shadow (a simply-connected region) and 'splits' the particles from shadow boundary convexity points if a relatively large gradient path occurs. The second algorithm finds clusters of rock particles which may not be delineated due to the lack of a strong gradient along the touching portions and delineates them using a shape heuristics. A large number of test results show that the method is fast and accurate.<>
{"title":"A segmentation method for multi-connected particle delineation","authors":"Xing-Qiang Wu, J. Kemeny","doi":"10.1109/ACV.1992.240305","DOIUrl":"https://doi.org/10.1109/ACV.1992.240305","url":null,"abstract":"An automatic particle segmentation system is developed for calculating the size distribution of rock fragments created by blasting. A rock composite due to blasting is often fully multi-connected in which individual particles cannot be delineated by the existing segmentation algorithms. Two algorithms are proposed to approach this multi-connected segmentation problem. The first algorithm analyzes the shape of each shadow (a simply-connected region) and 'splits' the particles from shadow boundary convexity points if a relatively large gradient path occurs. The second algorithm finds clusters of rock particles which may not be delineated due to the lack of a strong gradient along the touching portions and delineates them using a shape heuristics. A large number of test results show that the method is fast and accurate.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124296324","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：