Improved HardNet and Stricter Outlier Filtering to Guide Reliable Matching

As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of image matching using classical local detectors,e.g.,scale-invariant feature transform(SIFT),and the outlier filtering approaches,e.g.,Random sample consensus(RANSAC),show high computation speed and pool robustness under changing illumination and viewpoints conditions,while image matching approaches with deep learning strategy(such as HardNet,OANet)display reliable achievements in large-scale datasets with challenging scenes.However,the past learning-based approaches are limited to the distinction and quality of the dataset and the training strategy in the image-matching approaches.As an extension of the previous conference paper,this paper proposes an accurate and robust image matching approach using fewer training data in an end-to-end manner,which could be used to estimate the pose error This research first proposes a novel dataset cleaning and construction strategy to eliminate the noise and improve the training efficiency;Secondly,a novel loss named quadratic hinge triplet loss(QHT)is proposed to gather more effective and stable feature matching;Thirdly,in the outlier filtering process,the stricter OANet and bundle adjustment are applied for judging samples by adding the epipolar distance constraint and triangulation constraint to generate more outstanding matches;Finally,to recall the matching pairs,dynamic guided matching is used and then submit the inliers after the PyRANSAC process.Multiple evaluation metrics are used and reported in the 1st place in the Track1 of CVPR Image-Matching Challenge Workshop.The results show that the proposed method has advanced performance in large-scale and challenging Phototourism benchmark.

Feature Relationship and Process Planning

Concurrent engineering(CE)involves the consideration during the design phase of the various factors associated with the life cycle of the product.Using the principle of CE,a feature-based CAPP system is proposed.On the basis of feature modeling,the system is able to reason feature relationships,produce feature digraph of a part,and decide the machining sequence of features.

Novel Design for High Speed and Resolution Delta-sigma A/D Converter

The delta-sigma converter is one of the high speed and resolution analog-to-digital modulators. Its implementation needs the low oversampling technique and the multi-bit D/A converter. The noise induced by the multi-bit D/A converter becomes one of the key factors deteriorating the signal-to-noise rate of the delta-sigma A/D converter. A novel structure with signal unity transfunction, dynamic element matching(DEM) and noise-shaping is discussed. The method is investigated to design converter based on the proposed structure. The behavior simulation indicates that the structure and the design method are feasible.

Computerized methods of analyzing faults between wells

The analysis of strata between wells is fundamental in the study of oil and gas reservoirs. Automatic analysis of strata between wells, based on stratigraphic division of well logs, is realized using computer techniques. We use a technique of dynamic waveform matching to build cross-well stratigraphic correlation relationships and automatically draw a path diagram of the cross-well stratigraphic contrast through piecewise line fitting, log character extraction, match cost calculation, and etc.. After analyzing many structure path diagrams between wells, 30 path patterns for normal faults, reverse faults, unconformities, synsedimentary faults, listric faults, pinch-outs, and so on were summarized and the path diagram patterns and correlation conceptions are presented. The application analysis in Dagang Oil Field shows that this method is effective.

View synthesis based on the serial images from camera lengthways motion

For the pre-acquired serial images from camera lengthways motion, a view synthesis algorithm based on epipolar geometry constraint is proposed in this paper. It uses the whole matching and maintaining order characters of the epipolar line, Fourier transform and dynamic programming matching theories, thus truly synthesizing the destination image of current viewpoint. Through the combination of Fourier transform, epipolar geometry constraint and dynamic programming matching, the circumference distortion problem resulting from conventional view synthesis approaches is effectively avoided. The detailed implementation steps of this algorithm are given, and some running instances are presented to illustrate the results.

Vehicle Ego-Localization Based on Streetscape Image Database Under Blind Area of Global Positioning System

Vehicle positioning is critical for inter-vehicle communication, navigation, vehicle monitoring and tracking. They are regarded as the core technology ensuring safety in everyday-driving. This paper proposes an enhanced vehicle ego-localization method based on streetscape image database. It is most useful in the global positioning system(GPS) blind area. Firstly, a database is built by collecting streetscape images, extracting dominant color feature and detecting speeded up robust feature(SURF) points. Secondly, an image that the vehicle shoots at one point is analyzed to find a matching image in the database by dynamic programming(DP)matching. According to the image similarity, several images with higher probabilities are selected to realize coarse positioning. Finally, different weights are set to the coordinates of the shooting location with the maximum similarity and its 8 neighborhoods according to the number of matching points, and then interpolating calculation is applied to complete accurate positioning. Experimental results show that the accuracy of this study is less than 1.5 m and its running time is about 3.6 s. These are basically in line with the practical need. The described system has an advantage of low cost, high reliability and strong resistance to signal interference, so it has a better practical value as compared with visual odometry(VO) and radio frequency identification(RFID) based approach for vehicle positioning in the case of GPS not working.

Three-dimensional sound source localization using distributed microphone arrays

To improve the performance of sound source localization based on distributed microphone arrays in noisy and reverberant environments,a sound source localization method was proposed.This method exploited the inherent spatial sparsity to convert the localization problem into a sparse recovery problem based on the compressive sensing（CS） theory.In this method two-step discrete cosine transform（DCT）-based feature extraction was utilized to cover both short-time and long-time properties of the signal and reduce the dimensions of the sparse model.Moreover,an online dictionary learning（DL） method was used to dynamically adjust the dictionary for matching the changes of audio signals,and then the sparse solution could better represent location estimations.In addition,we proposed an improved approximate l_0norm minimization algorithm to enhance reconstruction performance for sparse signals in low signal-noise ratio（SNR）.The effectiveness of the proposed scheme is demonstrated by simulation results where the locations of multiple sources can be obtained in the noisy and reverberant conditions.

A 2.5 GS/s 14-bit D/A converter with 8 to 1 MUX

A 2.5 GS/s 14-bit D/A converter（DAC） with 8 to 1 MUX is presented. This 14-bit DAC uses a ＂5＋9＂segment PMOS current-steering architecture. A bias circuit which ensures the PMOS current source obtains a larger output impedance under every PVT（process, source voltage and temperature） corner is also presented. The8 to 1 MUX has a 3 stage structure, and a proper timing sequence is designed to ensure reliable data synthesis. A DEM function which is merged with a ＂5-31＂decoder is used to improve the DAC＇s dynamic performance. This DAC is embedded in a 2.5 GHz direct digital frequency synthesizer（DDS） chip, and is implemented in a 0.18 m CMOS technology, occupies 4.86 2. 28 mm-2 including bond pads（DAC only）, and the measured performance is SFDR 〉 40 d B（with and without DEM） for output signal frequency up to 1 GHz. Compared with other present published DACs with a non-analog-resample structure（means return-to-zero or quad-switch structure is unutilized）,this paper DAC＇s clock frequency（2.5 GHz） and higher output frequency SFDR（〉 40 d B, up to 1 GHz） has some competition.