检索结果-内蒙古大学图书馆

FPGA-Accelerated YOLOX With Enhanced Attention Mechanisms for Real-Time Wildfire Detection on AAVs

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Elhence, Anubhav Panda, Anubhav Chamola, Vinay Sikdar, Biplab BITS Pilani Dept Elect & Elect Engn Pilani 333031 India BITS Pilani APPCAIR Pilani 333031 India Natl Univ Singapore NUS Dept Elect & Commun Engn Singapore 119077 Singapore

Real-time wildfire detection is crucial for enabling prompt intervention and minimizing environmental and economic damages;however, deploying high-accuracy detection models on resource-constrained platforms such as autonomous aerial vehicles (AAVs) presents significant challenges due to limitations in computational capacity and power availability. In this article, we propose layerwise channel attention module (LCAM)-YOLOX, an enhanced object detection framework that integrates an LCAM into the YOLOX architecture to improve detection accuracy while maintaining computational efficiency. The model is optimized for deployment on FPGA platforms through 8-bit integer quantization, facilitating efficient inference on devices with limited resources. We implement and evaluate the LCAM-YOLOX model on the Xilinx Kria KV260 FPGA platform, demonstrating that it achieves a quantized mean average precision (mAP) of 78.11%, outperforming other state-of-the-art models such as YOLOv3, YOLOv5, and YOLOX-m. Moreover, the LCAM-YOLOX model processes at 195 frames per second (FPS) using a single DPU core on the KV260, exceeding real-time processing requirements while consuming only 10.45 W of power, which translates to the highest performance per watt ratio among the tested platforms. These results highlight the suitability of the KV260 FPGA as an optimal choice for deploying high-performance, energy-efficient wildfire detection models on AAVs, enabling real-time monitoring in resource-constrained environments.

关键词： Wildfires Computational modeling Feature extraction Real-time systems Field programmable gate arrays Autonomous aerial vehicles Accuracy Biological system modeling Quantization (signal) computer architecture Aerial robotics computer vision for other robotic applications energy and environment-aware automation field robots hardware-software co-design intelligent transportation systems quantized neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Visual SLAM for Underwater Vehicle Manipulator Systems

引用

IEEE roboticS AND AUTOMATION LETTERS 2022年第3期7卷 6798-6805页

作者： Billings, Gideon Camilli, Richard Johnson-Roberson, Matthew Univ Michigan Dept Naval Architecture & Marine Engn Ann Arbor MI 48109 USA Woods Hole Oceanog Inst Deep Submergence Lab Woods Hole Appl Ocean Phys & Engn Woods Hole MA 02543 USA Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA

This letter presents a novel visual feature based scene mapping method for underwater vehicle manipulator systems (UVMSs), with specific emphasis on robust mapping in natural seafloor environments. Our method uses GPU accelerated Sill' features in a graph optimization framework to build a feature map. The map scale is constrained by features from a vehicle mounted stereo camera, and we exploit the dynamic positioning capability of the manipulator system by fusing features from a wrist mounted fisheye camera into the map to extend it beyond the limited viewpoint of the vehicle mounted cameras. Our hybrid SLAM method is evaluated on challenging image sequences collected with a UVMS in natural deep seafloor environments of the Costa Rican continental shelf margin, and we also evaluate the stereo only mode on a shallow reef survey dataset. Results on these datasets demonstrate the high accuracy of our system and suitability for operating in diverse and natural seafloor environments. We also contribute these datasets(3) for public use.

关键词： SLAM sensor fusion computer vision for automation computer vision for other robotic applications data sets for robotic vision

来源：评论

学校读者我要写书评

暂无评论

Seeing Through the Occluders: Robust Monocular 6-DOF Object Pose Tracking via Model-Guided Video Object Segmentation

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 5159-5166页

作者： Zhong, Leisheng Zhang, Yu Zhao, Hao Chang, An Xiang, Wenhao Zhang, Shunli Zhang, Li Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China CSSC Syst Engn Res Inst Beijing 100094 Peoples R China Beijing Jiaotong Univ Sch Software Engn Beijing 100044 Peoples R China

To deal with occlusion is one of the most challenging problems for monocular 6-DOF object pose tracking. In this letter, we propose a novel 6-DOF object pose tracking method which is robust to heavy occlusions. When the tracked object is occluded by another object, instead of trying to detect the occluder, we seek to see through it, as if the occluder doesnt exist. To this end, we propose to combine a learning-based video object segmentation module with an optimization-based pose estimation module in a closed loop. Firstly, a model-guided video object segmentation network is utilized to predict the accurate and full mask of the object (including the occluded part). Secondly, a non-linear 6-DOF pose optimization method is performed with the guidance of the predicted full mask. After solving the current object pose, we render the 3D object model to obtain a refined, model-constrained mask of the current frame, which is then fed back to the segmentation network for processing the next frame, closing the whole loop. Experiments show that the proposed method outperforms the state-of-arts by a large margin for dealing with heavy occlusions, and could handle extreme cases which previous methods would fail.

