New Compound Method for Target Recognition and Tracking

2013 ◽  
Vol 273 ◽  
pp. 790-795
Author(s):  
Kang Sun
Keyword(s):  
Local Features ◽  
Classification Theory ◽  
Typical Application ◽  
Detection And Tracking ◽  
Tracking Detector ◽  
Temporal Continuity ◽  
Matching Complex ◽  
On Line ◽  
Compound Method ◽  
Template Tracking

In this paper, we propose compound target detection and tracking method that combines Bayesian local features classification and global template tracking. During target initialization phase, we convert local features recognition problem into Semi-Naive Bayesian classification theory to avoid computing and matching complex high-dimension descriptor. During tracking, detector hands over tracking task to the template tracker, which imposes temporal continuity constraints across on-line frames in order to increase the robustness and efficiency of the results. In typical application scenarios, once the tracker loses target, it requires the detector for reinitialization. Experiment results confirm the efficiency of our approach at last.

scholarly journals Rapid Mapping of Small-Scale River-Floodplain Environments Using UAV SfM Supports Classical Theory

2019 ◽  
Vol 11 (8) ◽  
pp. 982 ◽  
Author(s):  
Schumann ◽  
Muhlhausen ◽  
Andreadis
Keyword(s):  
Urban Areas ◽  
Flash Flood ◽  
Classification Theory ◽  
Small Scale ◽  
Steady Increase ◽  
Typical Application ◽  
Small Stream ◽  
River Floodplain ◽  
Terrain Model ◽  
Channel Hydraulics

Unmanned Aerial Vehicle (UAV) platforms have rapidly developed as tools for remote mapping at very high spatial resolutions. They have recently gained in popularity in many application fields owing to the versatility of platforms and sensors, ease of deployment, and a steady increase in computational power. Obtaining highly detailed topography data over very small scales is one of the more typical application domains. Here, we demonstrate this application using Structure from Motion (SfM) processing over a small river floodplain in Howard County (Maryland, USA). Evaluation of the derived bare-earth terrain model with state-of-the art LiDAR shows a trivial bias of 1.6 cm and a root mean square deviation (RMSD) of 39 cm. We then applied this terrain model to extract floodplain and river cross-section geometries of a small stream, important during high-magnitude urban flash flood events, with the aim to assess its value for floodplain inundation mapping and first order characterization of in-channel hydraulics. Initial findings agree with traditional stream and floodplain classification theory and thus show very promising results for this type of UAV usage. We expect this type of application to gain more momentum in the near future with the ever-growing importance of more detailed data in order to increase resilience to flood risk, especially in urban areas.

On-Line Detection and Tracking Welding Control Technology of Thin-Walled Bellow

2011 ◽  
Vol 211-212 ◽  
pp. 336-339
Author(s):  
Zhong Wei Ren ◽  
Zhen Yun Duan ◽  
Wen Hui Zhao ◽  
Wei Wei Jiang
Keyword(s):  
Control System ◽  
Detection System ◽  
Line Detection ◽  
Laser Sensor ◽  
Control Technology ◽  
Detection And Tracking ◽  
Motion Control Card ◽  
On Line ◽  
Thin Walled ◽  
Automation Level

In order to improve the welding speed, quality and automation level of thin-walled bellow, on-line detection and tracking welding control technology is proposed which includes on-line detection system and tracking welding control system. Based on laser sensor, on-line detection system can rapidly filter the data, and the data is stored in a queue, the control system which is based on motion control card is developed by using ActiveX controls for programming, VB is used to develop the integrated user operating system, other control tasks are completely integrated on this system to realize real-time welding control bellow. Results showed that the system is reliable and effectively, the automation level of the bellow welding is greatly improved.

