期刊：
Journal of Ambient Intelligence and Humanized Computing,2023年14(11):14859-14872 ISSN：1868-5137
通讯作者：
Jianxu Mao
作者机构：
[Liu C.; Long Y.; Huang R.] College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China;[Mao J.; Dai Y.] College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China;[Zhang H.] College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, 410012, China
通讯机构：
[Jianxu Mao] C;College of Electrical and Information Engineering, Hunan University, Changsha, China
摘要：
This article presents a new supervised multilayer subnetwork-based feature refinement and classification model for representation learning. The novelties of this algorithm are as follows: 1) different from most multilayer networks that go deeper with increased number of network layers, this work architects a model with wider subnetwork nodes; 2) the conventional classification methods adopt a separate search mechanism to derive a generalized feature space and to get the final cognition, but this work proposes a one-shot process to find the meaningful latent space and recognize the objects; and 3) the traditional feature representation and image classification approaches apply a unimodal feature coding, which suffers from lack of global knowledge. This work overcomes the pitfall through multimodal fusion that fuses various feature sources into one superstate encoding to achieve higher performance. A cross-domain experimental study on camera identification and image classification shows that the proposed method achieves superior performance compared to the existing models.
作者机构：
[易俊飞; 赵晨阳; 车爱博] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha;410114, China;[张辉; 王耀南] National Engineering Laboratory for Robot Visual Perception and Control Technology, Hunan University, Changsha;410082, China;[易俊飞; 赵晨阳; 车爱博] 410114, China
摘要：
This article addresses the problem of autonomous servoing control of an unmanned aerial manipulator with the capability of grasping target objects using computer vision. Specifically, a practical visual servo control using a spherical projection model is proposed. The aerial manipulator is an unmanned aerial vehicle equipped with a robotic arm that greatly increases the freedom and operational flexibility of the end-effector. However, it also increases the complexity of the kinematics, dynamics, and control design of the complete system. A novel passivity-like error equation of the image features is established by using the spherical camera geometry dynamics with an eye-in-hand configuration. To further improve the grasping performance, a task-priority control scheme is utilized with one main task and several subtasks, i.e., controlling the gripper position and orientation, vertically aligning the center of gravity, and avoiding the joint limitation. Simulation results are provided to illustrate and assess the performance of the proposed visual servo control. The practicability and effectiveness of autonomous aerial manipulation are well supported by the experimental results acquired through outdoor environments.
关键词：
Faster RCNN;improved Gaussian mixture model (GMM);Markov random field (MRF);rail inspection;surface defect;visual detection
摘要：
Rail inspection system (RIS) remains an emergent instrumentation for railway transportation, with its capacity of measuring surface defect on steel rail. However, detecting technique and interpretation of RIS constitute a challenging problem since traditional technologies are expensive and prone to errors. In this paper, a deep multimodel RIS (DM-RIS) is established for surface defect where fast and robust spatially constrained Gaussian mixture model is presented for segmentation proposal and Faster RCNN is utilized for objective location in a parallel structure. First, we incorporate spatial information between pixels into an improved Gaussian mixture model based on Markov random field (MRF) for accurate and rapid defect edge segmentation. Specifically, a direct parameter-learning in expectation & x2013;maximization (EM) algorithm is proposed. Meanwhile, to remove nondefect, numerous labeled samples with weak illumination, inequality reflection, external noise, rust, and greasy dirt are fed into Faster RCNN so that DM-RIS is robust environmentally to various light, angle, background, and acquisition equipment. Finally, the joint hit area refers to a real defect. The experimental results demonstrate that the proposed method performs well with 96.74 & x0025; precision, 94.13 & x0025; recall, 95.18 & x0025; overlap, and 0.485 s/frame speed on average, and is robust compared with the related well-established approaches.
作者机构：
[张辉; 易俊飞; 吴刘宸; 陈瑞博] College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha;410114, China;[王耀南] National Engineering Laboratory for Robot Visual Perception and Control Technology, Hunan University, Changsha;410082, China;[张辉] 410114, China <&wdkj&> National Engineering Laboratory for Robot Visual Perception and Control Technology, Hunan University, Changsha
摘要：
The quality detection of pharmaceutical liquid products is inevitable and crucial in drug manufacture because drugs contaminated with foreign particles are definitely not to be used. However, with the current detection methods, it is still a challenge to detect and identify the small moving particles using an imaging system. In this article, a deep multimodel cascade method combining single-frame image and multiframe images processing method to detect and identify foreign particles is proposed. The proposed method consists of three stages. First, a Faster R-CNN convolutional neural network is adopted to detect and localize the multiple suspected foreign particles of each single-frame image. Then, the k-means clustering algorithm is used to cluster the trail of that detected multiple suspected foreign particles in the eight sequential images to obtain the moving object trajectory. Finally, trajectory features are extracted and the random forest (RF) classifier is used to distinguish noises and foreign particles according to the motion feature of the moving object trajectory. Experimental results demonstrate that the proposed multitask stepwise method improves the accuracy of foreign particles detection and reduces the rate of omission in the case of strong noise, which proves the effectiveness of this method.
