Research Interests:
Research Interests:
Research Interests:
Primary vaginal cancer is a rare disease for which treatment has been modeled based on cervical cancer. We report our experience in the use of image-guided adaptive brachytherapy (IGABT) in this indication. Patients treated for vaginal... more
Primary vaginal cancer is a rare disease for which treatment has been modeled based on cervical cancer. We report our experience in the use of image-guided adaptive brachytherapy (IGABT) in this indication. Patients treated for vaginal cancer with a combination of external beam radiation therapy and IGABT were identified through electronic search. The Groupe Européen de Curiethérapie-European Society for Radiotherapy and Oncology recommendations for cervical cancer have been extrapolated with the definition of two clinical target volumes (CTVs) corresponding to the residual disease after external beam radiation therapy (CTV), assessed from clinical and imaging findings, and the so-called CTV, comprising the CTV with directional margins and at least the initial disease at diagnosis. Twenty-seven patients were identified. MRI was used for brachytherapy guidance in 82% of the cases. An interstitial component was used in 59% of the cases. The D CTV and D CTV were 73.1 ± 12.8 Gy and 66.6...
Research Interests:
Research Interests:
Research Interests: Engineering, Computer Science, Algorithms, Computer Graphics, Artificial Intelligence, and 14 moreImage Processing, Data Mining, Pattern Recognition, Productivity, Image Registration, Automation, Aerial Photography, Change detection, Matching, Reliability, Resonance, Shadows, Pixels, and Model Building
With the increasing use of simultaneous integrated boost in the treatment of cervical cancer, there is a need to anticipate the brachytherapy (BT) contribution at the level of the pathologic pelvic lymph nodes. This study aimed to report... more
With the increasing use of simultaneous integrated boost in the treatment of cervical cancer, there is a need to anticipate the brachytherapy (BT) contribution at the level of the pathologic pelvic lymph nodes. This study aimed to report the dose delivered at their level during BT. Patients with pelvic nodal involvement and treated with a combination of chemoradiation followed by image-guided adaptive pulsed-dose-rate BT were selected. On per BT three-dimensional images, pelvic lymphadenopathies were delineated, without planning aim. For the purposes of the study, D100, D98, D90, and D50 were reviewed and converted in 2-Gy equivalent doses, using the linear quadratic model with an α/β of 10 Gy. Ninety-one patients were identified, allowing evaluation at the level of 226 lymphadenopathies. The majority of them were external iliac (48%), followed by common iliac (25%), and internal iliac (16%) regions. The 2-Gy equivalent doses D98 were 4.4 ± 1.9 Gy, 5.4 ± 3.1 Gy, and 4.3 ± 2.1 Gy for...
Research Interests:
Research Interests:
Machine perception can benefit from the use of features extracted from data provided by a variety of sensor modal- ities. Recent advances in sensor design makes it possible to incorporate multiple sensors into vision systems for increased... more
Machine perception can benefit from the use of features extracted from data provided by a variety of sensor modal- ities. Recent advances in sensor design makes it possible to incorporate multiple sensors into vision systems for increased capability. Two important issues must be con- sidered for the integration task: The sensors must be spa- tially coregistered and the phenomenologies must
Research Interests:
Research Interests:
Unmanned planetary landers to date have landed "blind"; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn... more
Unmanned planetary landers to date have landed "blind"; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn constrains the scientific agenda of missions. The state of the art Entry, Descent, and Landing (EDL) technology can land a spacecraft on Mars somewhere within a 20-100km landing ellipse. Landing ellipses are very likely to contain hazards such as craters, discontinuities, steep slopes, and large rocks, than can cause mission-fatal damage. We briefly review sensor options for landing hazard detection and identify a perception approach based on stereo vision and shadow analysis that addresses the broadest set of missions. Our approach fuses stereo vision and monocular shadow-based rock detection to maximize spacecraft safety. We summarize performance models for slope estimation and rock detection within this approach and validate those models experimentally....
Research Interests:
Detecting water hazards is a significant challenge to unmanned ground vehicle autonomous off-road navigation. This paper focuses on detecting the presence of water during the daytime using color cameras. A multi-cue approach is taken.... more
Detecting water hazards is a significant challenge to unmanned ground vehicle autonomous off-road navigation. This paper focuses on detecting the presence of water during the daytime using color cameras. A multi-cue approach is taken. Evidence of the presence of water is generated from color, texture, and the detection of reflections in stereo range data. A rule base for fusing water cues was developed by evaluating detection results from an extensive archive of data collection imagery containing water. This software has been implemented into a run-time passive perception subsystem and tested thus far under Linux on a Pentium based processor.
