Online RGB-D person re-identification based on metric model update

Person re-identification （re-id） on robot platform is an important application for human-robot- interaction （HRI）, which aims at making the robot recognize the around persons in varying scenes. Although many effective methods have been proposed for surveillance re-id in recent years, re-id on robot platform is still a novel unsolved problem. Most existing methods adapt the supervised metric learning offline to improve the accuracy. However, these methods can not adapt to unknown scenes. To solve this problem, an online re-id framework is proposed. Considering that robotics can afford to use high-resolution RGB-D sensors and clear human face may be captured, face information is used to update the metric model. Firstly, the metric model is pre-trained offline using labeled data. Then during the online stage, we use face information to mine incorrect body matching pairs which are collected to update the metric model online. In addition, to make full use of both appearance and skeleton information provided by RGB-D sensors, a novel feature funnel model （FFM） is proposed. Comparison studies show our approach is more effective and adaptable to varying environments.

Estimation of land surface evapotranspiration using the METRIC model in Nepal

Climatic and atmospheric properties vary significantly within a small area for a topographically diverse region like Nepal.Remote sensing can be used for large-scale monitoring of atmospheric parameters in such diverse terrains.This work evaluates the Landsat-based METRIC(Mapping Evapotranspiration at High Resolution with Internalized Calibration)model for estimating Evapotranspiration(ET)in Nepal.The slope and aspect of terrain are accounted for in our implementation,making the model suitable for regions with topographical variations.The estimations obtained from the model were compared with ground-based measurements.The root-meansquare error for hourly ET(daily ET)was 0.06 mm h-1(1.24 mm d-1),while the mean bias error was0.03 mm h-1(0.29 mm d-1).These results are comparable with results from other studies in the literature that have used the METRIC model for different regions of the world.Thus,this work validates the applicability of the METRIC model for ET estimation in a mountainous area like Nepal.Further,this implementation provides ET estimation at a very high resolution of 30 m compared to the best available resolution of 5 km in earlier works,without compromising on the accuracy.ET estimation with high resolution over a large region in Nepal has applications in agricultural planning and monitoring,among others.

An Arithmetic of Mapping Enterprise Process Metrics to Information Model Based on Semantics

This paper analyzes the semantics structure of enterprise process metric and gives guidelines to describe the semantics of metric for collecting metric data automatically. Based on domain ontology, a structure called semantic tree is defined to de- scribe the semantics relationships among measured entity, meas- urable attribute and constraints, which provides the same method to define semantics of process metrics and data elements in enterprise information model. The arithmetic to map process metrics to enterprise information model is put forward, which can compute the query conditions to retrieve process metrics data from enterprise information systems accurately. This arithmetic has been applied in an information project.

BGMM： A Body Gauss-Markov Based Mobility Model for Body Area Networks

Existing mobility models have limitations in their ability to simulate the movement of Wireless Body Area Network（WBAN） since body nodes do not exactly follow either classic mobility models or human contact distributions. In this paper, we propose a new mobility model called Body Gauss–Markov Mobility（BGMM） model,which is oriented specially to WBAN. First, we present the random Gauss-Markov mobility model as the most suitable theoretical basis for developing our new model, as its movement pattern can reveal real human body movements. Next, we examine the transfer of human movement states and derive a simplified mathematical Human Mobility Model（HMM）. We then construct the BGMM model by combining the RGMM and HMM models. Finally,we simulate the traces of the new mobility model. We use four direct metrics in our proposed mobility model to evaluate its performance. The simulation results show that the proposed BGMM model performs with respect to the direct mobility metrics and can effectively represent a general WBAN-nodes movement pattern.

Unusual Event Detection and Prediction in Real-life Scenes

In this paper,we consider unusual event detection problem in a novel viewpoint and provide an algorithm to solve the problem.The actions or events in the scene is usual or not will eventually be reflected on the changes of some basic features.We summarize these basic event features and propose special representation for each of them.Thus we can model these features in a uniform mode using adaptive Gaussian mixture model.Supervised and unsupervised unusual event detection algorithm can be designed to fit various situations based on this model.The superiority of our model is that it can detect unusual event automatically without to know the determinate model of unusual events.In conclusion,we provide two applications to verify the effectiveness of our model.