摘要：
Glass bottles must be thoroughly inspected before they are used for packaging. However, the vision inspection of bottle bottoms for defects remains a challenging task in quality control due to inaccurate localization, the difficulty in detecting defects in the texture region, and the intrinsically nonuniform brightness across the central panel. To overcome these problems, we propose a surface defect detection framework, which is composed of three main parts. First, a new localization method named entropy rate superpixel circle detection (ERSCD), which combines least-squares circle detection and entropy rate superpixel (ERS) with an improved randomized circle detection, is proposed to accurately obtain the region of interest (ROI) of the bottle bottom. Then, according to the structure-property, the ROI is divided into two measurement regions: central panel region and annular texture region. For the former, a defect detection method named frequency-tuned anisotropic diffusion super-pixel segmentation (FTADSP) that integrates frequency-tuned salient region detection (FT), anisotropic diffusion, and an improved superpixel segmentation is proposed to precisely detect the regions and boundaries of defects. For the latter, a defect detection strategy called wavelet transform multiscale filtering (WTMF) based on a wavelet transform and a multiscale filtering algorithm is proposed to reduce the influence of texture and to improve the robustness to localization error. The proposed framework is tested on four data sets obtained by our designed vision system. The experimental results demonstrate that our framework achieves the best performance compared with many traditional methods.
摘要：
<jats:sec><jats:title content-type="abstract-subheading">Purpose</jats:title><jats:p>This paper aims to solve the problem between detection efficiency and performance in grasp commodities rapidly. A fast detection and grasping method based on improved faster R-CNN is purposed and applied to the mobile manipulator to grab commodities on the shelf.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Design/methodology/approach</jats:title><jats:p>To reduce the time cost of algorithm, a new structure of neural network based on faster R CNN is designed. To select the anchor box reasonably according to the data set, the data set-adaptive algorithm for choosing anchor box is presented; multiple models of ten types of daily objects are trained for the validation of the improved faster R-CNN. The proposed algorithm is deployed to the self-developed mobile manipulator, and three experiments are designed to evaluate the proposed method.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Findings</jats:title><jats:p>The result indicates that the proposed method is successfully performed on the mobile manipulator; it not only accomplishes the detection effectively but also grasps the objects on the shelf successfully.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Originality/value</jats:title><jats:p>The proposed method can improve the efficiency of faster R-CNN, maintain excellent performance, meet the requirement of real-time detection, and the self-developed mobile manipulator can accomplish the task of grasping objects.</jats:p></jats:sec>
会议论文集名称：
2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
摘要：
With the development of artificial intelligence, robot swarm systems also frequently appear in complex tasks of different situation. One of the important research directions is the formation of multi-robots. This paper analyzes the limitations of existing algorithms for large-scale mobile robot swarm formation control problems and proposes a consensus control algorithm with two-layer nearest neighbor information. It carries out experimental simulation to verify its convergence performance. At the same time, combined with a distributed structure control strategy that can change the number of robot formation members, the formation control experiment is carried out on the experimental platform consisted of robot state information detection device and multiple mobile robots,to further verify its feasibility.
摘要：
Glass bottles are widely used as containers in the food and beverage industry, especially for beer and carbonated beverages. As the key part of a glass bottle, the bottle bottom and its quality are closely related to product safety. Therefore, the bottle bottom must be inspected before the bottle is used for packaging. In this paper, an apparatus based on machine vision is designed for real-time bottle bottom inspection, and a framework for the defect detection mainly using saliency detection and template matching is presented. Following a brief description of the apparatus, our emphasis is on the image analysis. First, we locate the bottom by combining Hough circle detection with the size prior, and we divide the region of interest into three measurement regions: central panel region, annular panel region, and annular texture region. Then, a saliency detection method is proposed for finding defective areas inside the central panel region. A multiscale filtering method is adopted to search for defects in the annular panel region. For the annular texture region, we combine template matching with multiscale filtering to detect defects. Finally, the defect detection results of the three measurement regions are fused to distinguish the quality of the tested bottle bottom. The proposed defect detection framework is evaluated on bottle bottom images acquired by our designed apparatus. The experimental results demonstrate that the proposed methods achieve the best performance in comparison with many conventional methods.
摘要：
传统的RRT(Rapid-exploration Random Tree)算法具有搜索速度快,适用于解决动力学非完整性约束问题,但是由于算法本身的随机性,生成的路径比较曲折,甚至出现绕远路现象.为此,本文提出一种改进的RRT路径规划算法,该算法结合目标偏向策略,使算法快速向目标节点收敛;对选取节点的度量函数,加入了角度的影响;同时引入贪心剪枝思想,对冗余节点进行剪枝,提高了路径规划算法的效率;最后通过仿真实验,验证了该算法的正确性和有效性.
作者机构：
[金侠挺; 王耀南; 刘理; 钟杭] College of Electrical and Information Engineering, Hunan University, Changsha;410082, China;[张辉] National Engineering Laboratory of Robot Vision Perception and Control Technology, Hunan University, Changsha;College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha;410114, China
通讯机构：
National Engineering Laboratory for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China
