Search

Your search keyword '"Sun, Ziwei"' showing total 173 results
Start Over Author "Sun, Ziwei"
173 results on '"Sun, Ziwei"'

1. A Flying Bird Object Detection Method for Surveillance Video

Author

Sun, Ziwei, Hua, Zexi, Li, Hengchao, and Li, Yan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Aiming at the specific characteristics of flying bird objects in surveillance video, such as the typically non-obvious features in single-frame images, small size in most instances, and asymmetric shapes, this paper proposes a Flying Bird Object Detection method for Surveillance Video (FBOD-SV). Firstly, a new feature aggregation module, the Correlation Attention Feature Aggregation (Co-Attention-FA) module, is designed to aggregate the features of the flying bird object according to the bird object's correlation on multiple consecutive frames of images. Secondly, a Flying Bird Object Detection Network (FBOD-Net) with down-sampling followed by up-sampling is designed, which utilizes a large feature layer that fuses fine spatial information and large receptive field information to detect special multi-scale (mostly small-scale) bird objects. Finally, the SimOTA dynamic label allocation method is applied to One-Category object detection, and the SimOTA-OC dynamic label strategy is proposed to solve the difficult problem of label allocation caused by irregular flying bird objects. In this paper, the performance of the FBOD-SV is validated using experimental datasets of flying bird objects in traction substation surveillance videos. The experimental results show that the FBOD-SV effectively improves the detection performance of flying bird objects in surveillance video.

Published
2024

2. Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Information

Author

Sun, Ziwei, Hua, Zexi, Li, Hengcao, and Zhong, Haiyan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

A Flying Bird Object Detection algorithm Based on Motion Information (FBOD-BMI) is proposed to solve the problem that the features of the object are not obvious in a single frame, and the size of the object is small (low Signal-to-Noise Ratio (SNR)) in surveillance video. Firstly, a ConvLSTM-PAN model structure is designed to capture suspicious flying bird objects, in which the Convolutional Long and Short Time Memory (ConvLSTM) network aggregated the Spatio-temporal features of the flying bird object on adjacent multi-frame before the input of the model and the Path Aggregation Network (PAN) located the suspicious flying bird objects. Then, an object tracking algorithm is used to track suspicious flying bird objects and calculate their Motion Range (MR). At the same time, the size of the MR of the suspicious flying bird object is adjusted adaptively according to its speed of movement (specifically, if the bird moves slowly, its MR will be expanded according to the speed of the bird to ensure the environmental information needed to detect the flying bird object). Adaptive Spatio-temporal Cubes (ASt-Cubes) of the flying bird objects are generated to ensure that the SNR of the flying bird objects is improved, and the necessary environmental information is retained adaptively. Finally, a LightWeight U-Shape Net (LW-USN) based on ASt-Cubes is designed to detect flying bird objects, which rejects the false detections of the suspicious flying bird objects and returns the position of the real flying bird objects. The monitoring video including the flying birds is collected in the unattended traction substation as the experimental dataset to verify the performance of the algorithm. The experimental results show that the flying bird object detection method based on motion information proposed in this paper can effectively detect the flying bird object in surveillance video.

Published
2023

22. The Method of Detecting Flying Birds in Surveillance Video Based on Their Characteristics

Author

Sun, Ziwei, Hua, Zexi, Li, Hengchao, Li, Yan, Sun, Ziwei, Hua, Zexi, Li, Hengchao, and Li, Yan

Abstract

Aiming at the characteristics of the flying bird object in surveillance video, such as the single frame image feature is not obvious, the size is small in most cases, and asymmetric, this paper proposes a Flying Bird Object Detection method in Surveillance Video (FBOD-SV). Firstly, a new feature aggregation module, the Correlation Attention Feature Aggregation (Co-Attention-FA) module, is designed to aggregate the features of the flying bird object according to the bird object's correlation on multiple consecutive frames of images. Secondly, a Flying Bird Object Detection Network (FBOD-Net) with down-sampling and then up-sampling is designed, which uses a large feature layer that fuses fine spatial information and large receptive field information to detect special multi-scale (mostly small-scale) bird objects. Finally, the SimOTA dynamic label allocation method is applied to One-Category object detection, and the SimOTA-OC dynamic label strategy is proposed to solve the difficult problem of label allocation caused by irregular flying bird objects. In this paper, the algorithm's performance is verified by the experimental data set of the surveillance video of the flying bird object of the traction substation. The experimental results show that the surveillance video flying bird object detection method proposed in this paper effectively improves the detection performance of flying bird objects.

