Guozhang Jiang

An Interactive Image Segmentation Method in Hand Gesture Recognition

In order to improve the recognition rate of hand gestures a new interactive image segmentation method for hand gesture recognition is presented, and popular methods, e.g., Graph cut, Random walker, Interactive image segmentation using geodesic star convexity, are studied in this article. The Gaussian Mixture Model was employed for image modelling and the iteration of Expectation Maximum algorithm learns the parameters of Gaussian Mixture Model. We apply a Gibbs random field to the image segmentation and minimize the Gibbs Energy using Min-cut theorem to find the optimal segmentation. The segmentation result of our method is tested on an image dataset and compared with other methods by estimating the region accuracy and boundary accuracy. Finally five kinds of hand gestures in different backgrounds are tested on our experimental platform, and the sparse representation algorithm is used, proving that the segmentation of hand gesture images helps to improve the recognition accuracy.

Simultaneous Calibration: A Joint Optimization Approach for Multiple Kinect and External Cameras

Camera calibration is a crucial problem in many applications, such as 3D reconstruction, structure from motion, object tracking and face alignment. Numerous methods have been proposed to solve the above problem with good performance in the last few decades. However, few methods are targeted at joint calibration of multi-sensors (more than four devices), which normally is a practical issue in the real-time systems. In this paper, we propose a novel method and a corresponding workflow framework to simultaneously calibrate relative poses of a Kinect and three external cameras. By optimizing the final cost function and adding corresponding weights to the external cameras in different locations, an effective joint calibration of multiple devices is constructed. Furthermore, the method is tested in a practical platform, and experiment results show that the proposed joint calibration method can achieve a satisfactory performance in a project real-time system and its accuracy is higher than the manufacturer’s calibration.

A simulation-based study of dispatching rules in a dynamic job shop scheduling problem with batch release and extended technical precedence constraints

This paper considers a simulation-based analysis of dispatching rules for scheduling in a dynamic job shop with batch release taking into account the extended technical precedence constraint which is a new term defined as the extension of conventional routing-based technical precedence constraint in our paper. With respect to tardiness-related measures, the relative performances of some widely-used dispatching rules as well as four new ones proposed in our paper are evaluated for different settings of the model parameters. The results of the simulation study demonstrate the effectiveness of the four new proposed dispatching rules, and also reveal that the relative performance of dispatching rules can be affected by some model parameters. For the standard job shop scheduling problem model, where there are no extended technical precedence constraints between jobs, as well as for the models taking into account the extended technical precedence constraint, it is shown that for minimizing the total tardiness and the percentage of tardy jobs, the four new proposed dispatching rules are very effective under relatively loose due date. With respect to tardiness-related objectives, the relative performance of the analyzed dispatching rules can be affected by changing not only the levels of the extended technical precedence constraint, but also the due date tightness.

Numerical simulation of temperature field and thermal stress field in the new type of ladle with the nanometer adiabatic material

With the development of metallurgical industry and the improvement of continuous casting technology, the processing properties of casting technology equipment are being paid more attention. Ladle is one of the most representatives of the furnace equipment; higher requirements of ladle are put forward in response to the call for national energy-saving and emission reduction. According to the requirements of actual operator and working condition, a lining structure of a new type of ladle with nanometer adiabatic material is put forward. Based on heat transfer theory and finite element technology, the three-dimensional finite element model of a new type of ladle is established. Temperature field and stress field of the new type of ladle with the nanometer adiabatic material in lining structure after baking are analyzed. The results indicate that the distributions of temperature and thermal stress level of working layer, permanent layer, and nanometer heat insulating layer are similar, and they are in the permissible stress and temperature range of each material for the new type of ladle. Especially heat preservation effect of nanometer adiabatic material is excellent. Furthermore, the maximum temperature of shell for the new type of ladle drops to 114°C than the traditional ladle, and the maximum stress of shell for the new type of ladle is lower than the traditional ladle, that is, 114 MPa. It can provide reliable theory for energy-saving and emission reduction of metallurgy industry, which also points out the right direction for the future development of the iron and steel industry.

Gesture recognition based on an improved local sparse representation classification algorithm

The sparse representation classification method has been widely concerned and studied in pattern recognition because of its good recognition effect and classification performance. Using the minimized

Gesture Recognition Based on Kinect and sEMG Signal Fusion

l_{1}

Gesture recognition based on sparse representation

l1 norm to solve the sparse coefficient, all the training samples are selected as the redundant dictionary to calculate, but the computational complexity is higher. Aiming at the problem of high computational complexity of the