Abstract:Fast and high-precision video based image stitching plays an important role in many machine vision applications, such as UAV mapping and reconnaissance. Due to the large number of frames and high redundancy of video sequence, image stitching is very time-consuming. Therefore, from the perspective of reducing the number of redundant frames, this paper proposes a novel video sequence key frame selection method based on rough camera external parameters and key point fusion, which selects the appropriate key frames by optimizing the overlap rate and the number of reliable key points between two adjacent key frames. The algorithm not only greatly reduces the number of key frames, but also ensures the reliable video mosaic. The experimental results on Bu S\' videos show that our method can reduce the number of key frames by 92%. In addition, compared with the key frame selection method based only on navigation information, this method also overcomes the problem of missing stitched images caused by insufficient key points in overlapping regions.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. A novel key frame selection method for aerial image stitching by integrating navigation information and trusted key points
	Zheng Yongji,Wang Guoyou
	Computer Science and Technology 01 April 2021
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Fast and high-precision video based image stitching plays an important role in many machine vision applications, such as UAV mapping and reconnaissance. Due to the large number of frames and high redundancy of video sequence, image stitching is very time-consuming. Therefore, from the perspective of reducing the number of redundant frames, this paper proposes a novel video sequence key frame selection method based on rough camera external parameters and key point fusion, which selects the appropriate key frames by optimizing the overlap rate and the number of reliable key points between two adjacent key frames. The algorithm not only greatly reduces the number of key frames, but also ensures the reliable video mosaic. The experimental results on Bu S\' videos show that our method can reduce the number of key frames by 92%. In addition, compared with the key frame selection method based only on navigation information, this method also overcomes the problem of missing stitched images caused by insufficient key points in overlapping regions.
	TO cite this article:Zheng Yongji,Wang Guoyou. A novel key frame selection method for aerial image stitching by integrating navigation information and trusted key points[OL].[ 1 April 2021] http://en.paper.edu.cn/en_releasepaper/content/4754321


	2. Head Pose Estimation Based on Dlib and Savitzky-Golay Smoothing Algorithm
	LU Xiaoning,LIU Wen
	Computer Science and Technology 18 January 2021
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, We apply the Savitsky-Golay filter algorithm to head pose estimation. Firstly, the Dlib algorithm is to detect key points of the corresponding face in the video. Then, the function solvepnp built in opencv is to estimate the pose. Finally, through MATLAB simulation, we can find that the Savitsky-Golay filter algorithm can filter the noisiness in the observed data to obtain a smoother and more accurate change trajectory of head pose.
	TO cite this article:LU Xiaoning,LIU Wen. Head Pose Estimation Based on Dlib and Savitzky-Golay Smoothing Algorithm[OL].[18 January 2021] http://en.paper.edu.cn/en_releasepaper/content/4753447

Saved Papers

Saved Papers


	3. An Improved Visual-Inertial Odometry Based on Self-Adaptive Attention-Anticipation Feature Selector
	Ruan Wenlong,Wang Jing
	Computer Science and Technology 22 November 2019
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Visual inertia odometers have achieved great success with the development of robot vision. However, it remains a challenging problem to achieve robust and efficient pose estimation on low-power platforms such as smartphones. This paper proposes a new visual inertial odometer scheme for low-power platforms, named visual inertial odometer based on adaptive attention-anticipation mechanism, which adds visual information to the VINS-based visual inertial odometer. The attention distribution module and the motion information forward anticipation module are controlled by the adaptive adjustment module to reduce the system operation load and improve the system tracking accuracy. We contribute in the following three aspects: 1) A attention mechanism for visual inertia history is proposed, which provides visual attention distribution for system radical motion in complex space environment, and extracts vision with high weight on system influence. Feature tracking; 2) A visual feature screening mechanism based on motion prediction is proposed to filter the visual features that will escape the camera perspective in advance; 3) use the adaptive adjustment module for front-end control and efficiently allocate restricted computing resources. Our approach achieves advanced estimation performance on the Euroc MAV datasets.
	TO cite this article:Ruan Wenlong,Wang Jing. An Improved Visual-Inertial Odometry Based on Self-Adaptive Attention-Anticipation Feature Selector[OL].[22 November 2019] http://en.paper.edu.cn/en_releasepaper/content/4750006