Research Interests:
this report derives from an earlier system described in [Noronha & Nevatia, 1997]; a block diagram is shown in Figure 1.1. The approach is basically one of hypothesize and verify. Hypotheses for potential roofs are made from fragmented... more
this report derives from an earlier system described in [Noronha & Nevatia, 1997]; a block diagram is shown in Figure 1.1. The approach is basically one of hypothesize and verify. Hypotheses for potential roofs are made from fragmented lowerlevel image features. The system is hierarchical and uses evidence from all the views in a non-preferential, order-independent way. Promising hypotheses are selected among these by using relatively inexpensive evidence from the rooftops only. The selected hypotheses are then verified by using more reliable global evidence. The verified hypotheses are then examined for overlap that may result in either elimination or in the merging of them. Cues from a depth map (such as IFSAR or a DEM) can be incorporated at the hypotheses formation, selection, or verification stages
Unmanned planetary landers to date have landed "blind"; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn... more
Unmanned planetary landers to date have landed "blind"; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn constrains the scientific agenda of missions. The state of the art Entry, Descent, and Landing (EDL) technology can land a spacecraft on Mars somewhere within a very large landing ellipse (20-100 km). However, even if a landing ellipse is only a few kilometers long, it is very likely to contain hazards such as craters, discontinuities, steep slopes, and large rocks, regardless of how the ellipse is selected. A lander that encounters a large rock, falls off a cliff, or tips over on a steep slope can sustain mission-fatal damage. In this paper, we will briefly review sensor options for landing hazard detection and identify an approach based on stereo vision and shadow analysis that addresses the broadest set of missions. We present the hazard detection appro...
Research Interests:
Improvements to the rock-counting software that segments shadows in HiRISE images and correctly predicted the distributions later found by the Phoenix lander have been made and results at the four Mars Science Laboratory landing sites are... more
Improvements to the rock-counting software that segments shadows in HiRISE images and correctly predicted the distributions later found by the Phoenix lander have been made and results at the four Mars Science Laboratory landing sites are presented.
Research Interests:
An effective 3D method incorporating user assistance for modeling complex buildings is proposed. This method utilizes the connectivity and similar structure information among unit blocks in a multi-component building structure, to enable... more
An effective 3D method incorporating user assistance for modeling complex buildings is proposed. This method utilizes the connectivity and similar structure information among unit blocks in a multi-component building structure, to enable the user to incrementally construct models of many types of buildings. The system attempts to minimize the time and the number of user interactions needed to assist an
Research Interests:
3-D building detection and description is a practical application of 3-D object description, a key task of computer vision. We present an approach to detecting and describing buildings of polygonal rooftops by using multiple, overlapping... more
3-D building detection and description is a practical application of 3-D object description, a key task of computer vision. We present an approach to detecting and describing buildings of polygonal rooftops by using multiple, overlapping images of the scene. First, 3-D features are generated by using multiple images, and rooftop hypotheses are generated by neighborhood searches on those features. For
Research Interests:
An important application of machine vision is to provide a means to monitor a scene over a period of time and report changes in the content of the scene. We have developed a validation mechanism that implements the first step towards a... more
An important application of machine vision is to provide a means to monitor a scene over a period of time and report changes in the content of the scene. We have developed a validation mechanism that implements the first step towards a system for detecting changes in images of aerial scenes. By validation we mean the confirmation of the presence
Research Interests:
Surface characteristics at the six sites where spacecraft have successfully landed on Mars can be related favorably to their signatures in remotely sensed data from orbit and from the Earth. Comparisons of the rock abundance, types and... more
Surface characteristics at the six sites where spacecraft have successfully landed on Mars can be related favorably to their signatures in remotely sensed data from orbit and from the Earth. Comparisons of the rock abundance, types and coverage of soils (and their physical properties), thermal inertia, albedo, and topographic slope all agree with orbital remote sensing estimates and show that
Research Interests:
Research Interests:
Landing spacecraft safely on Mars is a fundamental concern for mission planning. One recognized hazard is the presence of boulders large enough to tilt or damage the lander. We investigate the safety of the candidate landing sites for the... more
Landing spacecraft safely on Mars is a fundamental concern for mission planning. One recognized hazard is the presence of boulders large enough to tilt or damage the lander. We investigate the safety of the candidate landing sites for the MSL rover, set to launch in 2009, by calculating the abundance and spatial distribution of large (>1.5 m) rocks using Mars
Research Interests:
The size-frequency distributions of rocks in HiRISE images follow exponential models developed from lander measurements of smaller rocks and are extrapolated to smaller diameter to estimate the number of rocks in the Phoenix robotic arm... more
The size-frequency distributions of rocks in HiRISE images follow exponential models developed from lander measurements of smaller rocks and are extrapolated to smaller diameter to estimate the number of rocks in the Phoenix robotic arm workspace.
