Search

Your search keyword '"Han, Jiacheng"' showing total 34 results
Start Over Author "Han, Jiacheng"
34 results on '"Han, Jiacheng"'

1. PESAM: Privacy-Enhanced Segment Anything Model for Medical Image Segmentation

Author

Cai, Jiuyun, Niu, Ke, Pan, Yijie, Tai, Wenjuan, Han, Jiacheng, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Huang, De-Shuang, editor, Zhang, Xiankun, editor, and Pan, Yijie, editor

Published
2024
Full Text
View/download PDF

2. Lane detection with Position Embedding

Author

Xie, Jun, Han, Jiacheng, Qi, Dezhen, Chen, Feng, Huang, Kaer, and Shuai, Jianwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Recently, lane detection has made great progress in autonomous driving. RESA (REcurrent Feature-Shift Aggregator) is based on image segmentation. It presents a novel module to enrich lane feature after preliminary feature extraction with an ordinary CNN. For Tusimple dataset, there is not too complicated scene and lane has more prominent spatial features. On the basis of RESA, we introduce the method of position embedding to enhance the spatial features. The experimental results show that this method has achieved the best accuracy 96.93% on Tusimple dataset.

Published
2022

7. Improving Deep Image Matting via Local Smoothness Assumption

Author

Wang, Rui, Xie, Jun, Han, Jiacheng, and Qi, Dezhen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-posed, further assumptions on the data distribution are required to make the problem well-posed. For classical matting methods, a commonly adopted assumption is the local smoothness assumption on foreground and background colors. However, the use of such assumptions was not systematically considered for deep learning based matting methods. In this work, we consider two local smoothness assumptions which can help improving deep image matting models. Based on the local smoothness assumptions, we propose three techniques, i.e., training set refinement, color augmentation and backpropagating refinement, which can improve the performance of the deep image matting model significantly. We conduct experiments to examine the effectiveness of the proposed algorithm. The experimental results show that the proposed method has favorable performance compared with existing matting methods., Comment: 9 pages, accepted by IEEE ICME 2022

Published
2021

25. Design And Simulation Of An Air Floating Platform With Zero Gravity Self-adjusting

Author

Li Duanling, Han Jiacheng, Fu Jincai, Li Lin, and Li Bing

Subjects
0209 industrial biotechnology, Gravity (chemistry), Spacecraft, Levelling, Computer science, business.industry, 02 engineering and technology, Self adjusting, Space exploration, 020901 industrial engineering & automation, Software deployment, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Zero gravity, business, Floating platform, Simulation
Abstract

With the rapid development of space exploration, the performance of spacecraft is increasingly demanded. So, on the ground, we need to simulate the zero gravity environment and perform performance tests on the satellite antenna deployment system. In response to this demand, a kind of zero gravity self-adjusting air floating platform has been designed. The composition and principle of the air floating platform have been elaborated, and the performance of the platform has been measured and analyzed. The platform can realize automatic levelling and own high levelling precision and fast speed. It is a good simulation of the ground zero gravity environment and can effectively evaluate the simulation results.

Published
2019

27. GTree: an Open-source Tool for Dense Reconstruction of Brain-wide Neuronal Population

Author

Zhou, Hang, primary, Li, Shiwei, additional, Li, Anan, additional, Huang, Qing, additional, Xiong, Feng, additional, Li, Ning, additional, Han, Jiacheng, additional, Kang, Hongtao, additional, Chen, Yijun, additional, Li, Yun, additional, Lin, Huimin, additional, Zhang, Yu-Hui, additional, Lv, Xiaohua, additional, Liu, Xiuli, additional, Gong, Hui, additional, Luo, Qingming, additional, Zeng, Shaoqun, additional, and Quan, Tingwei, additional

