Zhanwei Feng

Bio: Zhanwei Feng is an academic researcher. The author has contributed to research in topics: Artificial intelligence & Image (mathematics). The author has co-authored 1 publications.

Vanadium complexes bearing the bulky bis(imino)pyridine ligands :Good thermal stability towaard ethylene polymerization

Abstract: Vanadium complexes with unsymmetric bulky ligands 2-[1-(2,6-dibenzhydryl-4-methylphenylimino)ethyl]-6-[1-(arylimino)ethyl]pyridine (V1-V3) and symmetrical bulky ligand 2,6-bis(1-(2,6-dibenzhydryl-4-methylphenylimino)ethyl)pyridine (V4) were prepared and thoroughly characterized. Single crystals of V1 and V4 were further tested with X-ray single crystal diffraction to prove the molecular structures, and a distorted triangular biconical geometry was adopted around vanadium centers of V1 and V4. These vanadium complexes bearing bulky ligands displayed moderate to high catalytic activity (up to 24.0 × 106 g molV-1 h−1) toward ethylene polymerization when ethylaluminum sesquichloride was employed as a cocatalyst, affording moderate to ultrahigh molecular weight polyethylenes (18.7 × 104 to 176.9 × 104 g/mol). Compared with the classical bis(imino)pyridine vanadium complex VR, complex V3 demonstrated a long lifetime as well as excellent thermal stability. Furthermore, polyethylenes derived from complexes V1-V4 had significantly higher molecular weights at high temperatures.

High Speed Moving Target Tracking Algorithm based on Mean Shift for Video Human Motion

Abstract: As an important research field of computer vision, there are a lot of achievements of human action recognition in recent Most of the researches are confined to the daily gentle action of human, such as walking jogging, sitting down. In sports video there were many specific characteristics about human actions, such as the upside pose of human, high speed, moving viewpoint. For human motion characteristics of sports video, a highspeed moving target tracking algorithm was proposed. Mean shift was an effective tracking algorithm, which was employed to track moving object in video, but it loses object frequently when the tracked object in the video moves rapidly. We advanced an approach to tracking object moving rapidly, and it can work effectively when the object was in cluttered environment. Experimental shows that the proposed algorithm can improve the tracking effect of mean shift algorithm and effectively track high-speed moving target.

An Improved Segmentation Algorithm Based on Video Human Motion

Abstract: AbstractThe paper proposed an approach to extracting human body from an image without interaction of user. Image segmentation algorithm was an Interactive segmentation algorithm, which was employed to extract the foreground of an image, but it works wrong frequently when the pixels around the foreground are similar to the pixels of the background. We advanced a new cost function to correct the mistake. Using the human detection method, we proposed a human body extraction method from image without interaction. Through experiments, our segmentation algorithm can achieve better segmentation results in two situations. The experiment shows that the size of user input box has less influence on this proposed algorithm.KeywordsHuman action recognitionSport analysisHuman detectionImage segmentation algorithm

Image Features Fused with BP Neural Network

Abstract: : Because of the remarkable advantages of computer neural network(NN), it has been widely used in the field of image feature(IF) fusion recognition, and the research involves multiple research fields. In addition to image recognition or image classification, it has been studied in computer vision, industrial control and other aspects. This paper focuses on the analysis of the IF of the fusion BP NN. This paper briefly analyzes the fusion of IF, spectral features and texture features, proposes BP NN algorithm, and applies it to image fusion design; Finally, through experimental tests, the detection accuracy of fusion BP NN and traditional BP algorithm in IF fusion is compared and analyzed, which verifies the effectiveness and feasibility of the BP NN algorithm in this paper.

