The most standard image object detectors are usually comprised of one or multiple feature extractors or classifiers within a sliding window framework. Nevertheless, this type of approach has demonstrated a very limite...
详细信息
The most standard image object detectors are usually comprised of one or multiple feature extractors or classifiers within a sliding window framework. Nevertheless, this type of approach has demonstrated a very limited performance under datasets of cluttered scenes and real life situations. To tackle these issues, LIDAR space is exploited here in order to detect 2D objects in 3D space, avoiding all the inherent problems of regular sliding window techniques. Additionally, we propose a relational parts-based pedestrian detection in a probabilistic non-iid framework. With the proposed framework, we have achieved state-of-the-art performance in a pedestrian dataset gathered in a challenging urban scenario. The proposed system demonstrated superior performance in comparison with pure sliding-window-based image detectors.
A method for Kinect sensor was presented based on SLAM (simultaneous localization and mapping) problem via inverse depth parameterization model, where the depth of features from Kinect was employed to improve the conv...
详细信息
A method for Kinect sensor was presented based on SLAM (simultaneous localization and mapping) problem via inverse depth parameterization model, where the depth of features from Kinect was employed to improve the convergence of method. To further improve the accuracy and robustness, SURF (speed up robust features) feature detection operator was adopted to extract image features, and extended Kalman filter (EKF) was used to estimate the trajectory of camera and the position of features. Experimental results are given to demonstrate the effectiveness and applicability of the proposed method.
Several sources of error exist in lidar measurements for feedforward control of wind turbines including the ability to detect only radial velocities, spatial averaging, and wind evolution. This paper investigates anot...
Several sources of error exist in lidar measurements for feedforward control of wind turbines including the ability to detect only radial velocities, spatial averaging, and wind evolution. This paper investigates another potential source of error: the upstream induction zone. The induction zone can directly affect lidar measurements and presents an opportunity for further decorrelation between upstream wind and the wind that interacts with the rotor. The impact of the induction zone is investigated using the combined CFD and aeroelastic code SOWFA. Lidar measurements are simulated upstream of a 5 MW turbine rotor and the true wind disturbances are found using a wind speed estimator and turbine outputs. Lidar performance in the absence of an induction zone is determined by simulating lidar measurements and the turbine response using the aeroelastic code FAST with wind inputs taken far upstream of the original turbine location in the SOWFA wind field. Results indicate that while measurement quality strongly depends on the amount of wind evolution, the induction zone has little effect. However, the optimal lidar preview distance and circular scan radius change slightly due to the presence of the induction zone.
The main point of this paper is to present a time domain strategy for drug dosage to treat psychiatric disorders. A time domain model of emotion is obtained from an extension of a recently developed fractional nonline...
详细信息
ISBN:
(纸本)9781467356329
The main point of this paper is to present a time domain strategy for drug dosage to treat psychiatric disorders. A time domain model of emotion is obtained from an extension of a recently developed fractional nonlinear dynamic model of happiness. First, the Fractional Optimal Control law for incommensurate multi state systems is obtained. It will be then applied as an optimal drug administration procedure in the line of psychiatric disorders treatment. Results of this paper show that optimal control scheme is a proper approach to face the difficulties of analysis and control the incommensurate systems. It can be also clearly seen from the simulation results that this approach is very effective in the case that control methods are used as treatment techniques.
Microgrids are small-scale highly controlled networks designed to supply electrical energy. From the operational point of view, microgrids are active distribution networks, facilitating the integration of distributed ...
详细信息
ISBN:
(纸本)9781479913022
Microgrids are small-scale highly controlled networks designed to supply electrical energy. From the operational point of view, microgrids are active distribution networks, facilitating the integration of distributed generation units. Major technical issues in this concept include system stability and protection coordination which are significantly influenced by the high penetration of inverter-interfaced distributed energy sources. These units often adopt the frequency-active power and voltagereactive power droop control strategy to participate in the load sharing of an islanded microgrid. The scope of the paper is to investigate the dynamic performance of a low voltage laboratory-scale microgrid system, using experimental results and introduce the concept of Prony analysis for understanding the connected components. Several small disturbance test cases are conducted and the investigations focus on the influence of the droop controlled distributed generation sources.
This paper presents a new multiple-classifier approach for accurate spectral-spatial classification of hyperspectral images, where the spectral information is exploited by combining probabilistic support vector machin...
详细信息
ISBN:
(纸本)9781479911127
This paper presents a new multiple-classifier approach for accurate spectral-spatial classification of hyperspectral images, where the spectral information is exploited by combining probabilistic support vector machines (SVM) and subspace-based multinomial logistic regression (MLRsub) and the spatial information is exploited by means of a Markov random field (MRF) regularizer. The proposed approach is based on the decision fusion of global posterior probability distributions and local probabilities which result from the whole image and the class combinations map respectively. With respect to the SVM or MLRsub algorithms, the proposed method greatly improves the classification accuracy. Our experimental results with real hyperspectral images collected by the NASA Jet Propulsion laboratory's Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) and the Reflective Optics Spectrographic Imaging System (ROSIS), indicate that the proposed multiple-classifier system leads to state-of-the-art classification performance for cases with very limited number of training samples.
作者：
Mingfen LiJie JiaYe LiuDepartment of Rehabilitation
Huashan Hospital Fudan University MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University China
The use of groups of autonomous marine vehicles has enormous potential in numerous marine applications, perhaps the most relevant of which is the surveying and exploration of the oceans, still widely unknown and misun...
详细信息
ISBN:
(纸本)9781467356404
The use of groups of autonomous marine vehicles has enormous potential in numerous marine applications, perhaps the most relevant of which is the surveying and exploration of the oceans, still widely unknown and misunderstood. In many mission scenarios requiring the concerted operation of multiple marine vehicles carrying distinct, yet complementary sensor suites, relative positioning and formation control becomes mandatory. However, the constraints placed by the medium make it hard to both communicate and localize vehicles, even in relation to each other. In this paper, we deal with the challenging problem of keeping an autonomous underwater vehicle in a moving triangular formation with respect to 2 leader vehicles. We build upon our previous theoretical work on range-only formation control, which presents simple feedback laws to drive the controlled vehicle to its intended position in the formation using only ranges obtained to the leading vehicles with no knowledge of the formation path. We then introduce the real-world constraints associated with the use of autonomous underwater vehicles, especially the low frequency characteristics of acoustic ranging and its unreliability. We discuss the required changes to implement the solution in our vehicles, and provide simulation results using a full dynamic and communication model. Finally, we present the results of real world trials using MEDUSA-class autonomous marine vehicles.
The International Workshop on Emerging Trends in Software Metrics aims at gathering together researchers and practitioners to discuss the progress of software metrics. The motivation for this workshop is the low impac...
详细信息
ISBN:
(纸本)9781467330756
The International Workshop on Emerging Trends in Software Metrics aims at gathering together researchers and practitioners to discuss the progress of software metrics. The motivation for this workshop is the low impact that software metrics has on current software development. The goals of this workshop includes critically examining the evidence for the effectiveness of existing metrics and identifying new directions for metrics. Evidence for existing metrics includes how the metrics have been used in practice and studies showing their effectiveness. Identifying new directions includes use of new theories, such as complex network theory, on which to base metrics.
Neural network language models, or continuous-space language models (CSLMs), have been shown to improve the performance of statistical machine translation (SMT) when they are used for reranking n-best translations. Ho...
详细信息
暂无评论