关键词： computer vision for other robotic applications visual tracking virtual reality and interfaces

来源：评论

学校读者我要写书评

暂无评论

Discontinuous and Smooth Depth Completion With Binary Anisotropic Diffusion Tensor

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 5128-5135页

作者： Yao, Yasuhiro Roxas, Menandro Ishikawa, Ryoichi Ando, Shingo Shimamura, Jun Oishi, Takeshi Univ Tokyo Inst Ind Sci Tokyo 1538505 Japan NTT Corp Media Intelligence Labs Tokyo 1008116 Japan

We propose an unsupervised real-time dense depth completion from a sparse depth map guided by a single image. Our method generates a smooth depth map while preserving discontinuity between different objects. Our key idea is a Binary Anisotropic Diffusion Tensor (B-ADT) which can completely eliminate smoothness constraint at intended positions and directions by applying it to variational regularization. We also propose an Image-guided Nearest Neighbor Search (IGNNS) to derive a piecewise constant depth map which is used for B-ADT derivation and in the data term of the variational energy. Our experiments show that our method can outperform previous unsupervised and semi-supervised depth completion methods in terms of accuracy. Moreover, since our resulting depth map preserves the discontinuity between objects, the result can be converted to a visually plausible point cloud. This is remarkable since previous methods generate unnatural surface-like artifacts between discontinuous objects.

关键词： Sensor fusion range sensing computer vision for other robotic applications depth completion total generalized variation

来源：评论

学校读者我要写书评

暂无评论

"Good Robot!": Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 6724-6731页

作者： Hundt, Andrew Killeen, Benjamin Greene, Nicholas Wu, Hongtao Kwon, Heeyeon Paxton, Chris Hager, Gregory D. Johns Hopkins Univ Baltimore MD 21218 USA NVIDIA Seattle WA 98105 USA

Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progressmay be easily reversed. We develop the SPOT framework, which explores within action safety zones, learns about unsafe regions without exploring them, and prioritizes experiences that reverse earlier progress to learn with remarkable efficiency. The SPOT framework successfully completes simulated trials of a variety of tasks, improving a baseline trial success rate from 13% to 100% when stacking 4 cubes, from 13% to 99% when creating rows of 4 cubes, and from 84% to 95% when clearing toys arranged in adversarial patterns. Efficiency with respect to actions per trial typically improves by 30% or more, while training takes just 1-20 k actions, depending on the task. Furthermore, we demonstrate direct sim to real transfer. We are able to create real stacks in 100% of trials with 61% efficiency and real rows in 100% of trials with59% efficiency by directly loading the simulation-trained model on the real robot with no additional real-world fine-tuning. To our knowledge, this is the first instance of reinforcement learning with successful sim to real transfer applied to long term multi-step tasks such as block-stacking and row-making with consideration of progress reversal. Code is available at https://***/ jhulcsr/good_robot.

关键词： computer vision for other robotic applications deep learning in grasping and manipulation reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Extrinsic Calibration of an Eye-In-Hand 2D LiDAR Sensor in Unstructured Environments Using ICP

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第2期5卷 929-936页

作者： Peters, Arne Schmidt, Adam Knoll, Alois C. Tech Univ Munich Chair Robot Artificial Intelligence & Real Time S D-85748 Garching Germany Tech Univ Munich D-85748 Garching Germany Netherlands Org Appl Sci Res TNO NL-5656 AE Eindhoven Netherlands

We propose a calibration method for the six degrees of freedom (DOF) extrinsic pose of a 2D laser rangefinder mounted to a robot arm. Our goal is to design a system that allows on-site re-calibration without requiring any kind of special environment or calibration objects. By moving the sensor we generate 3D scans of the surrounding area on which we run a iterative closest point (ICP) variant to estimate the missing part of the kinematic chain. With this setup we can simply scale the density and format of our 3D scan by adjusting the robot speed and trajectory, allowing us to exploit the power of a high resolution 3D scanner for a variety of tasks such as mapping, object recognition and grasp planning. Our evaluation, performed on synthetic datasets as well as from real-data shows that the presented approach provides good results both in terms of convergence on crude initial parameters as well as in the precision of the final estimate.

