Dissertation > Excellent graduate degree dissertation topics show

Research on Multiple Moving Objects Recognition Technology Based on Video

Author: LanLiBao
Tutor: DongHuiYing
School: Shenyang University of Technology
Course: Pattern Recognition and Intelligent Systems
Keywords: Multi - moving object segmentation Feature Extraction Fuzzy Recognition BP neural network recognition Adaptive fuzzy neural network to identify
CLC: TP391.41
Type: Master's thesis
Year: 2008
Downloads: 310
Quote: 2
Read: Download Dissertation

Abstract


Multi - sport target recognition is an important part of intelligent video surveillance systems , is also a hot research topic in the field of computer vision , its research has a very important theoretical significance and application value . Sports car , bicycle / motorcycle , pedestrian study carried out in-depth research on video - based multi- moving object recognition technology . First of all, to establish the initial background model using the value of the synthetic strategy combining adaptive background update algorithm and weighted mean threshold realize multi- moving object segmentation , and select the area of ??the shape complexity , aspect ratio, speed as a moving target identification features . The simulation results show that the target partition to good effect , having the identifying characteristics extracted better distinction . Then , the identification of multiple moving objects based on fuzzy theory . Fuzzy C - means clustering method to achieve the characteristic quantity of fuzzy and Mamdani fuzzy classifier Sugeno fuzzy classifier designed to achieve the recognition of multiple moving targets . The simulation results show that high recognition accuracy than Mamdani fuzzy classifier Sugeno fuzzy classifier . Then , the identification of multiple moving targets based on BP neural network . Ordinary BP algorithm shortcomings the elastic BP algorithm and LM algorithm to improve the performance of the network , and were designed for multi-output the BP classifier and single output type BP joint classifier to achieve the recognition of multiple moving targets . Simulation results show that the single output-type BP combined classification in the same exercise index , higher than the accuracy of identification of the multi - output-type BP classifier . Finally, the identification of multiple moving targets based on adaptive fuzzy neural network (ANFIS) . Respectively , the use of mesh segmentation method and subtraction clustering method to generate the the ANFIS classifier initial structure and hybrid learning algorithm using the least squares method combined with BP algorithm to train the network . The simulation results show that the indicators of the same training the ANFIS classifier than the the ANFIS classifier training speed mesh segmentation method to generate subtractive clustering method to generate high recognition accuracy . ANFIS combines the advantages of fuzzy systems and neural networks , with a transparent structure , interpretability and good , and has better adaptive learning ability , the best overall performance .

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  3. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  4. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  5. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  6. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  7. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  8. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  9. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  10. Multi-currency Notes Technology Research and Implementation,TP391.41
  11. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  12. Pavement Distress Recognition Based on Image,TP391.41
  13. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  14. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  15. An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
  16. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  17. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  18. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  19. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  20. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  21. Feature Extraction Technologies Research and Implementation of 3D Models Based on Wavelet Transform,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile