Hongbin Jin

  • Citations Per Year
Learn More
Inspired by the boosting technique for detecting objects, this paper proposes a cascade structure with a resurrection mechanism to establish keypoint mappings on multispectral images. The cascade structure is composed of four steps by utilizing best bin first (BBF), color and intensity distribution of segment (CIDS), global information and the RANSAC(More)
For the problem that the single-phase permanent magnet synchronous motor has no capability self-starting, the structure with a step-airgap is adopted. Under the effect of locating torque, there will be a phase angle existing between the rotor and stator magnetic field, so as to achieve a self-starter. By using 2D-FEM, it analyzed the influence of the(More)
In the multi-sensor data fusion system, the data acquired by each sensor which will be fused should be at the same time level so that the correct state can be worked out. But actually the time error exists for the delay of the data transmission and the disaccord of the sampling cycles of the sensors. The time error has great effect on the measured distance(More)
Singer model is a whole statistic model, which considers all the possibility of the variance of the maneuvering target, and it is fit for a variety of situations and many kinds of maneuvers. So the probability of the occurrence of the concrete maneuver in each concrete tactics situation is small, which leads to the low accuracy of tracking. The(More)
Fault diagnosis of actuators in flight control system of an unmanned tandem helicopter has been studied in this paper. A support vector machine (SVM) observer is designed to parameter estimation and model compensation for its uncertainty, and then to fault detection. Further more, a fuzzy sample SVM (FS-SVM) based diagnostic tool is used to fault diagnosis(More)
Concerning for air target attribute identification, an attribute identification method based on the combination of multi-class SVM and D-S evidence theory is proposed. The method constructs several multi-class support vector machine (SVM) classifiers, and generates the basic probability assignment (BPA) by the class-wise probability. Then D-S evidence(More)
This paper proposes an algorithm of building keypoint matches on multimodal images by combining a bootstrap process and global information. The correct ratio of keypoint matches built with descriptors is typically very low on multimodal images of large spectral difference. To identify correct matches, global information is utilized for evaluating keypoint(More)
Acknowledgments: This paper was supported by the National Natural Science Foundation of China (Grants No. NSFC-61170176), Fund for the Doctoral Program of Higher Education of China (Grants No. 20120005110002), Fund for Beijing University of Posts and Telecommunications (Grants No. 2013XD-04), National Natural Science Foundation of China (Grants No.(More)