检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shi, Yuguang School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

One of the key problems in 3D object detection is to reduce the accuracy gap between methods based on LiDAR sensors and those based on monocular cameras. A recently proposed framework for monocular 3D detection based on Pseudo-Stereo has received considerable attention in the community. However, so far these two problems are discovered in existing practices, including (1) monocular depth estimation and Pseudo-Stereo detector must be trained separately, (2) Difficult to be compatible with different stereo detectors and (3) the overall calculation is large, which affects the reasoning speed. In this work, we propose an end-to-end, efficient pseudo-stereo 3D detection framework by introducing a Single-View Diffusion Model (SVDM) that uses a few iterations to gradually deliver right informative pixels to the left image. SVDM allows the entire pseudo-stereo 3D detection pipeline to be trained end-to-end and can benefit from the training of stereo detectors. Afterwards, we further explore the application of SVDM in depth-free stereo 3D detection, and the final framework is compatible with most stereo detectors. Among multiple benchmarks on the KITTI dataset, we achieve new state-of-the-art performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DSFFNet: Dual-Side Feature Fusion Network for 3D Pose Transfer

arXiv

引用

arXiv 2023年

作者： Liu, Jue School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

To solve the problem of pose distortion in the forward propagation of pose features in existing methods, this paper proposes a Dual-Side Feature Fusion Network for pose transfer (DSFFNet). Firstly, a fixed-length pose code is extracted from the source mesh by a pose encoder and combined with the target vertices to form a mixed feature;Then, a Feature Fusion Adaptive Instance Normalization module (FFAdaIN) is designed, which can process both pose and identity features simultaneously, so that the pose features can be compensated in layer-by-layer forward propagation, thus solving the pose distortion problem;Finally, using the mesh decoder composed of this module, the pose are gradually transferred to the target mesh. Experimental results on SMPL, SMAL, FAUST and MultiGarment datasets show that DSFFNet successfully solves the pose distortion problem while maintaining a smaller network structure with stronger pose transfer capability and faster convergence speed, and can adapt to meshes with different numbers of vertices. Code is available at https://***/YikiDragon/DSFFNet Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intrinsic-feature-guided 3D Object Detection

arXiv

引用

arXiv 2025年

作者： Zhang, Wanjing Wang, Chenxing School of Automation Southeast University 2# Sipailou Xuanwu Nanjing210096 China Key laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

LiDAR-based 3D object detection is essential for autonomous driving systems. However, LiDAR point clouds may appear to have sparsity, uneven distribution, and incomplete structures, significantly limiting the detection performance. In road driving environments, target objects referring to vehicles, pedestrians and cyclists are well-suited for enhancing representation through the complete template guidance, considering their grid and topological structures. Therefore, this paper presents an intrinsic-feature-guided 3D object detection method based on a template-assisted feature enhancement module, which extracts intrinsic features from relatively generalized templates and provides rich structural information for foreground objects. Furthermore, a proposal-level contrastive learning mechanism is designed to enhance the feature differences between foreground and background objects. The proposed modules can act as plug-and-play components and improve the performance of multiple existing methods. Extensive experiments illustrate that the proposed method achieves the highly competitive detection results. Code will be available at https://***/zhangwanjingjj/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection

Phase-Shifting Coder: Predicting Accurate Orientation in Ori...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yi Yu Feipeng Da School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

With the vigorous development of computer vision, oriented object detection has gradually been featured. In this paper, a novel differentiable angle coder named phase-shifting coder (PSC) is proposed to accurately predict the orientation of objects, along with a dual-frequency version (PSCD). By mapping the rotational periodicity of different cycles into the phase of different frequencies, we provide a unified framework for various periodic fuzzy problems caused by rotational symmetry in oriented object detection. Upon such a framework, common problems in oriented object detection such as boundary discontinuity and square-like problems are elegantly solved in a unified form. Visual analysis and experiments on three datasets prove the effectiveness and the potentiality of our approach. When facing scenarios requiring high-quality bounding boxes, the proposed methods are expected to give a competitive performance. The codes are publicly available at https://***/open-mmlab/mmrotate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Augmented Kalman Filter-Based control for Electronic Throttle systems with Disturbances and Noises

Adaptive Augmented Kalman Filter-Based Control for Electroni...

引用

Chinese control Conference (CCC)

作者： Wen Li Jinya Su Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

In this study, we investigate the control problem of electronic throttle systems in the presence of practical challenges such as disturbances and measurement noises. To address these challenges, we propose an adaptive augmented Kalman filter (AAKF) based control approach that combines the strengths of extended state observer in disturbance estimation and adaptive Kalman fil-ter in adaptive noise filtering. The outputs of AAKF are integrated into the Backstepping control design, resulting in a composite control that concurrently achieves fast disturbance rejection and noise suppression. We conduct a comparative simulation study against conventional methods without adaptive filtering to validate the effectiveness of the proposed AAKF-based control strat-egy, which exhibits superior position control accuracy and disturbance attenuation performance. We envision that our proposed control strategy will contribute to improving vehicle power, fuel economy, and emission performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cycle-Based Signal Timing with Traffic Flow Prediction for Dynamic Environment

SSRN

引用

SSRN 2023年

作者： Li, Yisha Chen, Guoxi Zhang, Ya School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

