中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共7条，第1-7条

帮助

条数/页：排序方式：
	In silico off-target profiling for enhanced drug safety assessment 期刊论文 OAI收割 ACTA PHARMACEUTICA SINICA B, 2024, 卷号: 14, 期号: 7, 页码: 2927-2941 作者: Liu, Jin; Gui, Yike; Rao, Jingxin; Sun, Jingjing; Wang, Gang \| 收藏 \| 浏览/下载：11/0 \| 提交时间：2024/08/22 Drug safety Off-target prediction Adverse drug reactions Toxicity Molecular representation Artificial intelligence
	Prescribed-Time Adaptive Fuzzy Control for Pneumatic Artificial Muscle-Actuated Parallel Robots With Input Constraints 期刊论文 OAI收割 IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2024, 卷号: 32, 期号: 4, 页码: 2039-2051 作者: Diao, Shuzhen; Liu, Gendi; Liu, Zhuoqing; Zhou, Lu; Sun, Wei \| 收藏 \| 浏览/下载：27/0 \| 提交时间：2024/07/03 Parallel robots Actuators Target tracking Sun Muscles Transient analysis Safety Pneumatic artificial muscles (PAMs) multiple input constraints parallel robots prescribed-time control
	Robust correlation filter tracking with deep semantic supervision 期刊论文 OAI收割 IET IMAGE PROCESSING, 2019, 卷号: 13, 期号: 5, 页码: 754-760 作者: Wang, Wei; Chen, Zhaoming; Douadji, Lyes; Shi, Mingquan \| 收藏 \| 浏览/下载：89/0 \| 提交时间：2019/06/24 particle filtering (numerical methods) learning (artificial intelligence) target tracking convolutional neural nets robust correlation filter tracking high tracking performance tracking failure deep semantic supervision tracking framework redetection tracking mechanism particle filtering resampling CF tracker deep convolutional neural network tracking frames target occlusion handcrafted features real-time performance OTB2013 benchmark datasets OTB2015 benchmark datasets
	In-Flight Radiometric Calibration for ZY-3 Satellite Multispectral Sensor by Modified Reflectance-Based Method 期刊论文 OAI收割 SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 卷号: 35, 期号: 3, 页码: 305-326 作者: Han Jie; Xie Yong; Gu Xing-fa; Yu Tao; Liu Qi-yue 收藏 \| 浏览/下载：27/0 \| 提交时间：2016/04/20 ZY-3 satellite Multispectral sensor Artificial target Radiometric calibration
	The ship-borne infrared searching and tracking system based on the inertial platform (EI CONFERENCE) 会议论文 OAI收割 International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, May 24, 2011 - May 24, 2011, Beijing, China 作者: Li Y.; Zhang H.; Zhang H.; Li Y.; Li Y. 收藏 \| 浏览/下载：38/0 \| 提交时间：2013/03/25 As a result of the radar system got interferenced or in the state of half silent it can cause the guided precision drop badly In the modern electronic warfare therefore it can lead to the equipment depended on electronic guidance cannot strike the incoming goals exactly. It will need to rely on optoelectronic devices to make up for its shortcomings but when interference is in the process of radar leading especially the electro-optical equipment is influenced by the roll pitch and yaw rotation it can affect the target appear outside of the field of optoelectronic devices for a long time so the infrared optoelectronic equipment can not exert the superiority and also it cannot get across weapon-control system "reverse bring" missile against incoming goals. So the conventional ship-borne infrared system unable to track the target of incoming quickly the ability of optoelectronic rivalry declines heavily.Here we provide a brand new controlling algorithm for the semi-automatic searching and infrared tracking based on inertial navigation platform. Now it is applying well in our XX infrared optoelectronic searching and tracking system. The algorithm is mainly divided into two steps: The artificial mode turns into auto-searching when the deviation of guide exceeds the current scene under the course of leading for radar.When the threshold value of the image picked-up is satisfied by the contrast of the target in the searching scene the speed computed by using the CA model Least Square Method feeds back to the speed loop. And then combine the infrared information to accomplish the closed-loop control of the infrared optoelectronic system tracking. The algorithm is verified via experiment. Target capturing distance is 22.3 kilometers on the great lead deviation by using the algorithm. But without using the algorithm the capturing distance declines 12 kilometers. The algorithm advances the ability of infrared optoelectronic rivalry and declines the target capturing time by using semi-automatic searching and reliable capturing-tracking when the lead deviation of the radar is great. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).