Research Interests:
Research Interests:
ABSTRACT The Hazard Detection System (HDS) is a component of the ALHAT (Autonomous Landing and Hazard Avoidance Technology) suite of sensor systems, which together provide a lander Guidance, Navigation and Control (GN&C) system... more
ABSTRACT The Hazard Detection System (HDS) is a component of the ALHAT (Autonomous Landing and Hazard Avoidance Technology) suite of sensor systems, which together provide a lander Guidance, Navigation and Control (GN&C) system with the relevant measurements necessary to enable safe precision landing under any lighting conditions. The HDS consists of a stand-alone compute element (CE), an Inertial Measurement Unit (IMU), and a gimbaled flash-LIDAR sensor that are used, in real-time, to generate a Digital Elevation Map (DEM) of the landing terrain, detect candidate safe landing sites for the vehicle through Hazard Detection (HD), and generate the site-relative navigation measurements (known as Hazard Relative Navigation - HRN) used for safe precision landing. The challenges with the architecture and implementation of the HDS involve the fusion of multiple, asynchronous sensor measurements required for precision pointing of a narrow-field-of-view LIDAR to gather an overlapping mosaic of terrain images, along with significant real-time processing requirements to generate and process the DEM for HD and subsequent LIDAR images for HRN. In December 2012, the first-generation HDS underwent a rigorous field test campaign at the Kennedy Space Center where the ALHAT sensors were flown onboard a NASA UH-1H helicopter that conducted descent profiles toward a Lunar terrain field constructed at the end of the Shuttle Landing Facility (SLF). During the test the HDS constructed seamless DEMs from mosaicked flash LIDAR images and correctly identified safe landing sites on the Lunar terrain field in real-time. This paper provides an overview of the HDS architecture and summarizes its real-time performance during the helicopter test campaign, along with the lessons learned and revisions necessary to enable successful, future flight tests onboard the NASA Morpheus free-flying, rocket-powered terrestrial test vehicle at the SLF Lunar-terrain field.
Research Interests:
Research Interests:
Research Interests:
We describe a system for detection and description of buildings in aerial scenes. This is a difficult task as the aerial images contain a variety of objects. Low-level segmentation processes give highly fragmented segments due to a number... more
We describe a system for detection and description of buildings in aerial scenes. This is a difficult task as the aerial images contain a variety of objects. Low-level segmentation processes give highly fragmented segments due to a number of reasons. We use a perceptual grouping approach to collect these fragments and discard those that come from other sources. We use shape properties of the buildings for this. We use shadows and walls to help form and verify the hypotheses generated by the grouping process. This latter step also provides 3-D descriptions of the buildings. Our system has been tested on a number of examples and is able to work with overhead or oblique views.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT Unmanned planetary landers to date have landed ¿blind¿; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn... more
ABSTRACT Unmanned planetary landers to date have landed ¿blind¿; that is, without the benefit of onboard landing hazard detection and avoidance systems. This constrains landing site selection to very benign terrain, which in turn constrains the scientific agenda of missions. Systems for automatic surface reconstruction and for hazard detection, mapping, and assessment are becoming mature. Before they can be put to practical use, it is essential to be able to characterize their performance for the purposes of scientific evaluation and their utility to engineers planning and designing landed missions. It is also important to be able to predict performance for a variety of scenarios. The evaluation metrics need to be simple enough to be readily comprehensible but still to capture the important relevant performance parameters. In this paper we describe the process, metrics, results, and algorithm improvement recommendations from the evaluation of the performance of the hazard detection and avoidance (HDA) algorithms developed in the Autonomous Landing and Hazard Avoidance Technology (ALHAT) Project by means of Monte Carlo simulation of thousands of Lunar landings.