This article studies adaptive traffic signal control problem of single intersection in dynamic environment. A novel cycle-based signal timing method with traffic flow prediction (CycleRL) is proposed to improve the traffic efficiency under dynamic traffic flow. Firstly, the empirical mode decomposition is applied to denoise the flow data. Then a data-model hybrid driven traffic flow prediction strategy is designed to predict the traffic flow, which combines a model-based Kalman filter and an LSTM network-based predictor and adopts another Kalman filter to fuse both prediction results to improve the prediction precision. Besides, a robust signal cycle timing strategy based on human-machine collaboration is developed to deal with dynamic traffic flow, which firstly designs a rule-based signal cycle scheme according to the predicted flow data as the preliminary scheme, and then finetunes the preliminary scheme based on Soft Actor-Critic (SAC) algorithm according to the real-time traffic dynamics. The experiments in both synthetic scenario and real-world scenario show that the proposed data-model hybrid driven traffic flow prediction algorithm has better prediction performance and the proposed CycleRL method outperforms rule-based methods, flow-based allocation methods and traditional reinforcement learning method. Moreover, it is also shown that the proposed CycleRL method has better transferability to bridge the discrepancy across domains. © 2023, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Groups of People with Hypergraph Relational Reasoning

Reconstructing Groups of People with Hypergraph Relational R...

引用

International Conference on Computer Vision (ICCV)

作者： Buzhen Huang Jingyi Ju Zhihao Li Yangang Wang Southeast University China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Huawei Noah’s Ark Lab

Due to the mutual occlusion, severe scale variation, and complex spatial distribution, the current multi-person mesh recovery methods cannot produce accurate absolute body poses and shapes in large-scale crowded scenes. To address the obstacles, we fully exploit crowd features for reconstructing groups of people from a monocular image. A novel hypergraph relational reasoning network is proposed to formulate the complex and high-order relation correlations among individuals and groups in the crowd. We first extract compact human features and location information from the original high-resolution image. By conducting the relational reasoning on the extracted individual features, the underlying crowd collectiveness and interaction relationship can provide additional group information for the reconstruction. Finally, the updated individual features and the localization information are used to regress human meshes in camera coordinates. To facilitate the network training, we further build pseudo ground-truth on two crowd datasets, which may also promote future research on pose estimation and human behavior understanding in crowded scenes. The experimental results show that our approach outperforms other baseline methods both in crowded and common scenarios. The code and datasets are publicly available at https://***/boycehbz/GroupRec.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accurate Detection and Tracking of Trucks and Truck Drivers

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accura...

引用

Chinese control Conference (CCC)

作者： Xueqin Zheng Jinya Su Jun Yang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during the whole working process. In the proposed method, the improved YOLOX performs object detection and its output is used as the input for multi -object tracking using DeepSORT. The improved YOLOX model is developed through replacing standard convolution with depthwise separable convolution, adding the convolutional block attention module to enhance feature extraction, and using Focal Loss in the loss function to address sample imbalances. Comparative experiments were carried out on a self-built dataset, showing a 4.32% increase in mAP and improved reasoning speed for improved YOLOX compared to the original YOLOX. Furthermore, the optimized method shows a 3.57% increase in Multi-Object Tracking Accuracy and a 1.73% increase in Multi-Object Tracking Precision compared to the benchmark YOLOX+DeepSORT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Speed Regulation of PMSM Under Disturbances and Noises Using Composite Model Predictive control

Robust Speed Regulation of PMSM Under Disturbances and Noise...

引用

Chinese control Conference (CCC)

作者： Linxuan Mao Jinya Su Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

This paper presents a single-loop Model Predictive control strategy that incorporates a reduced-order Generalized Proportional Integral Observe and a Kalman filter to enhance the speed regulation of Permanent Magnet Synchronous Motor systems in the presence of complex disturbances and measurement noises. The proposed controller design seamlessly integrates the predictive control, disturbance observer, and state filter components, and it was evaluated through simulation comparisons. The performance of the proposed method is evaluated using various metrics, including maximum velocity drop, recovery time, and variance of steady-state error, which demonstrate its superior response performance and anti-disturbance ability when compared to other existing methods without state filtering.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pinr: A Physics-Integrated Neural Representation for Dynamic Fluid Scenes

SSRN

引用

SSRN 2024年

作者： Zhao, Ziyu Zhou, Sifan Lu, Xiaobo Zeng, Weili Qian, Jian School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of ASIC and System Fudan University Shanghai China

Recent research based on neural representation has achieved impressive results in dynamic reconstruction. However, reconstructing high-fidelity dynamic fluid scenes from multi-view videos remains challenging due to the complex fluid phenomena such as translucency, scattering, occlusion, and visual ambiguity. In this paper, we present a novel neural representation that simultaneously exploits physics knowledge and differentiable volume rendering techniques to construct a physically plausible neural field. We first propose a simple yet effective state field to separate fluid and non-fluid contents apart, which essentially reduces the amount of computation and appearance ambiguity. To achieve robust optimization and fast convergence, we introduce intermediate velocity in neural representation based on Helmholtz Decomposition to decouple physical quantities (velocity, pressure and density) that are tightly coupled in physical equations. In contrast to previous physics-informed reconstruction methods, we explore a novel solution by introducing a fast and stable fluid solver to update the intermediate velocity to a physically conserved incompressible velocity. This solver is based on a parallelizable multi-scale architecture, which can effectively avoid degenerate solutions. By adopting the proposed physics-aware loss, we achieved better convergence and superior performance in dynamic fluid scenes. Extensive experiments show that the proposed method can achieve state-of-the-art results for reconstructing dynamic fluid scenes, and the performance and efficiency have been significantly improved in different scenarios. © 2024, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：