Search

An accurate forest type map is important for the forestry resources monitor and management. Forest type mapping over a large and complicated mountain area is full of challenge due to complex forest type compositions, similar spectral characteristics between various forest types, lack of high quality images caused by clouds or cloud shadows, and the difficulties in managing and processing large amount data. This study aims to explore forest-type mapping methods over a mountain region with strong geographic and climate heterogeneity characteristic landscape (Yunnan Province, China). Based on Landsat OLI dense time series data, four median seasonal composites consist of 7 spectral bands and 5 vegetation indexes were derived on Google Earth Engine cloud platform. The Random Forest classifier was used in two-level classification, which includes the classification of forest/non-forest and the classification of forest-type. In two-level classification, three types of feature combination, single-seasonal composite in four seasons, multi-seasonal composite and the combination of multi-seasonal composite and three environmental factors, were set, respectively. We also compared our method with two commonly used methods. The resultant forest map was evaluated by using overall accuracy and Kappa and compared to the ground survey data and four public forest products. The results show that multi-seasonal multispectral variables and the combination with environment factors improved accuracy of forest type classification. Our result is also superior to stat-of-the-art result, FCS2020, in the research area.

In this paper, practical stability is concerned for positive switched nonlinear time-varying (PSNTV) systems and positive switched linear time-varying (PSLTV) systems with disturbances. Based on a new definition on practical stability which can fully reflect the positivity of every component of the solution, sufficient conditions on practical stability of PSNTV systems are given by using the multiple max-separable Lyapunov function method. As an application of our criterion, sufficient criteria on practical stability are also provided for PSLTV systems with disturbances. Through our criterion, the systems' practical stability can be judged directly from the algebraic characteristics of the systems. At the end, examples are presented to illustrate the effectiveness of our results.

In this paper, we discuss the practical stability of positive systems. By using the comparison lemma, max-separable Lyapunov function and generalized integral inequality, we provide sufficient conditions on practical stability for nonlinear positive systems and linear time-varying positive systems with disturbances, respectively. Especially, the practical stability of linear time-varying positive systems is discussed under several different disturbance conditions. At the end, three examples are presented to illustrate the effectiveness of our approaches.

Energy efficiency is an important factor to optimize the multi-hop forwarding strategy. PD (Pairing-inspired Dijkstra) multi-hop data forwarding algorithm is proposed to share cellular spectrum resources with D2D (device-to-device) users. Candidate multiplexing channel model is established in our proposal. Based on this model, PD algorithm solves the issue on channel and path selection. PD algorithm includes two parts, KM dichotomous matching algorithm and multiple iterations for Dijkstra algorithm. Under energy efficiency and QoS (Quality of Service) constraint, PD algorithm selects optimal transmission path among D2D users. Furthermore, the energy efficiency and transmission delay are evaluated in simulation section under PD, Dijkstra and CD (Closest to Destination) algorithm. Simulation results indicate that PD has better performance on energy efficiency and E2E (End to End) delay.

We propose a retailer's inventory replenishment policy to cooperate with suppliers in a periodic review. The retailer shares an advanced replenishment plan based on demand forecast with the supplier and commits cumulative periodic order quantity of the same planning horizon with advanced replenishment plan within range of a lower and upper percentage of the planned quantity. Using a year sales data of products with different delivery-lead-times and ordering cycles from a leisure food retail chain store in China, We contrast this policy through simulation with the store's previous policy in terms of inventory turnover performance and the error between stock level and actual demand. The result shows that the new policy can effectively improve the performance measures.

This article considers extended warranty decisions in competing dual-channel supply chains and uses game theories to analyze three model. We also discuss scenarios when the manufacturer provides the extended warranty and when the retailer does in each model. Our analysis reveals that: 1) In model MR, scenario MR-R outperforms MR-M for the manufacturer, the retailer and the whole system. 2) In model MRR, scenario MRR-R outperforms MRR-M for the manufacturer, while scenario MRR-R outperforms MRR-M under certain conditions for the retailers and the whole system. 3) In model MMR, scenario MMR-R outperforms MMR-M for the retailer and the whole system, while for the manufacturer, it depends on parameters such as channel substitutability and extended warranty sensitivity.

We consider the problem of finding distinctive social interactions involving groups of agents embedded in larger social gatherings. Given a pre-defined gallery of short exemplar interaction videos, and a long input video of a large gathering (with approximately-tracked agents), we identify within the gathering small sub-groups of agents exhibiting social interactions that resemble those in the exemplars. The participants of each detected group interaction are localized in space, the extent of their interaction is localized in time, and when the gallery of exemplars is annotated with group-interaction categories, each detected interaction is classified into one of the pre-defined categories. Our approach represents group behaviors by dichotomous collections of descriptors for (a) individual actions, and (b) pair-wise interactions, and it includes efficient algorithms for optimally distinguishing participants from by-standers in every temporal unit and for temporally localizing the extent of the group interaction. Most importantly, the method is generic and can be applied whenever numerous interacting agents can be approximately tracked over time. We evaluate the approach using three different video collections, two that involve humans and one that involves mice.

Boiler steam temperature system shows non-linear and time-varying, so the accurate modeling of steam temperature system is particularly important. A kind of method of fuzzy identification based on improved GK clustering algorithm (λ-sectional set fuzzy weighted GK clustering) is proposed in connection with the traditional Fuzzy clustering algorithm's defects such as low precision and slow search speed. By analyzing the correlation of input and output as weighted coefficient of fuzzy clustering algorithm, it is employed to cluster the input data of sample space. A more appropriate division of the input data is achieved, at the same time the sectional set fuzzy GK clustering is proposed to identify the model structure off line to improve searching rate, the method confirms the premise parameter by improved fuzzy partitions clustering algorithm and the consequence parameters is decided by LS algorithm. In this paper, the simulation of the temperature control TITO system of the boiler can illustrate that the method is accurate and effective.

