3D Radar Tracking Particle Filter
A robust 3D radar tracking particle filter implemented using MATLAB programming, featuring enhanced algorithms for multi-target tracking and sensor fusion capabilities
Kalman Filter Tracking for Constant Velocity Motion Objects
Kalman filters are extensively utilized in modern control systems. This implementation demonstrates the application of Kalman filtering theory for tracking and predicting uniformly moving objects, enabling comparative analysis between theoretical predictions and actual measurement data. The approach holds significant value for both control theory education and practical motion tracking applications, featuring state prediction and measurement update cycles with noise handling capabilities.
Robot Vision Toolbox
Robot Vision Toolbox with extensive routine libraries, useful for video surveillance, object detection and tracking applications. Includes implementation of computer vision algorithms and pre-built processing pipelines.
Implementing 2D Kalman Filter in MATLAB for Target Prediction and Tracking
Implementation of 2D Kalman Filter in MATLAB with target prediction and tracking capabilities, featuring state-space modeling, noise covariance configuration, and real-time estimation algorithms.
Particle Filter and Other Filtering Methods for Passive Localization and Tracking
A comprehensive program demonstrating various filtering techniques suitable for passive localization and tracking, including particle filter implementations and alternative filtering approaches with detailed code implementation examples.
MATLAB Implementation of GPS Signal Tracking Using Phase-Locked Loop
GPS signal tracking implementation using phase-locked loop technology, including code loop tracking and carrier tracking loop with algorithm explanations and key MATLAB functions
People Tracking and Counting
Disguise monitoring system. Counting people passing through monitored areas remains a critical research topic in this field, primarily relying on background subtraction processes. The method faces two major challenges: dynamic background model estimation and shadow removal. To address these, a bidirectional people counting algorithm is proposed. For developing robust counting systems, Gaussian Mixture Models (GMM) are employed to characterize background scenes. However, this algorithm lacks classification capability for detecting shadows in moving foreground objects. Performance enhancement is achieved by integrating color models with background models, improving motion object detection through shadow elimination from foreground elements. A multi-class feature-based tracking algorithm handles occlusion issues in multi-object tracking, while bidirectional counting improvement requires multi-level backward tracking procedure development.
MATLAB Simulation for GPS Signal Acquisition and Tracking
MATLAB simulation for GPS signal acquisition and tracking with comprehensive documentation
GPS Signal Acquisition, Tracking, and Positioning Algorithm
Application Background GPS signal acquisition, tracking, and positioning are frequently employed in undergraduate and graduate studies. This program provides a comprehensive implementation of GPS signal acquisition, tracking, and positioning algorithms, along with a real GPS signal sample for processing. Key Technologies The program utilizes non-coherent acquisition methods, second-order carrier and code tracking loops, and least-squares positioning algorithms for receiver location calculation.
Moving Object Tracking
Background Subtraction-Based Moving Object Detection and Tracking with Algorithm Implementation