	4. Study on Circle Detection Algorithm based on Data Dispersion
	WEI Youying,SHUAI Liguo,CHEN Huiling
	Computer Science and Technology 26 January 2016
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Keywords: circle detection, center coordinates, dispersion To reduce time-consuming, a new algorithm for circle detection is proposed based on data dispersion. The center coordinates and radius can be detected with five steps in this algorithm precisely and quickly; firstly, to reduce the original circle to single-pixel width circle with image processing. Secondly, to calculate the center coordinates with three arbitrary points on the circle. There might be a deviation between the calculated center and real center. Thirdly, to determine a square area for the center coordinates computing with an experimental range and each pixel inside the square is a potential center. Fourthly, to compute the center with distance criterion and the center coordinate is determined when the variance reaches the minimum. Lastly, the radius is equal to the means of the distance vector with the minimum variance. Experiments are conducted and the results show that, comparing with the traditional Hough transform, the new algorit?????
	TO cite this article:WEI Youying,SHUAI Liguo,CHEN Huiling. Study on Circle Detection Algorithm based on Data Dispersion[OL].[26 January 2016] http://en.paper.edu.cn/en_releasepaper/content/4677465


	5. Zooming image by a combination of bi-cubic polynomial with edges as twice constraints
	LIU Ye-Penguin, ZHANG Cai-Ming
	Computer Science and Technology 03 December 2015
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:The clarity and efficiency of the generated image is an important indicator which measures the quality of image zooming. Compared image which is obtained by existed zooming algorithm with the real images, it is more blurrier and consumes much time. On the basis of the existing scaling algorithm, this paper presents a zooming image by a combination of bi-cubic polynomial with edges as twice constraints algorithm. Algorithm is divided into two parts, in the first process, suppose the original scene surface corresponding to given data of the image can be represented by piecewise quadratic polynomial surface, and we can obtain the fitting surface by reversing of solving the image data. Then,by integrated to he fitting surface we can obtain a zooming image which is more blurrier in visual and fidelity. The initial image contains a lot of details of the information, but does not reflect visually. In the second process, it is the purpose that extracts the hide information and makes the image has better visual effect. By comparison, the new algorithm has better amplification effect and higher precision in visual, and spent less time.
	TO cite this article:LIU Ye-Penguin, ZHANG Cai-Ming. Zooming image by a combination of bi-cubic polynomial with edges as twice constraints[OL].[ 3 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4666447


	6. Real-time Road Detection with Image Texture Analysis-based Vanishing Point Estimation
	ZU Zhaozi,XUE Jianru,CUI Dixiao
	Computer Science and Technology 13 January 2013
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Visual perception is a key component of an autonomous vehicle system. Road detection is an essential function of a visual navigation system for an autonomous vehicle. In most cases detecting lane markings is one feasible and efficient approach to road detection. However, in some situation, for example, many rural roads have no lane markings. Furthermore, lacking of sharp, smooth edges and homogeneous surface brings difficulties to road detection. A texture analysis based vanishing point estimation method is used to detect road in this paper. The idea is that consistency in texture leads to the vanishing point in an image. The method uses the Sobel filter to compute the texture orientations. Then the vanishing point of the road is voted from the orientation of the texture. Finally, the vanishing point is used to constrain the searching of two road boundaries since they pass through the vanishing point.
	TO cite this article:ZU Zhaozi,XUE Jianru,CUI Dixiao. Real-time Road Detection with Image Texture Analysis-based Vanishing Point Estimation[OL].[13 January 2013] http://en.paper.edu.cn/en_releasepaper/content/4506414