On-Line New Event Detection and Tracking

2017 ◽  
Vol 51 (2) ◽  
pp. 185-193 ◽  
Author(s):  
James Allan ◽  
Ron Papka ◽  
Victor Lavrenko
Keyword(s):  
Event Detection ◽  
Detection And Tracking ◽  
On Line

scholarly journals Turbomachinery Diagnostic System: SNAM Cortemaggiore Compressor Station as a Typical Application

1996 ◽  
Author(s):  
Paolo Pulicani ◽  
Giuliano Zampieri
Keyword(s):  
Diagnostic System ◽  
Industrial Applications ◽  
Computer Networking ◽  
Typical Application ◽  
Functional Flexibility ◽  
Course Of Action ◽  
Gas Compression ◽  
Software Modules ◽  
On Line ◽  
Action Taking

The development in the computer networking area has been growing in the past few years in connection with the prevaling of the open system concepts and with the improvement in microcomputers as opposed to minicomputers technology. Compared to the structure of a centralized system, a distribuited structure gives the following advantages: functional flexibility, maintainability, software rangeability and friendly interface with the operator. Based on several years of field experience. Nuovo Pignone has developed an on-line diagnostic system for turbomachines made up of integrated hardware and software modules designed for optimum management of information coming from turbomachines. The system controls the mechanical and thermodynamic behaviour of the machines, thus providing an effective support to their operation and maintenance. This results in an increased availability lower maintainance costs and improved plant efficiency. A mathematical model, based on Gas Path Analysis (G.P.A.) methodology, has been implemented in the system and has already been successfully tested in several industrial applications, quite similar to Cortemaggiore plant. The experience gained in the Cortemaggiore gas compression station indicates that the main problem arises in interpretation of the data coming from the system. The Diagnostic System gives plenty of data, suitably arranged, to support the maintenance staff in their duties. Nevertheless is the operator who had to interpretate data, correlate thermodynamic information with mechanical data and decide on the best course of action. Taking into account that many plants are not continuously attended by highly experienced technicians in this domain, Nuovo Pignone has developed an Expert System, integrated with the Diagnostic Packages, that incorporates all the information acquired from skilled field engineers during years of activities.

scholarly journals SIMPLIPOLY: CURVATURE-BASED POLYGONAL CURVE SIMPLIFICATION

2011 ◽  
Vol 21 (04) ◽  
pp. 417-429 ◽  
Author(s):  
CHANSOPHEA CHUON ◽  
SUMANTA GUHA ◽  
PAUL JANECEK ◽  
NGUYEN DUC CONG SONG
Keyword(s):  
3D Modeling ◽  
Local Features ◽  
Third Party ◽  
Curvature Estimates ◽  
Modeling Software ◽  
Polygonal Curve ◽  
On Line ◽  
Curve Simplification ◽  
Curvature Driven ◽  
Input Curve

A curvature-based algorithm to simplify a polygonal curve is described, together with its implementation. The so-called SimpliPoly algorithm uses Bézier curves to approximate pieces of the input curve, and assign curvature estimates to vertices of the input polyline from curvature values computed for the Bézier approximations. The authors' implementation of SimpliPoly is interactive and available freely on-line. Additionally, a third-party implementation of SimpliPoly as a plug-in for the GNU Blender 3D modeling software is available. Empirical comparisons indicate that SimpliPoly performs as well as the widely-used Douglas-Peucker algorithm in most situations, and significantly better, because it is curvature-driven, in applications where it is necessary to preserve local features.

Re-Evaluation of On-Line Hot Topic Discovery Model

2011 ◽  
pp. 1-8
Author(s):  
Hui-min Ye ◽  
Sushil Sharma ◽  
Huinan Xu
Keyword(s):  
Information Transmission ◽  
Topic Detection ◽  
Topic Detection And Tracking ◽  
Topic Discovery ◽  
Detection And Tracking ◽  
Time Period ◽  
Index Approach ◽  
On Line ◽  
Major Medium

As a major medium for information transmission, Internet plays an important role in diffusing and spreading news on web. Some governments attach great importance and pay lot of effort trying to detect, track the development of events and forecast emergency on internet. On the basis of the researches in the field of topic detection and tracking, we proposed a model for hot topic discovery that would pick out hot topics by automatically detecting, clustering and weighting topics on the websites within a time period. We also introduced a topic index approach in following the growth of topics, which is useful to analyze and forecast the development of topics on web.

Sign in / Sign up

Export Citation Format

Share Document