Image detail enhancement of nanocomposites based on deep convolution neural networks

Abstract: Abstract Research on the image detail enhancement algorithm of nanocomposites can better improve the image quality of nanocomposites and facilitate researchers to understand the structural characteristics of materials. Due to the problems of low image quality and difficulty to retain the details of traditional nanocomposite image details enhancement algorithms, a new nanocomposite image details enhancement algorithm based on deep convolution neural networks (DCNN) is designed. Through histogram equalization, linear gray-scale stretching and median filtering, the image of nanocomposite is preprocessed, and then FCM algorithm is used for edge detection and image segmentation. Using color model transformation algorithm and DCNN, an image detail enhancement model including feature extraction and nonlinear mapping is constructed. Finally, the idea of image detail reconstruction is introduced, and image detail reconstruction is realized through a convolution layer. The results show that compared with the experimental comparison algorithm, the image processed by the proposed algorithm contains more detailed information and has higher image quality. The PSNR value reaches 27.1 dB, which indicates that the nanocomposite image has a better detail enhancement effect and can be widely used in the field of nanocomposite analysis and research.

Improved Cam Shift Algorithm for Detecting Athletes' Action Targets in Sports Videos

Abstract: The detection and tracking of athletes in sports videos is of great importance, as it helps to automate the analysis of sports videos, thus providing advanced tools and instruments for sports training. The Cam Shift algorithm uses the colour information of objects to achieve tracking of moving targets, so it is very important to choose a suitable colour space when obtaining the colour information of objects. To this end, this paper improves the Cam Shift algorithm by converting the visual system mechanism to perceive the colour characteristics of the image processing, i.e., converting the video image from the RGB colour space to the HSV colour space, using the H (hue) component to model the target object. Experiments show that the improved athlete detection and tracking algorithm is more robust in practical applications. The improved tracking algorithm also has better real-time performance, with a processing speed of 20 fps during the experiments.

Vanadium Complexes Derived from O,N,O-tridentate 6-bis(o-hydroxyalkyl/aryl)pyridines: Structural Studies and Use in the Ring-Opening Polymerization of ε-Caprolactone and Ethylene Polymerization

Abstract: Interaction of [VO(OiPr)3] with 6-bis(o-hydroxyaryl)pyridine, 2,6-{HOC(Ph)2CH2}2(NC5H3), LH2, afforded [VO(OiPr)L] (1) in good yield. The reaction of LNa2, generated in-situ from LH2 and NaH, with [VCl3(THF)3] led to the isolation of [VL2] (2) in which the pyridyl nitrogen atoms are cis; a regioisomer 3∙2THF, in which the pyridyl nitrogen atoms are trans, was isolated when using [VCl2(TMEDA)2]. The reaction of the 2,6-bis(o-hydroxyalkyl)pyridine {HOC(iPr)2CH2}2(NC5H3), L1H2, with [VO(OR)3] (R = nPr, iPr) led, following work-up, to [VO(OR)L1] (R = nPr (4), iPr (5)). Use of the bis(methylpyridine)-substituted alcohol (tBu)C(OH)[CH2(C5H3Me-5)]2, L2H, with [VO(OR)3] (R = Et, iPr) led to the isolation of [VO(μ-O)(L2)]2 (6). Complexes 1 to 6 have been screened for their ability to act as pre-catalysts for the ring opening polymerization (ROP) of ε-caprolactone (ε-CL), δ-valerolactone (δ-VL), and rac-lactide (r-LA) and compared against the known catalyst [Ti(OiPr)2L] (I). Complexes 1, 4–6 were also screened as catalysts for the polymerization of ethylene (in the presence of dimethylaluminium chloride/ethyltrichloroacetate). For the ROP of ε-CL, in toluene solution, conversions were low to moderate, affording low molecular weight products, whilst as melts, the systems were more active and afforded higher molecular weight polymers. For δ-VL, the systems run as melts afforded good conversions, but in the case of r-LA, all systems as melts exhibited low conversions (<10%) except for 6 (<54%) and I (<39%). In the case of ethylene polymerization, the highest activity (8600 Kg·mol·V−1bar−1h−1) was exhibited by 1 in dichloromethane, affording high molecular weight, linear polyethylene at 70 °C. In the case of 4 and 5, which contain the propyl-bearing chelates, the activities were somewhat lower (≤1500 Kg·mol·V−1bar−1h−1), whilst 6 was found to be inactive.