关键词： Calibration and identification computer vision for other robotic applications range sensing sensor fusion 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

3D-Aware Scene Change Captioning From Multiview Images

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第3期5卷 4743-4750页

作者： Qiu, Yue Satoh, Yutaka Suzuki, Ryota Iwata, Kenji Kataoka, Hirokatsu Natl Inst Adv Ind Sci & Technol Tsukuba Ibaraki 3058560 Japan Univ Tsukuba Grad Sch Syst & Informat Engn Tsukuba Ibaraki 3058577 Japan

In this letter, we propose a framework that recognizes and describes changes that occur in a scene observed from multiple viewpoints in natural language text. The ability to recognize and describe changes that occurred in a 3D scene plays an essential role in a variety of human-robot interaction applications. However, most current 3D vision studies have focused on understanding the static 3D scene. Existing scene change captioning approaches recognize and generate change captions from single-view images. Those methods have limited ability to deal with camera movement, object occlusion, which are common in real-world settings. To resolve these problems, we propose a framework that observes every scene from multiple viewpoints and describes the scene change based on an understanding of the underlying 3D structure of scenes. We build three synthetic datasets consisting of primitive 3D object and scanned real object models for evaluation. The results indicate that our method outperforms the previous state-of-the-art 2D-based method by a large margin in terms of sentence generation and change understanding correctness. In addition, our method is more robust to camera movements compared to the previous method and also performs better for scenes with occlusions. Moreover, our method also shows encouraging results in a realistic scene-setting, which indicates the possibility of adapting our framework to a more complicated and extensive scene-settings.

关键词： Multi-modal perception deep learning for visual perception computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

Gaussian Process Online Learning With a Sparse Data Stream

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 5977-5984页

作者： Park, Jehyun Choi, Jongeun Yonsei Univ Sch Mech Engn Seoul 03722 South Korea

Gaussian processes (GPs) have been exploited for various applications even including online learning. To learn time-varying hyperparameters from an information-limited sparse data stream, we consider the infinite-horizon Gaussian process (IHGP) with a low computational complexity. For example, the IHGP framework could provide efficient GP online learning with a sparse data stream in mobile devices. However, we show that the originally proposed IHGP has difficulty in learning time-varying hyperparameters online from the sparse data stream due to the numerically approximated gradient of the marginal likelihood function. In this paper, we show how to extend the IHGP in order to learn time-varying hyperparameters using a sparse and non-stationary data stream. In particular, our solution approach offers the exact gradient as the solution of a Lyapunov equation. Therefore, our approach achieves better performance with a sparse data stream while still keeping the computational complexity low. Finally, we present the comparison results to demonstrate that our approach outperforms the originally proposed IHGP on practical applications with sparse data streams. To demonstrate the effectiveness of our approach, we consider a multi-rate sensor fusion or an interpolation problem where slow vision systems need to be combined with other fast sensory units for feedback control in the field of autonomous driving. In particular, we apply our approach to vehicle lateral position error estimation together with a deep learning model for autonomous driving using non-stationary lateral position error signals in a model-free and data-driven fashion.

关键词： computer vision for other robotic applications optimization and optimal control probability and statistical methods

来源：评论

学校读者我要写书评

暂无评论

SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第3期5卷 4241-4248页

作者： Billings, Gideon Johnson-Roberson, Matthew Univ Michigan Dept Naval Architecture & Marine Engn Ann Arbor MI 48109 USA

There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the application space for monocular-based methods is expansive, there has been little work on applying these methods with fisheye imaging systems. Also, little exists in the way of annotated fisheye image datasets on which these methods can be developed and tested. The research landscape is even more sparse for object detection methods applied in the underwater domain, fisheye image based or otherwise. In this work, we present a novel framework for adapting a ROI-based 6D object pose estimation method to work on full fisheye images. The method incorporates the gnomic projection of regions of interest from an intermediate spherical image representation to correct for the fisheye distortions. Further, we contribute a fisheye image dataset, called UWHandles, collected in natural underwater environments, with 6D object pose and 2D bounding box annotations.

关键词： computer vision for automation computer vision for other robotic applications deep learning in robotics and automation recognition visual learning

来源：评论

学校读者我要写书评

暂无评论

ECG: Edge-aware Point Cloud Completion with Graph Convolution

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第3期5卷 4392-4398页

作者： Pan, Liang Natl Univ Singapore Adv Robot Ctr Singapore 119077 Singapore

Scanned 3D point clouds for real-world scenes often suffer from noise and incompletion. Observing that prior point cloud shape completion networks overlook local geometric features, we propose our ECG - an Edge-aware point cloud Completion network with Graph convolution, which facilitates fine-grained 3D point cloud shape generation with multi-scale edge features. Our ECG consists of two consecutive stages: 1) skeleton generation and 2) details refinement. Each stage is a generation sub-network conditioned on the input incomplete point cloud. The first stage generates coarse skeletons to facilitate capturing useful edge features against noisy measurements. Subsequently, we design a deep hierarchical encoder with graph convolution to propagate multi-scale edge features for local geometric details refinement. To preserve local geometrical details while upsampling, we propose the Edge-aware Feature Expansion (EFE) module to smoothly expand/upsample point features by emphasizing their local edges. Extensive experiments show that our ECG significantly outperforms previous state-of-the-art (SOTA) methods for point cloud completion.

关键词： Deep learning for visual perception computer vision for other robotic applications

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：