Based on the concept of low cost automation, a kind of multi-channel analog acquisition program based on traditional analog circuits and digital I/O ports of PLC is presented in this paper, including hardware circuit, program design and principles of signal acquisition. Compared with the expensive PLC analog module, the system is designed with features such as low cost, easy to implement. This paper makes use of PID module of PLC and self-tuning technology, applying this analog acquisition program to the temperature control system, PWM signal is generated to control solid state relays to accurately control temperature, at the same time the data exchange between computer and PLC has been completed, the interface is friendly, the experimental results show the feasibility and practicality of the program.

We propose an approach for cross-view action recognition by way of ‘virtual views’ that connect the action descriptors extracted from one (source) view to those extracted from another (target) view. Each virtual view is associated with a linear transformation of the action descriptor, and the sequence of transformations arising from the sequence of virtual views aims at bridging the source and target views while preserving discrimination among action categories. Our approach is capable of operating without access to labeled action samples in the target view and without access to corresponding action instances in the two views, and it also naturally incorporate and exploit corresponding instances or partial labeling in the target view when they are available. The proposed approach achieves improved or competitive performance relative to existing methods when instance correspondences or target labels are available, and it goes beyond the capabilities of these methods by providing some level of discrimination even when neither correspondences nor target labels exist.

Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categories across domains). Motivated by incremental learning, we create intermediate representations of data between the two domains by viewing the generative subspaces (of same dimension) created from these domains as points on the Grassmann manifold, and sampling points along the geodesic between them to obtain subspaces that provide a meaningful description of the underlying domain shift. We then obtain the projections of labeled source domain data onto these subspaces, from which a discriminative classifier is learnt to classify projected data from the target domain. We discuss extensions of our approach for semi-supervised adaptation, and for cases with multiple source and target domains, and report competitive results on standard datasets.

We address the problem of recognizing offensive play strategies from American football play videos. Specifically, we propose a probabilistic model which describes the generative process of an observed football play and takes into account practical issues in real football videos, such as difficulty in identifying offensive players, view changes, and tracking errors. In particular, we exploit the geometric properties of nonlinear spaces of involved variables and design statistical models on these manifolds. Then recognition is performed via 'analysis-by-synthesis' technique. Experiments on a newly established dataset of American football videos demonstrate the effectiveness of the approach.

We consider the ‘group motion segmentation’ problem and provide a solution for it. The group motion segmentation problem aims at analyzing motion trajectories of multiple objects in video and finding among them the ones involved in a ‘group motion pattern’. This problem is motivated by and serves as the basis for the ‘multi-object activity recognition’ problem, which is currently an active research topic in event analysis and activity recognition. Specifically, we learn a Spatio-Temporal Driving Force Model to characterize a group motion pattern and design an approach for segmenting the group motion. We illustrate the approach using videos of American football plays, where we identify the offensive players, who follow an offensive motion pattern, from motions of all players in the field. Experiments using GaTech Football Play Dataset validate the effectiveness of the segmentation algorithm.

While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activities, or group activities, present in a variety of applications such as surveillance, sports, and biological monitoring records, etc., are the main focus of this paper. Unlike earlier attempts which model the complex spatial temporal constraints among multiple objects with a parametric Bayesian network, we propose a Discriminative Temporal Interaction Manifold (DTIM) framework as a data-driven strategy to characterize the group motion pattern without employing specific domain knowledge. In particular, we establish probability densities on the DTIM, whose element, the discriminative temporal interaction matrix, compactly describes the coordination and interaction among multiple objects in a group activity. For each class of group activity we learn a multi-modal density function on the DTIM. A Maximum a Posteriori (MAP) classifier on the manifold is then designed for recognizing new activities. Experiments on football play recognition demonstrate the effectiveness of the approach.

While video-based activity analysis and recognition has received broad attention, existing body of work mostly deals with single object/person case. Modeling involving multiple objects and recognition of coordinated group activities, present in a variety of applications such as surveillance, sports, biological records, and so on, is the main focus of this paper. Unlike earlier attempts which model the complex spatial temporal constraints among different activities of multiple objects with a parametric Bayesian network, we propose a dynamic ‘event ensemble’ framework as a data-driven strategy to characterize the group motion pattern without employing any specific domain knowledge. In particular, we exploit the Riemannian geometric property of the set of ensemble description functions and develop a compact representation for group activities on the ensemble manifold. An appropriate classifier on the manifold is then designed for recognizing new activities. Experiments on football play recognition demonstrate the effectiveness of the framework.

This paper considers the replenishment problem of the rental stores in a duopoly environment. Specifically, when a new product such as video tapes, DVDs, books, etc., is released to the market, stores determine the replenishment quantities, respectively, in order to satisfy the demand in the retention time. The demand for each store is continuous and decreasing in time. Proportion of the unsatisfied demand of one store will turn to the other store. The store has to take the demand spill over effect into consideration when he makes the replenishment decision. We prove, in this duopoly environment, the replenishment quantity of each store consists a unique Nash equilibrium. And there exists a time window in the retention time in which the store with the higher penalty cost could earn extra profit due to the spill over effect.

A fast robust eigen-background update algorithm is proposed for foreground object detection. The update procedure involves no eigen decomposition, thus faster than former eigen-background based algorithms. Meanwhile, the algorithm can robustly maintain the desired background model, resistant to outlying objects.

A simulated face recognition experiment using enhanced pixelized images is designed and performed for the artificial visual prosthesis. The results of the simulation reveal new characteristics of visual performance in an enhanced pixelization condition, and then new suggestions on the future design of visual prosthesis are provided.