Published
2024

23. Visual Question Answer System Based on Bidirectional Recurrent Networks

Author

Tang, Haoyang, Qian, Meng, Sun, Ziwei, Song, Cong, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Krömer, Pavel, editor, Zhang, Hong, editor, Liang, Yongquan, editor, and Pan, Jeng-Shyang, editor

Published
2019
Full Text
View/download PDF

25. Nanometer-Thick CsPbBr3 Films with Embedded CsPb2Br5 Nanowires for Photodetector Applications.

Author

Sun, Ziwei, Wang, Yong, Liu, Ye, Liu, Ruliang, Chen, Tao, Ye, Shuming, Lai, Niu, Cui, Haoyang, Lin, Feng, Wang, Rongfei, Yang, Jie, Ke, Shaoying, and Wang, Chong

Abstract

All-inorganic perovskite materials have gained enormous attention in photodetectors (PDs) due to their high charge carrier mobility, cost-effectiveness, and tunable bandgap. However, instability and corresponding performance degradation of perovskite PDs when exposed to surrounding humidity persist as challenges. In this work, a composite PD was fabricated by combining CsPb2Br5 nanowires and CsPbBr3 thin-film perovskites as an example to address these problems. The CsPb2Br5 nanowires were prepared by a facile water-bath method to improve the water resistance, and the subsequent evaporation of the CsPbBr3 film formed a type-I heterostructure to enhance its photosensitivity of PDs. As a result, the device exhibits a 10 times higher responsivity of 206 mA/W than that of the bare CsPbBr3 thin film device and maintains 92.85% of its original detectivity after being exposed to a humid environment (RH = 75%) for 144 h. Furthermore, the corresponding fundamental characterization was also performed to reveal the role of CsPb2Br5 nanowires in enhancing the overall performance of the PD. This work provides a simple and efficient approach to enhancing the durability and performance of all-inorganic halide perovskite devices through the embedding of CsPb2Br5 perovskite nanowires. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

27. Oleic Acid‐Assisted Nucleation Growth of Highly Luminescent CsCu2I3 Single Crystals and Their Films for Flexible and Dynamic High‐Resolution X‐Ray Imaging

Author

Chen, Tao, primary, Li, Xin, additional, Lin, Feng, additional, Wu, Haodi, additional, Mu, Dedan, additional, Sun, Ziwei, additional, Chen, Chen, additional, Liu, Ruliang, additional, Yang, Jie, additional, Wang, Rongfei, additional, Zhao, Zhenhuan, additional, Meng, Bin, additional, Wen, Xiaoming, additional, Bao, Jiming, additional, Tang, Jiang, additional, Xu, Xuhui, additional, and Wang, Chong, additional

Published
2023
Full Text
View/download PDF

32. Oleic Acid‐Assisted Nucleation Growth of Highly Luminescent CsCu2I3 Single Crystals and Their Films for Flexible and Dynamic High‐Resolution X‐Ray Imaging.

Author

Chen, Tao, Li, Xin, Lin, Feng, Wu, Haodi, Mu, Dedan, Sun, Ziwei, Chen, Chen, Liu, Ruliang, Yang, Jie, Wang, Rongfei, Zhao, Zhenhuan, Meng, Bin, Wen, Xiaoming, Bao, Jiming, Tang, Jiang, Xu, Xuhui, and Wang, Chong

Subjects
X-ray imaging, SCINTILLATORS, SINGLE crystals, DISCONTINUOUS precipitation, ABSORPTION coefficients, PEROVSKITE
Abstract

Metal‐halide perovskites have emerged as one of the most promising contenders for the next‐generation X‐ray scintillators on account of their large absorption coefficients, high light yields, and low‐cost fabrication. However, the existing X‐ray scintillators are plagued either by poor stability or high toxicity. Here, highly stable and flexible CsCu2I3@polymethyl methacrylate (PMMA) composite films are fabricated simply by a facile one‐step drop‐coating technique. Benefiting from the reasonable light yields (24 100 photons MeV−1), short photoluminescence decay time (207 ns), and flat surface, a low detection limit of 39 nGyair s−1 and a record‐high resolution of up to 25 lp mm−1 are demonstrated in these CsCu2I3@PMMA composite films. The X‐ray imaging tests show that the CsCu2I3@PMMA composite films display excellent properties in the dynamic and irregular objects imaging. In addition, the CsCu2I3@PMMA composite films exhibit a desirable endurance to the high‐energy X‐ray's irradiation and the water erosion (photoluminescence quantum yield remains up of 90% of its initial value even after submersion in water for 300 h). This work provides a potential to develop eco‐friendly and highly stable halide perovskite materials for high‐resolution X‐ray imaging. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

35. Zeolitic imidazolate framework-8 modified bacterial cellulose/sodium alginate composite aerogel for efficient removal of tetracycline hydrochloride.

