Papers by Keyword: Key Point

Paper TitlePage

Authors: Sha Liu, Yun Qi Wang, Xiao Gang Ma, De Cheng Wang
Abstract: Refer to Reverse Engineering of extracting points cloud to generate a digital model, the paper proposes a rational method to design agricultural machinery's appearance. Depending on the product's internal structure contours, we can extract several key points and connect them by four ways: straight lines connecting, arcs connecting, free curves connecting and data fitting. Then we choose and modify the connected lines by a unified style to get the main profile of the machinery, which can better match the structural components. In the end a small self-propelled square baler's design process was presented to describe and testify the method.
Authors: Sha Liu, Yun Qi Wang, Lei Wei, De Cheng Wang
Abstract: Based on the internal structure of a small self-propelled mower, extract key points and make the main outlines of the machine by connecting the points in four ways: straight lines connect, arcs connect, free curves connect and data fitting. Then start from the main outlines and make the morphological evolution by the rules of "tilt", "fillet" and the characteristic of curves to obtain lots of basic shapes of the machines. Choose and modify the shapes by a unified style to get the final design of the mower. The period of the R&D of the small self-propelled mower is shorten and the final design is simple and effective in line with the appearance needs of such kind of products. Moreover the final shells of the mower are better match with the structural components. That verifies the feasibility of the design method and its better effect.
Authors: Qing Wei, Hao Zhang, Zhi Jing Liu
Abstract: This paper presents a new recognition method for human motion, which is represented by Haar wavelet transform and recognized by Coupled Hidden Markov Model. We tackle the challenge of detecting the feature points by Haar wavelet transform to improve the accuracy. We extract binary silhouette after creating the background model. Then the low-level features are detected by Haar wavelet and principal vectors in two subspaces are obtained. We utilize Coupled Hidden Markov Models to model and recognize them, and demonstrate their usability. Compared with others, our approach is simple and effective in feature detection, strength in robustness. Therefore, the video surveillance based on our method is practicable in (but not limited to) many scenarios where the background is known.
Authors: Hong Bo Niu, Hong Shan Zhao, Ji Fei Cao
Abstract: Long Horizontal Section Well has been an important way to explore deficient oil/gas field. Relative drilling technology has developed rapidly in recent years in China. This article puts focus on the methodology of well plan, trajectory control and matched tools and application situation of drilling fluid and drilling equipment for long horizontal section well. Based on the analysis of drilling and completion technical difficulties, suitability of some well design methods such as catenary curve used to decline friction and torque have been discussed, and even more practical means proven in many designs have been recommended. After introducing the drilling capability of the long horizontal-section well, the article indicated some special characteristic of the horizontal section wells and difference from ERD wells. Consequently, some advice is given on the definition and development of the drilling technology of long horizontal section wells.
Authors: Xin Jian Zheng
Abstract: A 3D coordinate measuring method was determined on the basis of the analysis about structure of the auto fan; plan of the key point data collection was stated; Pointed out the whole process of computer aided and reversed design which includes from choice of key point, curved fitting, curved surface to 3D design.
Authors: Yan Wei Wang, Si Qing Zhang, Bing Lin, Hong Liang, Yan Ming Pan
Abstract: Feature Point Extraction Method of X-ray Image Based on Scale Invariant is proposed in this paper for industrial X-ray image with low contrast and some artifacts. First of all, the scale transformation of original image is adopted by the Gaussian kernel to building the DOG multi-scale pyramid. Then, the location and scale of the key points is fixed by the three-dimensional quadratic function. Finally, the Simply SIFT descriptor illustrates the key points. Experimental results show that the algorithm has good stability in translation, rotation and affine transformation, especially with 10 percent normalized Gaussian noise, this algorithm can still be detected feature points accuracy.
Showing 1 to 6 of 6 Paper Titles