Published
2020
Full Text
View/download PDF

29. Dense reconstruction of brain-wide neuronal population close to the ground truth

Author

Zhou Hang, Li Shiwei, Li Anan, Xiong Feng, Li Ning, Han Jiacheng, Kang Hongtao, Chen Yijun, Li Yun, Fang Wenqian, Liu Yidong, Lin Huimin, Jin Sen, Li Zhiming, Xu Fuqiang, Zhang Yu-hui, Lv Xiaohua, Liu Xiuli, Gong Hui, Luo Qingming, Quan Tingwei, and Zeng Shaoqun

Subjects
Ground truth, Tree (data structure), Computer science, business.industry, Confocal, SIGNAL (programming language), Pattern recognition, Point (geometry), Tomography, Artificial intelligence, Projection (set theory), business
Abstract

Neuron is the basic structure and functional unit of the brain, its projection and connections with other neurons provide a basic physical infrastructure for neural signal storage, allocation, processing, and integration. Recent technique progresses allow for labeling and imaging specific neuronal populations at single axonal level across a whole mouse brain. However, digital reconstruction of these neuron individuals needs months of human labor or sometimes is even an impossible task. Here we developed a software tool, Advanced NeuroGPS-Tree (AdTree), to solve this problem. AdTree offers a special error screening system to achieve reconstruction close to the round truth. Moreover, AdTree equips with algorithms significantly reduces intense manual interferences and achieves high-level automated reconstruction. We demonstrated using AdTree to get almost complete reconstruction from basal dendrites to far-end axonal terminals on dense datasets that challenge state-of-the-art software tools, and even the manual reconstruction with commercial software, whose accuracy is well acknowledged. We also demonstrated about 5 times speed faster over commercial software in brain-wide reconstruction. In addition, AdTree is applicable on datasets collected with different types of light microscopies such as confocal, two-photon, and light-sheet and serial sectioning wide-field tomography. This tool will provide a starting point to reconstruct neuronal population for cell type, circuit, and neurocomputing studies at single cell level.

Published
2017
Full Text
View/download PDF

34. Effects of transcutaneous acupoint electrical stimulation on the imbalance of Th 1 , Th 2 , Th 17 and T reg cells following thoracotomy of patients with lung cancer.

Author

Wu H, Wang K, Li G, Meng D, Han J, Wang G, and Li YU

Abstract

An imbalance in the various T lymphocytes, including T-helper (Th) 1 , Th 2 and Th 17 cells, and regulatory T (T reg ) cells, has been associated with immune dysfunction, and may occur following thoracotomy of patients with lung cancer. The use of transcutaneous acupoint electrical stimulation (TAES) has previously been demonstrated to exert immunoregulatory effects; therefore, the present study aimed to evaluate whether TAES was able to attenuate postoperative immune suppression in patients with lung cancer. Thoracic surgical patients with lung cancer (n=27) underwent TAES (frequency, 2/100 Hz; intensity, 4-12 mA) at the bilateral large intestine 4, pericardium 6, small intestine 3 and San Jiao 6 acupuncture points for 30 min, prior to incision, and at 20, 44, 68, 92 and 116 h following thoracotomy. The number of Th 1 , Th 2 , Th 17 and T reg cells, and the protein and mRNA expression levels of related cytokines were measured by flow cytometry, ELISA and polymerase chain reaction, respectively. The balance of Th 1 , Th 2 , Th 17 and T reg cells in the peripheral blood of patients with lung cancer was disrupted following thoracotomy. TAES administration increased the percentage of Th 1 and Th 17 cells, the protein expression levels of interleukin (IL)-2 and interferon-γ, the mRNA expression levels of T-bet and RAR-related orphan receptor-γt, and decreased the percentage of Th 2 cells, IL-10 protein expression levels, and GATA binding protein 3 mRNA expression levels. The results of the present study demonstrated that TAES was able to partially attenuate the postoperative immune depression of patients with lung cancer, by regulating the balance of Th 1 , Th 2 , Th 17 and T reg cells, and the expression levels of related cytokines and transcription factors; therefore, TAES may be considered to be a promising strategy for treating postoperative immune dysfunction in patients with lung cancer.

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results