Author

Yang, Xu, Bismark, Sarkodie, Wang, Dengbing, Liu, Zuyi, Tao, Yun, Sun, Ziwei, Han, Xu, and Feng, Quan

Subjects
SODIUM alginate, AEROGELS, LANGMUIR isotherms, FOURIER transform infrared spectroscopy, TETRACYCLINE
Abstract

Antibiotics released in the water pose a serious threat to human and ecological health. Therefore, it is of great importance to effectively remove antibiotics from wastewater. In this study, recyclable bacterial cellulose/sodium alginate/zeolitic imidazolate framework-8 (BC/SA/ZIF-8) aerogel composites were prepared by chemical cross-linking and in situ growth in freeze-drying. The successful preparation of the composite aerogel was confirmed by scanning electron microscope (SEM), Fourier Transform infrared spectroscopy (FTIR) and X-ray diffraction (XRD) analysis. The results reveal that BC/SA/ZIF-8 aerogel composite has significantly high BET specific surface area of 165.24 m2/g than that of BC/SA at 7.39 m2/g. The BC/SA/ZIF-8 composite aerogel exhibited excellent adsorption performance for tetracycline hydrochloride, with a maximum adsorption capacity of 746.27 mg/g. The adsorption process followed the pseudo-second-order kinetic model and Langmuir adsorption isotherm model. Moreover, the reusability test on BC/SA/ZIF-8 composite aerogel revealed an insignificant decline in adsorption after six cycles. Therefore, BC/SA/ZIF-8 composite aerogel has a high potential as a novel and recyclable adsorbent for efficient removal of tetracycline hydrochloride from water. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

38. Small Moving Object Detection Algorithm in Surveillance Video Based on Motion Information

Author

Sun, Ziwei, Hua, Zexi, Li, Hengcao, and Zhong, Haiyan

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

A Small Moving Object Detection algorithm Based on Motion Information (SMOD-BMI) is proposed to detect small moving objects with a low Signal-to-Noise Ratio (SNR) in surveillance video. Firstly, a ConvLSTM-PAN model structure is designed to capture suspicious small moving objects, in which the Convolutional Long and Short Time Memory (ConvLSTM) network aggregated the Spatio-temporal features of the adjacent multi-frame small moving object and the Path Aggregation Network (PAN) located the suspicious small moving objects. Then, an object tracking algorithm is used to track suspicious small objects and calculate their Motion Range (MR). At the same time, the size of the MR of the suspicious small moving object is adjusted adaptively according to its speed of movement (specifically, if the object moves slowly, its MR will be expanded according to the speed of the object to ensure the necessary environmental information of the object). Adaptive Spatio-temporal Cubes (ASt-Cubes) of the small moving objects are generated to ensure that the SNR of the moving objects is improved, and the necessary environmental information is retained adaptively. Finally, a LightWeight U-Shape Net (LW-USN) based on ASt-Cubes is designed to detect small moving objects, which rejects false detections and returns the position of small moving objects. This paper uses the bird in the surveillance video as the experimental data set to verify the algorithm's performance. The experimental results show that the proposed small moving object detection method based on motion information in surveillance video can effectively reduce the missed and false detection rate of small moving objects.

Published
2023

43. Unencapsulated CsPbClBr2 Film Photodetectors Grown by Thermal Vacuum Deposition Exhibit Exceptional Environmental Stability in High-Humidity Air

Author

Li, Xiaonan, primary, Wang, Yong, additional, Chen, Tao, additional, Xu, Tian, additional, Ye, Shuming, additional, Liu, Ruliang, additional, Sun, Ziwei, additional, Tan, Chuhui, additional, Lv, Xinze, additional, Yang, Jie, additional, Wang, Rongfei, additional, Ke, Shaoying, additional, Cui, Haoyang, additional, Wen, Xiaoming, additional, and Wang, Chong, additional