	7. AN IMPROVED SMART CAR SOLUTION BASED ON HISTOGRAM AND REGION OF INTEREST (ROI)
	CHEN Zeyou,LI Wensheng
	Computer Science and Technology 18 September 2011
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Based on ordinary Hough transform, we propose an improved method by using Histogram and setting Region of interest (ROI), to do the quick Hough transform for tracking lane line. The dynamic adaptive threshold method can be suitable with different lighting conditions and quickly remove most of the information not relative to lane line. Setting ROI can let the program only care about the specific region which can provide useful information and decrease the processing data. And then briefly describe the innovative strategy about how to track the straight and curve line with the logic of monocular vision and the switch logic between them. The experiment shows, the improved solution greatly raises the efficiency.
	TO cite this article:CHEN Zeyou,LI Wensheng. AN IMPROVED SMART CAR SOLUTION BASED ON HISTOGRAM AND REGION OF INTEREST (ROI)[OL].[18 September 2011] http://en.paper.edu.cn/en_releasepaper/content/4443396


	8. LIVER SEGMENTATION BASED ON GRAPH-BASED AND QUADTREE
	Wei Qinlin,Fang Bin,Wang Yi
	Computer Science and Technology 05 September 2011
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, we present an algorithm based on Graph Theory for automatic liver segmentation of CT scans, combining with quad-tree. Firstly the isotropic nonlinear diffusion filter is used to filter the image data, and then the quad-tree algorithm is employed to segment the liver and the initial segmented regions are acquired. Finally we take these regions for the nodes of a graph, and segment the objects from the background by the theory of graph. Experimental results show the good performance of proposed algorithm.
	TO cite this article:Wei Qinlin,Fang Bin,Wang Yi. LIVER SEGMENTATION BASED ON GRAPH-BASED AND QUADTREE[OL].[ 5 September 2011] http://en.paper.edu.cn/en_releasepaper/content/4441763


	9. Adaptive image denoising using anisotropic diffusion and nonlocal means filter
	Fu Shujun,Zhang Caiming
	Computer Science and Technology 03 September 2011
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Adaptive processing integrating the anisotropic diffusion for image edge and detail, and the nonlocal means filter for texture is present in image denoising. Meanwhile, image sharpening is emphasized even if in a single denoising task. The two strategies of feature-dependent adaptive processing and image sharpening give better results compared with some related methods in experiments.
	TO cite this article:Fu Shujun,Zhang Caiming. Adaptive image denoising using anisotropic diffusion and nonlocal means filter[OL].[ 3 September 2011] http://en.paper.edu.cn/en_releasepaper/content/4441910


	10. DRESSING AVATARS AUTOMATICALLY BASED ON PERSONALITY
	Wang Xia ,Hou Jin ,Xiang Yu ,Zhang Dengsheng
	Computer Science and Technology 18 March 2010
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Avatar-based communication provides an immersive and natural way of HCI (Human-Computer Interaction). Just as a real human, each avatar, the digital equivalent of a user, should have a distinct personality too. But most current systems couldn’t describe the avatars’ personalities systematically and effectively. Moreover, little attention has been devoted to the task of dressing avatars automatically. In this paper, we propose a new practical approach to resolve the problem above. A model-based methodology is presented for dressing personalized avatars automatically. We implement a prototype system where users can generate personalized avatars by altering the appearance (such as clothing, skin color, accessories, etc.) of the avatar models according to their own profession, nation, taste, age, and so on.
	TO cite this article:Wang Xia ,Hou Jin ,Xiang Yu , et al. DRESSING AVATARS AUTOMATICALLY BASED ON PERSONALITY[OL].[18 March 2010] http://en.paper.edu.cn/en_releasepaper/content/40809

	Check out RSS, or use RSS reader to subscribe this item