Autonomous driving heavily relies on LiDAR and camera sensors, which can significantly improve the performance of perception and navigation tasks when fused together. The success of this cross-modality fusion hinges o...
详细信息
In this paper,we propose an improved part-based tracking method based on compressive *** traditional compressive tracking can hardly deal with occlusion and scale variation,which is not robust enough in these *** our ...
详细信息
ISBN:
(纸本)9781509009107
In this paper,we propose an improved part-based tracking method based on compressive *** traditional compressive tracking can hardly deal with occlusion and scale variation,which is not robust enough in these *** our part-based method,the occluded image patches which are selected by K-means are not able to participate in determining the location of the target in order to increase tracking *** solve the problem of scale variation,an algorithm is proposed to estimate the size of target with the information of the whole *** addition,we also use the positions of every part to help us to get a precise size of the *** the combination of two methods,the scale of the target is *** compared with five state-of-the-arts have been done to prove the effectiveness and robustness of our method.
As an interdisciplinary of fuzzy theory and clustering, Fuzzy C-Means(FCM) is widely applied for identifying categories with unlabeled data. However, its application to data which is hard to visualize rises the diff...
详细信息
As an interdisciplinary of fuzzy theory and clustering, Fuzzy C-Means(FCM) is widely applied for identifying categories with unlabeled data. However, its application to data which is hard to visualize rises the difficulty for users to determine the input parameters, especially for the number of clusters. In this paper, a kind of fuzzy clustering algorithm with self-regulated parameters named Density-Based Fuzzy C-Means(DBFCM) is proposed by integrating the idea of Density-Based Spatial Clustering of Application with Noise(DBSCAN) into FCM. Its advantage is using the inherit density characteristic of input data to self-determine the parameters of fuzzy clustering. The experimental results demonstrate that the proposed DBFCM can not only self-determine the proper parameters, but also accelerate the convergence process compared to the original FCM.
The combined control of variable speed and variable displacement is a new type of volume control with high efficiency and fast ***,due to the inherent nonlinearity of multiplication,it brings certain difficulties to t...
The combined control of variable speed and variable displacement is a new type of volume control with high efficiency and fast ***,due to the inherent nonlinearity of multiplication,it brings certain difficulties to the *** electric double-variable pump[1] is a dual-input single-output system,and it is a nonlinear system[2].It is necessary to linearize the system or use a nonlinear control method to control and solve the control problem of the *** this paper,an intelligentcontrol rule is proposed for the nonlinear problem of double input and single *** backstepping design[3],the nonlinear system is transformed into multiple linear *** the original system is turned into two independent subsystems with single input and single output,which are controlled *** co-simulation platform based on AMESIM and Simulink[4] has been verified and compared with a single PID control algorithm to simulate the step response and sinusoidal tracking performance of the *** results show that the response speed of the system has been greatly improved.
Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability ma...
详细信息
The extended state observer, a crucial part of the active disturbance rejection control, was first proposed in 1995 by Jingqing Han. The discrete-time form of the extended state observer has been extensively used in m...
详细信息
ISBN:
(纸本)9781467374439
The extended state observer, a crucial part of the active disturbance rejection control, was first proposed in 1995 by Jingqing Han. The discrete-time form of the extended state observer has been extensively used in many practical applications in engineering such as quad-rotor robot control and non-circular machining control;the convergence property of the discrete-time n-dimensional extended state observer, however, remains unexplored and is investigated in this work. The main idea is to construct the error equations of the discrete-time extended state observer for an n-dimensional single-input-single-output nonlinear system with uncertainty, and to prove the convergence of the extended state observer through induction.
In this paper, we introduce a local smooth path planning algorithm for turning around in narrow environment. The algorithm uses a combination of the minimum turning radius arc and the Bezier curve to generate a near o...
详细信息
ISBN:
(纸本)9781728136677
In this paper, we introduce a local smooth path planning algorithm for turning around in narrow environment. The algorithm uses a combination of the minimum turning radius arc and the Bezier curve to generate a near optimal smoothing turn-around path in narrow roads or cluttered environments. The algorithm will generate a smooth trajectory that conforms to the kinematic constraints of unmanned ground vehicle (UGV), by adjusting the heading to the target angle through several minimum-radius turns, and smoothly connecting to the global reference path via Bezier curve. We analyze the surrounding congestion and narrowness to choose appropriate turn-around area by integrating obstacle distribution and road edges before path planning. The algorithm was tested at IN 2 BOT UGV in our campus and 2018 Cross Dangers & obstacles. The experimental results indicated that the algorithm works efficiently with our previous work and shows good performance in accuracy and computational time.
Abnormal or drastic changes in the natural environment may lead to unexpected events,such as tsunamis and earthquakes,which are becoming a major threat to national ***,no effective assessment approach can deduce a sit...
详细信息
Abnormal or drastic changes in the natural environment may lead to unexpected events,such as tsunamis and earthquakes,which are becoming a major threat to national ***,no effective assessment approach can deduce a situation and determine the optimal response strategy when a natural disaster *** this study,we propose a social evolution modeling approach and construct a deduction model for self-playing,self-learning,and self-upgrading on the basis of the idea of parallel data and reinforcement *** proposed approach can evaluate the impact of an event,deduce the situation,and provide optimal strategies for *** the breakage of a submarine cable caused by earthquake as an example,we find that the proposed modeling approach can obtain a higher reward compared with other existing methods.
Disturbance widely exists in control *** disturbance rejection control(ADRC) has been proved to be an efficient way to deal with disturbance and achieves great success in *** most important part of ADRC is extended st...
详细信息
ISBN:
(纸本)9781509009107
Disturbance widely exists in control *** disturbance rejection control(ADRC) has been proved to be an efficient way to deal with disturbance and achieves great success in *** most important part of ADRC is extended state observer(ESO),which estimates the states of system and total *** regards internal disturbance and external disturbance as a total disturbance,estimates it and eliminates it in the *** faster ESO estimates total disturbance,the more quickly controller eliminates *** paper focuses on the discrete linear extended state observer(DLESO),and presents discrete predictive linear extended state observer(DPLESO).Stability and performances are *** result shows that DPLESO has better performances for disturbance rejection than DLESO.
Dynamic facial expression recognition(DFER) in the wild has received widespread attention *** are complex factors such as face occlusion and pose variation in the *** expression recognition has a subtle competition be...
详细信息
Dynamic facial expression recognition(DFER) in the wild has received widespread attention *** are complex factors such as face occlusion and pose variation in the *** expression recognition has a subtle competition between capturing local features of a human face and obtaining a global feature *** paper proposes an end-to-end DFER network GAT-Net based on the grid attention module and Transformer,which improves the robustness and accuracy of DFER in the ***,GAT-Net is divided into two components:spatial feature extraction and temporal feature *** grid attention module of the spatial feature extraction component guides the network to pay attention to the local salient features of the face,which reduces the interference of field occlusion and non-frontal *** Transformer in the temporal feature processing component guides the network to learn the temporal relationship of high-level semantic features and the global representation of facial expression *** two components balance the subtle competition between local features and global feature representations of facial *** ablation experiment has proved the effectiveness of the grid attention module and *** demonstrate that our GAT-Net outperforms state-of-the-art methods on DFEW and AFEW benchmarks with accuracies of 67.53%,and 50.14% respectively.
暂无评论