scholarly journals Research on semi-supervising learning algorithm for target model updating in target tracking

2015 ◽  
Vol 64 (1) ◽  
pp. 014205
Author(s):  
Gao Wen ◽  
Tang Yang ◽  
Zhu Ming
Keyword(s):  
Target Tracking ◽  
Model Updating ◽  
Learning Algorithm ◽  
Target Model

The Design Research of Millimeter-Wave Homing Empty - Empty Ammunition Ballistics

2014 ◽  
Vol 575 ◽  
pp. 337-342
Author(s):  
Wei Shi Xie ◽  
Zhi Hua Xiao ◽  
Jian Tang
Keyword(s):  
Target Tracking ◽  
Millimeter Wave ◽  
Design Research ◽  
Optical Axis ◽  
Terminal Velocity ◽  
Target Model ◽  
Search Area ◽  
Pitch Direction ◽  
Trajectory Guidance ◽  
Terminal Guidance

The millimeter-wave terminal guidance ammunition monitoring scanning field is small. The modified design is in order to improve the search section trajectory guidance. This study established seeker search area to capture the target model, which leads to the missile engine unpowered glide distance formula after flameout. At the millimeter-wave terminal on the missiles contraction section ballistic. Each missile is designed for the flat road, the swash decline ballistic programs. Flat missile road program scans and does not shrink. Its flight speed falls and declines rapidly, has different gliding distance and terminal velocity. After the missile engine is flameout, its start-gliding speed is great. Ramp fell ballistic program enhances the air-air (or air-ground) guided missile’s gliding ability, helping to improve range. But shortcomings are that target tracking scanning domain contracts. Using the seeker optical axis in the pitch direction can achieve accurate positioning with the height precession. Two ballistic designs can both meet the target seeker’s scanning, thus effectively improve the striking precision.

Detecting, localizing, and tracking an unknown number of moving targets using a team of mobile robots

2017 ◽  
Vol 36 (13-14) ◽  
pp. 1540-1553 ◽  
Author(s):  
Philip Dames ◽  
Pratap Tokekar ◽  
Vijay Kumar
Keyword(s):  
Target Tracking ◽  
Greedy Algorithm ◽  
Fundamental Problem ◽  
Mathematical Concept ◽  
Data Driven ◽  
Objective Functions ◽  
Probability Hypothesis Density ◽  
Target Model ◽  
Density Filter ◽  
New Formulation

Target tracking is a fundamental problem in robotics research and has been the subject of detailed studies over the years. In this paper, we generate a data-driven target model from a real-world dataset of taxi motions. This model includes target motion, appearance, and disappearance from the search area. Using this target model, we introduce a new formulation of the mobile target tracking problem based on the mathematical concept of random finite sets. This formulation allows for tracking an unknown and dynamic number of mobile targets with a team of robots. We show how to employ the probability hypothesis density filter to simultaneously estimate the number of targets and their positions. Next, we present a greedy algorithm for assigning trajectories to the robots to allow them to actively track the targets. We prove that the greedy algorithm is a two-approximation for maximizing submodular tracking objective functions. We examine two such functions: the mutual information between the estimated target positions and future measurements from the robots and a new objective that maximizes the expected number of targets detected by the robot team. We provide extensive simulation evaluations to validate the performance of our data-driven motion model and to compare the behavior and tracking performance of robots using our objective functions.

scholarly journals Resolvable Group State Estimation with Maneuver Based on Labeled RFS and Graph Theory

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1307
Author(s):  
Weifeng Liu ◽  
Yudong Chi
Keyword(s):  
Graph Theory ◽  
State Estimation ◽  
Target Tracking ◽  
Finite Sets ◽  
Target Model ◽  
Group Members ◽  
Group Target ◽  
Random Finite Sets ◽  
Resolvable Group

In this paper, multiple resolvable group target tracking was considered in the frame of random finite sets. In particular, a group target model was introduced by combining graph theory with the labeled random finite sets (RFS). This accounted for dependence between group members. Simulations were presented to verify the proposed algorithm.

Target Tracking Based on Improved Camshift and Kalman Filter

2014 ◽  
Vol 989-994 ◽  
pp. 3587-3590
Author(s):  
Li Ying Ban ◽  
Yue Hua Han ◽  
Yan Hai Wu
Keyword(s):  
Kalman Filter ◽  
Target Tracking ◽  
Target Object ◽  
Tracking Algorithm ◽  
Color Target ◽  
Motion Cues ◽  
Target Model ◽  
Camshift Algorithm ◽  
Novel Target

A tracking algorithm based on improved Camshift and Kalman filter is proposed in this paper to deal with the problems in traditional Camshift algorithm, such as tracking failure under color interference or occlusion. Firstly, the proposed algorithm improves the single color target model and presents a novel target model, which fuses color and motion cues, to enhance the robustness and accuracy of target tracking. And in order to increase the tracking efficiency, the algorithm combines Kalman filter with the improved Camshift algorithm by using Kalman filter to predict the position of the tracking target under color noises and occlusion. The experiment results demonstrate that the proposed algorithm can track the target object accurately and has better robustness.

scholarly journals Multi-face recognition and dynamic tracking based on reinforcement learning algorithm

2021 ◽  
Vol 336 ◽  
pp. 06006
Author(s):  
Yuxin Li ◽  
Yinggang Xie ◽  
Xi Lu
Keyword(s):  
Face Recognition ◽  
Reinforcement Learning ◽  
Target Tracking ◽  
Success Rate ◽  
Face Detection ◽  
Learning Algorithm ◽  
Identification System ◽  
Dynamic Tracking ◽  
The Face ◽  
Reinforcement Learning Algorithm

Aiming at the problem that the current low accuracy rate of face detection and target tracking, a reinforcement learning algorithm is proposed, which integrates face detection technology and target tracking technology organically, adopts the face detection algorithm based on Multi-Task Convolutional Neural Network (MTCNN) and target tracking algorithm based on Kalman filtering, so as to realize face detection, multiplayer face recognition and dynamic tracking of personnel movement. In this paper, the configuration environment is Anaconda, the operating platform is PyCharm, the video-based face detection and dynamic capture and rapid identification system has been designed and developed. The system consists of two modules: face detection module and target tracking module. The optimized face detection and dynamic capture algorithm improved the detection success rate by about 11.5%, the face detection success rate by about 15.2%, the dynamic capture success rate increased by about 12.0%, and the optimized system has a wider practicality.

A Research on the Weight of Interactive Multiple Model in Maneuvering Target Tracking

2014 ◽  
Vol 568-570 ◽  
pp. 1008-1011
Author(s):  
Ming Yong Liu ◽  
Yang Li ◽  
Xiao Jian Zhang
Keyword(s):  
Target Tracking ◽  
Multiple Model ◽  
Maneuvering Target Tracking ◽  
Target Model ◽  
Maneuvering Target ◽  
Interactive Multiple Model ◽  
Model Set ◽  
Change Mechanisms ◽  
Model Weight

The establishment of the target model is the key of maneuvering target tracking. The previous research on interactive multiple model, which is applied on tracking extensively, focused on the design of the model set and fusion with other algorithms, while there is less study on change mechanisms of the model weight. In light of this, the impetus behind this paper is to do some analysis which based on the model weight of different trajectories, reveal the change rule. Finally, the validity of the proposed approach is demonstrated by simulation.

Sign in / Sign up

Export Citation Format

Share Document