Published
2022
Full Text
View/download PDF

45. Construction of Novel Prognostic Nomogram for Mucinous and Signet Ring Cell Colorectal Cancer Patients with a Survival Longer Than 5 Years

Author

Xu,Juan, Sun,Ziwei, Ju,Huanyu, Xie,Erfu, Mu,Yuan, Xu,Jian, Pan,Shiyang, Xu,Juan, Sun,Ziwei, Ju,Huanyu, Xie,Erfu, Mu,Yuan, Xu,Jian, and Pan,Shiyang

Abstract

Juan Xu,1,2,* Ziwei Sun,1,2,* Huanyu Ju,1,2 Erfu Xie,1,2 Yuan Mu,1,2 Jian Xu,1,2 Shiyang Pan1,2 1Department of Laboratory Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People’s Republic of China; 2Branch of National Clinical Research Center for Laboratory Medicine, Nanjing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Shiyang Pan, Tel +86 139 5181 4639, Email sypan@njmu.edu.cnPurpose: Mucinous adenocarcinoma (MA) and signet ring cell carcinoma (SRCC) are aggressive colorectal cancer histological subtypes with dismal prognosis. This study investigated prognostic factors and constructed novel nomograms for MA and SRCC patients who survived for over 5 years to optimize the follow-up regime, especially for early-onset patients.Patients and Methods: Data from the Surveillance, Epidemiology, and End Results (SEER) database registered between 2004 and 2018 were extracted. MA and SRCC patients were divided into two groups with survival time of 5 years as a cut-off point. Prognostic factors for overall survival (OS) and cancer-specific survival (CSS) were determined by Cox regression models, and survival curves were plotted by the Kaplan–Meier method.Results: We identified 8286 MA patients (45.73%) and 551 SRCC patients (20.32%) who survived for over 5 years. Multivariable Cox analyses identified age, tumor location, N stage, metastasis, CEA level, surgery, and lymph nodes dissection as independent risk factors for MACSS. SRCC was more aggressive and only N2 stage (P = 0.011) and metastasis (P = 0.043) were inversely associated with SRCCSS. Furthermore, we observed that small tumor size, well differentiation, and chemotherapy no longer provided survival benefit to ≥ 5-year survivors. Therefore, we constructed novel nomograms appropriate for MA patients who survived for over 5 years. The consistency indexes for predicting 10-year OS and CSS were respectively 0.717, 0.

Published
2022

50. Novel mulberry silkworm cocoon-derived carbon dots and their anti-inflammatory properties

Author

Hui Kong, Yue Zhang, Sun Ziwei, Wang Suna, Jinjun Cheng, Meiling Zhang, Huihua Qu, Yan Zhao, Wang Xiaoke, and Jiaxing Liu

Subjects
medicine.drug_class, Anti-Inflammatory Agents, Biomedical Engineering, Pharmaceutical Science, Medicine (miscellaneous), chemistry.chemical_element, 02 engineering and technology, Biology, Anti-inflammatory, Mice, 03 medical and health sciences, 0302 clinical medicine, Sepsis, Quantum Dots, medicine, Animals, Edema, Traditional medicine, fungi, General Medicine, Bombyx, 021001 nanoscience & nanotechnology, Carbon, RAW 264.7 Cells, chemistry, 030220 oncology & carcinogenesis, Female, 0210 nano-technology, Biotechnology
Abstract

Mulberry silkworm cocoon (MSC) carbonisata has been used for the treatment of inflammatory diseases for hundreds of years; however, after years of research efforts, little information is available on its anti-inflammatory components and underlying mechanism. We developed novel carbon dots (CDs) derived from MSC carbonisata (MSC-CDs), for the first time, with an average diameter of 2.26-9.35 nm and a quantum yield (QY) of 6.32%. The MSC-CDs were prepared using a modified pyrolysis method, and no further modification and external surface passivation agent was required. With abundant surface groups, MSC-CDs showed distinct solubility and bioactivity. In this study, we innovatively used three classical experimental models of inflammation to evaluate the anti-inflammatory bioactivity of MSC-CDs. The results indicated that MSC-CDs exhibited marked anti-inflammatory bioactivity which was likely mediated by inhibition of the expression of interleukin-6 and tumour necrosis factor-α. These results suggest that MSC-CDs possess a remarkable anti-inflammatory property, which provides evidence to support further investigation of the considerable potential and effective material basis of this traditional Chinese medicine.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results