Research Interests: Engineering, Computer Science, Monte Carlo Simulation, Propulsion, Probability, and 13 moreMonte Carlo Methods, Performance Evaluation, Moon Landing, Aerospace Industry, Remotely Operated Vehicles, Surface Reconstruction, Site Selection, High resolution satelite image, HAZARD, Terrain, Hazards, Space Missions, and Laser Radar
Research Interests: Engineering, Program Evaluation, Computer Science, Software Architecture, Parallel Processing, and 13 moreSoftware Design, Autonomous navigation, Stereo Vision, Environmental protection, Infrared, Autonomous Vehicle, Terrain, Ranging, Local Area Network, Data Processing, Real Time Operating System, Commercial Off-The-Shelf, and Jet Propulsion Laboratory
Research Interests:
Research Interests:
Research Interests:
Research Interests: Engineering, Robotics, Computer Science, Algorithms, Artificial Intelligence, and 15 moreIntelligent Control, Proceedings, Sensors, ROBOT, Man, Human Robot Interaction, Research and Development, Long Range, Polarization, Dynamic Environment, Pedestrian Detection, Front end, Region of Interest, Far Field, and Jet Propulsion Laboratory
Research Interests: Engineering, Computer Science, Artificial Intelligence, Computer Vision, Remote Sensing, and 13 moreCalibration, Autonomous navigation, Stereo Vision, Obstacle Detection, Infrared, Terrain, Pedestrian Detection, Thermal Infrared, Terrain Classification, LWIR, Unmanned Ground Vehicle, Stereo Camera, and Jet Propulsion Laboratory
Research Interests:
Research Interests:
Range data contains direct 3-D information about a scene. However, the resolution of such data is typi- cally lower than that of electro-optical (EO) images and the data may have many missing or highly erro- neous elements. We propose to... more
Range data contains direct 3-D information about a scene. However, the resolution of such data is typi- cally lower than that of electro-optical (EO) images and the data may have many missing or highly erro- neous elements. We propose to use range data to provide cues for more accurate reconstruction using the EO images. It is shown that such cues can not only greatly improve the efficiency of the automatic system but also improve the quality of the results. Quantitative evaluations are given. 1 Introduction and Overview
Research Interests:
Research Interests:
We present a model-based approach to detecting and describing compositions of buildings with complex roof- tops. Previous approaches have dealt with either simpler models or models which lack geometric information. In spite of increasing... more
We present a model-based approach to detecting and describing compositions of buildings with complex roof- tops. Previous approaches have dealt with either simpler models or models which lack geometric information. In spite of increasing model complexity, we maintain the computation affordable by effectively using multiple over- lapping images. We obtain rooftop hypotheses in 3-D by using 3-D lines and junctions
Research Interests:
An important application of machine vision is to provide a means to monitor a scene over a period of time and report changes in the content of the scene. We have developed a validation mechanism that implements the first step towards a... more
An important application of machine vision is to provide a means to monitor a scene over a period of time and report changes in the content of the scene. We have developed a validation mechanism that implements the first step towards a system for detecting changes in images of aerial scenes. By validation we mean the confirmation of thepresence of model objects in the image. Our system uses a 3-0 site model of the scene as a basis for model validation, and eventually for detecting changes and to update the site model. The scenario for our present validation system consists of adding a new image to a database associated with the site. The validation process is implemented in three steps: registration of the image to the model, or equivalently, determination of the position and orientation of the camera; matching of model features to image features; and validation of the objects in the model. Our system processes the new image monocularly and uses shadows as 3-0 clues to help validate the model. The system has been tested using a hand-generated site model and several images of a 500:l scale model of the site, acpired form several viewpoints.
Research Interests:
Research Interests:
Research Interests:
Research Interests: Robotics, Computer Science, Artificial Intelligence, Computer Vision, Image Processing, and 15 moreStereopsis, Planetary exploration, Navigation, FPGA implementation, Noise reduction, Feature tracking, Stereo Vision, Obstacle Detection, Field Programmable Gate Array, Solar System, Spacecraft, SLIP, Computer, Mars Exploration Rover Spirit, and Odometer
Research Interests:
In a recent paper by J.S. Chen et al. (ibid., vol.PAMI-9, p.584-90, July 1987) the authors presented a means of decomposing the Laplacian-of-Gaussian (LoG) kernel into the product of a Gaussian and a (smaller) LoG mask. They then... more
In a recent paper by J.S. Chen et al. (ibid., vol.PAMI-9, p.584-90, July 1987) the authors presented a means of decomposing the Laplacian-of-Gaussian (LoG) kernel into the product of a Gaussian and a (smaller) LoG mask. They then proceeded to develop a fast algorithm for convolution which exploits the spatial frequency properties of these operators to allow the image to be decimated (subsampled). Although this approach is both novel and interesting, it is contended that the exposition suffers from some inconsistencies and minor errors. The commenters clarify matters for those who wish to implement this technique. The original authors acknowledge two of the three points raised, and provide further clarification of the other one namely, the claim that the masks (Gaussian and LoG) are too small