	The research of the accurate measure of static transfer function for the TDI CCD camera (EI CONFERENCE) 会议论文 OAI收割 3rd International Photonics and OptoElectronics Meetings, POEM 2010, November 2, 2010 - November 5, 2010, Wuhan, China Guo-Ning L.; Long-Xu J.; Jian-Yue R.; Wen-Hua W.; Shuang-Li H. 收藏 \| 浏览/下载：25/0 \| 提交时间：2013/03/25 In the test course of static transfer function of TDI CCD camera because of the influence that gets environmental and artificial etc. factor the value of static transfer function measured at any time is between unceasing fluctuation so make accuracy reduce. To solve this problem a kind of accurate measurement technique of static transfer function is put forward. First before carrying out the measure of static quiet of transfer function the best test point of transfer function of the TDI CCD camera must be determined it is parallel to guarantee the rectangle target surface of parallel optical pipe and camera focal plane maintenance parallel and again guarantee target strip in rectangle target and TDI CCD in camera focal plane maintenance vertical. TDI CCD catches rectangle target image per 1000 lines of target mark image as a measures sample of static transfer function exclude because of atmosphere tremble twisted vague rectangle target mark image retain 500 distinct and steady target mark image as measure sample set. Then calculate the static transfer function of each measure sample respectively take the average of all static quiet transfer function in measure sample set as the static transfer function of camera. Finally the measure of the static transfer function for TDI CCD camera makes error analysis. Experimental results indicate that the value of the static transfer function of TDI CCD camera measured with this kind of method is 0.2923 with before measurement technique comparison the value of static transfer function has raised 0.02 makes the accuracy of the measure of static transfer function have gotten raising.
	Intelligent MRTD testing for thermal imaging system using ANN (EI CONFERENCE) 会议论文 OAI收割 ICO20: Remote Sensing and Infrared Devices and Systems, August 21, 2005 - August 26, 2005, Changchun, China Sun J.; Ma D. 收藏 \| 浏览/下载：27/0 \| 提交时间：2013/03/25 The Minimum Resolvable Temperature Difference (MRTD) is the most widely accepted figure for describing the performance of a thermal imaging system. Many models have been proposed to predict it. The MRTD testing is a psychophysical task for which biases are unavoidable. It requires laboratory conditions such as normal air condition and a constant temperature. It also needs expensive measuring equipments and takes a considerable period of time. Especially when measuring imagers of the same type the test is time consuming. So an automated and intelligent measurement method should be discussed. This paper adopts the concept of automated MRTD testing using boundary contour system and fuzzy ARTMAP but uses different methods. It describes an Automated MRTD Testing procedure basing on Back-Propagation Network. Firstly we use frame grabber to capture the 4-bar target image data. Then according to image gray scale we segment the image to get 4-bar place and extract feature vector representing the image characteristic and human detection ability. These feature sets along with known target visibility are used to train the ANN (Artificial Neural Networks). Actually it is a nonlinear classification (of input dimensions) of the image series using ANN. Our task is to justify if image is resolvable or uncertainty. Then the trained ANN will emulate observer performance in determining MRTD. This method can reduce the uncertainties between observers and long time dependent factors by standardization. This paper will introduce the feature extraction algorithm demonstrate the feasibility of the whole process and give the accuracy of MRTD measurement.