Tier-scalable robotic reconnaissance missions are called for in extreme space environments, including planetary atmospheres, surfaces (both solid and liquid), and subsurfaces (e.g., oceans), as well as in potentially ...
详细信息
Tier-scalable robotic reconnaissance missions are called for in extreme space environments, including planetary atmospheres, surfaces (both solid and liquid), and subsurfaces (e.g., oceans), as well as in potentially hazardous or inaccessible operational areas on Earth. Such future missions will require increasing degrees of operational autonomy: (1) Automatic mapping of an operational area from different vantages (i.e., spaceborne, airborne, surface, subsurface); (2) automatic sensor deployment and sensor data gathering; (3) automatic feature extraction and target/region-of-interest/anomaly identification within the mapped operational area; (4) automatic target prioritization for follow-up or close-up (in-situ) examination; and (5) subsequent automatic, targeted deployment and navigation/relocation of agents/sensors (e.g., to follow up on transient events). We report on recent progress in developing an Earth-based (outdoors) robotic test bed for Tier-scalable Reconnaissance at the University of Arizona and Caltech for distributed, science-driven, and significantly less constrained (compared to state-of-the-art) reconnaissance of prime locations on a variety of planetary bodies, with particular focus on Saturn's moon Titan with its methane/hydrocarbon lakes and Mars. The test bed currently comprises several computer-controlled robotic surface vehicles, i.e., rovers and lake landers/boats equipped with a variety of sensors. To achieve a fully operational Tier-scalable Reconnaissance test bed, aerial platforms will be integrated as a next step. The robotic surface vehicles can be interactively or automatically controlled from anywhere in the world in near real-time via the Internet. The test bed enables the implementation, field-testing, and validation of algorithms and strategies for navigation, exploration, sensor deployment, sensor data gathering, feature extraction, anomaly detection, and science goal prioritization for autonomous planetary exploration. Furthermor
Collagenous colitis is prevalent among pathological diseases. Because of normal radiological and endoscopic appearances, the microscopic image of colon tissue is necessary and important material for investigation of t...
详细信息
Collagenous colitis is prevalent among pathological diseases. Because of normal radiological and endoscopic appearances, the microscopic image of colon tissue is necessary and important material for investigation of this disease. In this paper, a computerized system is developed for collagenous colitis diagnosis. First, colon tissues are colored with Mason trichrome to make sub-epithelial collagen band to be appeared in blue. Second, preprocessing is done on the microscopic image of colon tissue, and then Color histogram features in HSV color space and Haar Wavelet energy in detail coefficients of sub-band images are implemented to characterize the histological structure representation for tissue classification. KNN Classifier is selected for this classification, which segments the sub-epithelial collagen band from the image, and finally, thickness of sub-epithelial collagen band is determined by morphological operations. Abnormal case will be recognized if the thickness of sub-epithelial collagen band be more than 10 μm. Fifty clinical image samples were employed in the training and testing procedures for the evaluation of system performance. Through the applied classification it was revealed that collagenous colitis can be diagnosed accurately.
Road network detection from very high resolution satellite images is important for two main reasons. First, the detection result can be used in automated map making. Second, the detected network can be used in traject...
详细信息
Three dimensional range data provides useful information for computervision, computer graphics, and object recognition applications. For these, extracting the range data reliably is utmost important. Therefore, vario...
详细信息
Object range data provide valuable information in recognition and modeling applications. Therefore, it is extremely important to reliably extract the range data from a given object. There are various range scanners ba...
详细信息
Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from the target template subspace. Though effective, these L1 trackers require high computat...
详细信息
Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from the target template subspace. Though effective, these L1 trackers require high computational costs due to numerous calculations for ℓ 1 minimization. In addition, the inherent occlusion insensitivity of the ℓ 1 minimization has not been fully utilized. In this paper, we propose an efficient L1 tracker with minimum error bound and occlusion detection which we call Bounded Particle Resampling (BPR)-L1 tracker. First, the minimum error bound is quickly calculated from a linear least squares equation, and serves as a guide for particle resampling in a particle filter framework. Without loss of precision during resampling, most insignificant samples are removed before solving the computationally expensive ℓ 1 minimization function. The BPR technique enables us to speed up the L1 tracker without sacrificing accuracy. Second, we perform occlusion detection by investigating the trivial coefficients in the ℓ 1 minimization. These coefficients, by design, contain rich information about image corruptions including occlusion. Detected occlusions enhance the template updates to effectively reduce the drifting problem. The proposed method shows good performance as compared with several state-of-the-art trackers on challenging benchmark sequences.
Range scanners are getting more popular as their application areas expand. Among various range scanners used in applications, the single stripe triangulation based ones are promising for high resolution scanning. Unfo...
详细信息
This paper deals with the problem of deploying a team of flying robots to perform surveillance coverage missions over a terrain of arbitrary morphology. In such missions, a key factor for the successful completion is ...
详细信息
This paper deals with the problem of deploying a team of flying robots to perform surveillance coverage missions over a terrain of arbitrary morphology. In such missions, a key factor for the successful completion is the knowledge of the terrain's morphology. In this paper, we introduce a two-step centralized procedure to align optimally a swarm of flying vehicles for the aforementioned task. Initially, a single robot constructs a map of the area of interest using a novel monocular-vision-based approach. A state-of-the-art visual-SLAM algorithm tracks the pose of the camera while, simultaneously, building an incremental map of the surrounding environment. The map generated is processed and serves as an input in an optimization procedure using the cognitive adaptive methodology initially introduced in [1], [2]. The output of this procedure is the optimal arrangement of the robot team, which maximizes the monitored area. The efficiency of our approach is demonstrated using real data collected from aerial robots in different outdoor areas.
In this paper, a new method for signature identification and verification based on contourlet transform (CT) is proposed. This method uses contourlet coefficient as the feature extractor and Support Vector Machine (SV...
详细信息
Abstract In this paper, the relative position parameters of the target spacecraft are obtained by using the vision measurement and the target maneuver positions are calculated through the isochronous interpolation met...
详细信息
Abstract In this paper, the relative position parameters of the target spacecraft are obtained by using the vision measurement and the target maneuver positions are calculated through the isochronous interpolation method. Furthermore, new switch control laws under constant thrust are designed for active collision avoidance maneuver of the chaser along a specified trajectory. The switch control laws are obtained based on the acceleration sequences and the working times of thrusters in three axes which can be respectively computed by the time series analysis method. The perturbations and fuel consumptions are addressed during the computation of the working times. The simulation results show that the constant thrust maneuver can effectively guarantee the chaser maneuvering along the specified trajectory.
暂无评论