中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共5条，第1-5条

帮助

条数/页：排序方式：
	Multi-Stage Image-Language Cross-Generative Fusion Network for Video-Based Referring Expression Comprehension 期刊论文 OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 卷号: 33, 页码: 3256-3270 作者: Zhang, Yujia; Li, Qianzhong \| 收藏 \| 浏览/下载：26/0 \| 提交时间：2024/07/03 Feature extraction Visualization Task analysis Representation learning Location awareness Linguistics Grounding Video-based referring expression comprehension multi-stage learning image-language cross-generative fusion consistency loss
	Realization of FPGA-based video image fusion technology 会议论文 OAI收割 2015 international conference on advanced electronics and communications engineering, shanghai, china, 2015-02 作者: Duan CP; W. Liu; Y.H. Chen; Q.S. Xie; B. Yi 收藏 \| 浏览/下载：26/0 \| 提交时间：2016/01/05 video image fusion ADV7180 image registration pixel weighted average
	The new approach for infrared target tracking based on the particle filter algorithm (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: Sun H.; Han H.-X.; Sun H. 收藏 \| 浏览/下载：59/0 \| 提交时间：2013/03/25 Target tracking on the complex background in the infrared image sequence is hot research field. It provides the important basis in some fields such as video monitoring precision and video compression human-computer interaction. As a typical algorithms in the target tracking framework based on filtering and data connection the particle filter with non-parameter estimation characteristic have ability to deal with nonlinear and non-Gaussian problems so it were widely used. There are various forms of density in the particle filter algorithm to make it valid when target occlusion occurred or recover tracking back from failure in track procedure but in order to capture the change of the state space it need a certain amount of particles to ensure samples is enough and this number will increase in accompany with dimension and increase exponentially this led to the increased amount of calculation is presented. In this paper particle filter algorithm and the Mean shift will be combined. Aiming at deficiencies of the classic mean shift Tracking algorithm easily trapped into local minima and Unable to get global optimal under the complex background. From these two perspectives that "adaptive multiple information fusion" and "with particle filter framework combining" we expand the classic Mean Shift tracking framework.Based on the previous perspective we proposed an improved Mean Shift infrared target tracking algorithm based on multiple information fusion. In the analysis of the infrared characteristics of target basis Algorithm firstly extracted target gray and edge character and Proposed to guide the above two characteristics by the moving of the target information thus we can get new sports guide grayscale characteristics and motion guide border feature. Then proposes a new adaptive fusion mechanism used these two new information adaptive to integrate into the Mean Shift tracking framework. Finally we designed a kind of automatic target model updating strategy to further improve tracking performance. Experimental results show that this algorithm can compensate shortcoming of the particle filter has too much computation and can effectively overcome the fault that mean shift is easy to fall into local extreme value instead of global maximum value.Last because of the gray and fusion target motion information this approach also inhibit interference from the background ultimately improve the stability and the real-time of the target track. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).
	互联网不良图像及视频检测技术学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2010 作者: 左海强收藏 \| 浏览/下载：56/0 \| 提交时间：2015/09/02 不良信息检测肤色检测色情图像检测色情视频检测音视频融合 Harmful information detection human skin tone detection pornographic image detection pornographic video detection audio and video fusion
	Restoration of an atmospherically blurred image based on physical model fusion approach (EI CONFERENCE) 会议论文 OAI收割 2010 IEEE 10th International Conference on Signal Processing, ICSP2010, October 24, 2010 - October 28, 2010, Beijing, China 作者: Wang Y.; Li J.; Li J.; Li J.; Wang Y. 收藏 \| 浏览/下载：26/0 \| 提交时间：2013/03/25 This paper proposes a new restoration method only using the single image information combining atmospheric physical model with fusion techniques to reduce the degradation of the image contrast in bad weather conditions caused by atmospheric aerosols such as haze and fog. The basic idea of this method is to utilize physics-based model method instead of multisensors to generate a serial of virtual images and then to fuse those virtual images into a high contrast image based on the wavelet fusion technique. In contrast to previous methods our restoration technique is not only independent on predicted structure distributions of scene reflectance or detailed knowledge about the particular weather condition but also adapt to the situation without a reference image or images with moving objects captured by a video camera. Experiments on different poorcontrast images demonstrate the availability of the proposed method in case of restoring the atmospherically blurred images. 2010 IEEE.