检索结果-内蒙古大学图书馆

Fast Fog Detection for Camera Based Advanced Driver Assistance Systems

学校读者我要写书评

暂无评论

Fast Fog Detection for Camera Based Advanced Driver Assistan...

17th International IEEE Conference on Intelligent Transportation Systems & The Asia-Pacific Council on Systems Engineering Conference 2014

作者： Rita Spinneker Carsten Koch Su-Birm Park Jason Jeongsuk Yoon Hochschule Emden/Leer University of Applied Sciences Institute of InformaticsAutomation and Robotics (I2AR)EmdenGermany LG Electronics Future IT Lab Computer Vision Team SeoulRepublic of Korea

In an increasing number of cars,the driver is supported by Advanced Driver Assistance Systems(ADAS).In particular camera based ADAS are a key component for further improvements in safety and driving *** imaging sensors are performing well under good weather conditions,their efficiency suffers under adverse environmental influences such as heavy rain,fog or *** handle such optical threats and to estimate information quality of cameras in order to warn the assistance system of possible critical working conditions,a self-diagnosis mechanism is of great importance for reliable operation of an optical *** this paper an approach of camera based fog detection as part of a self-diagnosis mechanism for ADAS based on the blurring effect of fog is *** encouraging results of our experiments have shown that the presented approach of analysing the power spectrum slope(PSS) of a small image block in close proximity to the vanishing point enables a fast discrimination of street scenes with and without fog.

关键词： image Fast Fog Detection for Camera Based Advanced Driver Assistance Systems

A graph neural network to model disruption in human-aware robot navigation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bachiller, Pilar Rodriguez-Criado, Daniel Jorvekar, Ronit R. Bustos, Pablo Faria, Diego R. Manso, Luis J. Robotics and Artificial Vision Laboratory University of Extremadura Extremadura Spain College of Engineering and Physical Sciences Aston University BirminghamB4 7ET United Kingdom Department of Computer Engineering Pune Institute of Computer Technology India

Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to minimise the disruption caused to humans while moving. This implies predicting how people will move and complying with social conventions. Avoiding disrupting personal spaces, people's paths and interactions are examples of these social conventions. This paper leverages Graph Neural Networks to model robot disruption considering the movement of the humans and the robot so that the model built can be used by path planning algorithms. Along with the model, this paper presents an evolution of the dataset SocNav1 [25] which considers the movement of the robot and the humans, and an updated scenario-to-graph transformation which is tested using different Graph Neural Network blocks. The model trained achieves close-to-human performance in the dataset. In addition to its accuracy, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered in comparison with handcrafted models. The dataset and the model are available in a public repository. © 2021, CC BY-SA.

关键词： Graph neural networks

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Goswami, Dipam Liu, Yuyang Twardowski, Bartlomiej van de Weijer, Joost Department of Computer Science Universitat Autònoma de Barcelona Spain Computer Vision Center Barcelona Spain University of Chinese Academy of Sciences China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM. © 2023, CC BY.

关键词： Normal distribution

Lprr: Locality Preserving Robust Regression Based Sparse Feature Extraction

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhu, Yufei Wen, Jiajun Lai, Zhihui Zhou, Jie Kong, Heng The Computer Vision Institute The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China the Department of Breast and Thyroid Surgery BaoAn Central Hospital of Shenzhen Shenzhen518060 China

Jointly sparse projection learning attracts considerable attention due to its strong interpretability in feature extraction. To address the challenges related to weak discriminating representation in supervised feature extraction, we propose a more powerful regression framework. Based on the framework, we exhibit a new regression model called locality preserving robust regression (LPRR). In LPRR, we first combine the reconstruction error minimization and the projection variance maximization to explore the structured information of the data. Then, the label information is utilized and the low rank representation can be learned to explore the latent correlation structures among different classes. Furthermore, L2,1-norm is applied to measure the loss function and regularization terms, enhancing the robustness of the model and ensuring the joint sparsity of the projection matrix. An iterative algorithm is elaborately designed to achieve the optimal solutions of LPRR, in which the subproblem of LPRR can be regarded as a general quadratic problem on the Stiefel manifold. The convergence and the computational complexity of LPRR are analyzed rigorously. Finally, comprehensive experiments demonstrate the competitive performance of the proposed algorithm. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

An improved YOLO V3 for small vehicles detection in aerial images

学校读者我要写书评

暂无评论

An improved YOLO V3 for small vehicles detection in aerial i...

作者： Moran Ju Haibo Luo Zhongbo Wang Shenyang Institute of Automation &Institutes for Robotics and Intelligent Manufacturing & Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences University of Chinese Academy of Sciences The Key Laboratory of Image Understanding and Computer Vision

Small vehicle detection in aerial images is a challenge in computer vision because small vehicles occupy less pixels and the environment around the small vehicles is complex. To improve the detection performance for the vehicles in aerial images, we propose an improved YOLO V3. The main contributions of our work include:(1)We redesign the backbone of YOLO V3 to select suitable scales for small vehicle detection in aerial images;(2) To make the improved YOLO V3 much stronger, we redesign the loss function of original YOLO V3 by GIOU loss and Focal loss;(3) To verify the performance of improved YOLO V3, we do the comparative experiments on VEDAI dataset. The experimental results show that the proposed method has obtained better performance than original YOLO V3 for small vehicle detection in aerial image.

关键词： Convolutional neural network Small vehicle detection YOLO V3 Aerial image

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Qinliang Luo, Cheng Niu, Zenghao He, Xilin Xie, Weicheng Hou, Yuanbo Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China WAVES Research Group Ghent University Belgium University of Leicester United Kingdom

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://***/LinQinLiang/DeCoWA. © 2024, CC BY-NC-SA.

关键词： Semantics

Fast Texture Synthesis via Pseudo Optimizer

学校读者我要写书评

暂无评论

Fast Texture Synthesis via Pseudo Optimizer

Conference on computer vision and Pattern Recognition (CVPR)

作者： Wu Shi Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Texture synthesis using deep neural networks can generate high quality and diversified textures. However, it usually requires a heavy optimization process. The following works accelerate the process by using feed-forward networks, but at the cost of scalability. diversity or quality. We propose a new efficient method that aims to simulate the optimization process while retains most of the properties. Our method takes a noise image and the gradients from a descriptor network as inputs, and synthesize a refined image with respect to the target image. The proposed method can synthesize images with better quality and diversity than the other fast synthesis methods do. Moreover, our method trained on a large scale dataset can generalize to synthesize unseen textures.

关键词： Neural networks Training Transforms Scalability Optimization methods Convolution

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Qitao Zheng, Ce Liu, Mengyuan Chen, Chen Robotics Institute Carnegie Mellon University United States Center for Research in Computer Vision University of Central Florida United States Key Laboratory of Machine Perception Peking University Shenzhen Graduate School China

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [77], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning