Feature Points In Real Time Research Articles

Light-weight segmentation network based on SOLOv2 for weld seam feature extraction

The laser vision sensor-based welding robot collects weld images of the workpiece surface and utilizes image processing algorithms to locate feature points in real time during welding. Among the existing methods of weld seam feature extraction, the traditional image processing methods cannot overcome the interference of strong noise, while deep learning-based methods have high computational overhead. Therefore, a light-weight segmentation network based on SOLOv2 is proposed in this paper. It is verified that the proposed network can accurately segment laser stripes under strong noise and achieve a speed of about 29 FPS on the CPU. The proposed network is integrated into the ECO tracking algorithm for welding experiments and the mean absolute error of welding is stable at about 0.2 mm, outperforming the original ECO method. This demonstrates that the proposed network can improve the robustness and accuracy of the weld seam tracking system without significantly increasing the computational resource requirements.

A SLAM-Based Mobile Augmented Reality Tracking Registration Algorithm

This paper proposes a simultaneous localization and mapping (SLAM)-based markerless mobile-end tracking registration algorithm to address the problem of virtual image drift caused by fast camera motion in mobile-augmented reality (AR). The proposed algorithm combines the AGAST-FREAK-SLAM algorithm with inertial measurement unit (IMU) data to construct a scene map and localize the camera’s pose. The extracted feature points are matched with feature points in a map library for real-time camera localization and precise registration of virtual objects. Experimental results show that the proposed method can track feature points in real time, accurately construct scene maps, and locate cameras; moreover, it improves upon the tracking and registration robustness of earlier algorithms.

Research on Virtual Makeup System Based on SDM

This paper presents a visual-based virtual makeup system, which uses a camera to turn a user's computer into a virtual mirror. With this system, users do not need to experience in physical store, through the computer user can pick their own designated color lipstick, and to see their lip’s color effect of lipstick in real time. The system first detects the user's face and the positions of user's lips. Based on feature point detection and alignment, the SDM[1] algorithm is used to detect the lip’s feature points in real time. It is highly accurate, fast and it can meet the real-time requirements. We set the lips as the region of interest, then smooth the edge of lips, through the gamma correction to solve the lips of the light compensation because light compensation have a big influence to my lip makeup effect, and finally to achieve lip color. The user can freely choose the lipstick color in the video to watch the effect of the using lipstick. The biggest advantage of the system compared to other existing lip systems is it’s real-time and accuracy.

Researches on binocular vision pose measurement with selected feature points

Generally, the binocular vision system for pose measurement can identify much more than 3 feature points each time. However, the pose of an object can be measured with 3 feature points. Different combinations of feature points may make different effect on the measurement accuracy of the object pose. This article presents a method to optimize the selection of feature points in real time and consequently ensure optimized accuracy of pose measurement based on binocular vision. At first, the object poses measurement model based on binocular vision is established. Then, pose measurement error model is deduced, and the objective function is presented for optimizing the selection of feature points based on error transferring matrix. At last, simulations are conducted and the results verified the correctness of pose measurement error model and the effectiveness of the selected feature points.

Novel Method of Monocular Real-Time Feature Point Tracking for Tethered Space Robots

This paper proposes a visual perception system for a tethered space robot’s (TSR) automatic rendezvous from 100 to 0.15 m. The core problem, tracking the entire contour of noncooperative moving targets in real time, is emphasized in this work. Given numerous challenges in a dynamic scene, a novel feature tracking algorithm is developed, i.e., the monocular real-time robust feature tracking algorithm (MRRFT). To generate a robust target model, improved speeded-up robust features (SURF) are used to extract features from a marked target box. The tracker then uses the pyramid Kanade-Lucas-Tomasi (P-KLT) matching algorithm and eliminates mismatched points by a statistical method. The greedy snake algorithm is applied to obtain the exact location of the target box and to update it automatically. A discrete feature filter and an adaptive feature updating strategy are also designed to enhance robustness. A three-dimensional (3D) simulation and a semiphysical system are developed to evaluate the method. Numerous experiments demonstrate that the tracker can stably track satellite models with simple structures with improved accuracy and time savings than good features to track (GFTT)+P-KLT or scale invariant feature transform (SIFT)+P-KLT.