检索结果-内蒙古大学图书馆

International Conference on Unmanned Systems and Artificial Intelligence

作者： Jianyu Yan Lu Xu Kuizhi Mei Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9781728158594

ISBN: (纸本)9781728158600

In auto-driving tasks, visual prediction is very meaningful and difficult, because the motion of the predicted target has many possible outputs. It is very effective to predict the motion of the target by optical flow, but the output of the previous optical flow models is fixed. In this paper, we proposed an optical flow prediction model via Conditional Variational Auto-Encoder. In experiment, the model can effectively predict a variety of possible optical motions in the real world. A number of experimental results show that our models outperform all prior state-of-the-art on the test of a recent optical flow prediction competition.

关键词： Conditional Variational Auto-Encoder optical flow prediction Auto-Driving (key words)

来源：评论

学校读者我要写书评

暂无评论

Line Segment Matching of Space Target Image Sequence based on optical flow prediction 3

Line Segment Matching of Space Target Image Sequence based o...

引用

3rd IEEE International Conference on Progress in Informatcs and Computing (IEEE PIC)

作者： Huang, Liang Chang, Qing Chen, Shangfeng Dai, Huadong Natl Univ Def Technol Sci & Technol ATR Lab Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781467390880

On the purpose to access the motion and structure information of space targets, a line segment matching method of space target sequence based on optical flow prediction was proposed. Firstly, the Edge Draw Lines (EDLines) algorithm was adopted to extract line segments, and then the optical flows of pixels on the line segments and Line Band Descriptor (LBD) of the line segments were calculated. optical flow assessment was applied to predict the positions of line segments in the next frame. The line segment matching of image sequence was achieved by choosing the distance between the descriptors as the similarity measure. Compared with existing algorithms, the simulation results show that the method can efficiently reduce the number of correspondent candidate matches of every line segment, decrease the computational complexity in the matching process, and accurately accomplish the task of line segment matching of space target image sequence.

关键词： optical flow prediction space target image sequence line segment matching

来源：评论

学校读者我要写书评

暂无评论

A Video prediction Method Based on optical flow Estimation and Pixel Generation

引用

IEEE ACCESS 2021年 9卷 100395-100406页

作者： Lu, Wei Cui, Junyun Chang, Yanshuo Zhang, Longmei Xian Univ Finance & Econ Sch Informat Xian 710100 Peoples R China Xian Univ Sci & Technol Sch Commun & Informat Engn Xian 710054 Peoples R China

Video prediction has developed rapidly after the booming of deep learning. As an important part of unsupervised representation learning, it plays an important role in anomalous behavior detection, autonomous driving, video games, and other fields. However, the prediction method based on optical flow estimation is susceptible to brightness change and camera shake, and it is difficult to predict occluded objects. While the prediction method based on pixel generation is difficult to fit ambiguous and complex scenes, which leads to a blurry prediction. In this work, we proposed an end-to-end video prediction framework that combines the optical flow estimation module with the pixel generation module by a learnable mask weight to predict high-fidelity videos. To further improve the prediction effect, we introduce adversarial training to the framework. We introduced a frame discriminator and a sequence discriminator to ensure the consistency of the spatio-temporal distribution of predicted video frames and real video frames. The results of experiments on challenging datasets demonstrate the practicability and effectiveness of our proposed video prediction framework. On the one hand, our proposed framework has achieved an equal quality compared with the current latest model, which requires fewer parameters and has a faster prediction speed. On the other hand, the results of ablation experiments demonstrate the effect of fusing different modules and the effectiveness of adversarial training.

关键词： optical flow Predictive models Estimation prediction methods Task analysis Training Cameras Adversarial training convolutional neural network optical flow prediction pixel generation video prediction

来源：评论

学校读者我要写书评

暂无评论

Line Segment Matching of Space Target Image Sequence based on optical flow prediction

Line Segment Matching of Space Target Image Sequence based o...

引用

2015 IEEE International Conference on Progress in Informatics and Computing(PIC 2015)

作者： Liang Huang Qing Chang Shangfeng Chen Huadong Dai Science and Technology on ATR laboratory National University of Defense Technology

On the purpose to access the motion and structure information of space targets, a line segment matching method of space target sequence based on optical flow prediction was proposed. Firstly, the Edge Draw Lines(EDLines) algorithm was adopted to extract line segments, and then the optical flows of pixels on the line segments and Line Band Descriptor(LBD) of the line segments were calculated. optical flow assessment was applied to predict the positions of line segments in the next *** line segment matching of image sequence was achieved by choosing the distance between the descriptors as the similarity measure. Compared with existing algorithms, the simulation results show that the method can efficiently reduce the number of correspondent candidate matches of every line segment, decrease the computational complexity in the matching process, and accurately accomplish the task of line segment matching of space target image sequence.

关键词： optical flow prediction space target image sequence line segment matching

来源：评论

学校读者我要写书评

暂无评论

Learnable spatiotemporal feature pyramid for prediction of future optical flow in videos

引用

MACHINE VISION AND APPLICATIONS 2020年第1期32卷 p1-10页

作者： Wadhwa, Laisha Mukherjee, Snehasis IIIT SriCity Chittoor India Shiv Nadar Univ Greater Noida India

The success of deep learning-based techniques in solving various computer vision problems motivated the researchers to apply deep learning to predict the optical flow of a video in the next frame. However, the problem of predicting the motion of an object in the next few frames remains an unsolved and less explored problem. Given a sequence of frames, predicting the motion in the next few frames of the video becomes difficult in cases where the displacement of optical flow vector across frames is large. Traditional CNNs often fail to learn the dynamics of the objects across frames in case of large displacements of objects in consecutive frames. In this paper, we present an efficient CNN based on the concept of feature pyramid for extracting the spatial features from a few consecutive frames. The spatial features extracted from consecutive frames by a modified PWC-Net architecture are fed into a bidirectional LSTM for obtaining the temporal features. The proposed spatiotemporal feature pyramid is able to capture the abrupt motion of the moving objects in video, especially when displacement of the object is large across the consecutive frames. Further, the proposed spatiotemporal pyramidal feature can effectively predict the optical flow in next few frames, instead of predicting only the next frame. The proposed method of predicting optical flow outperforms the state of the art when applied on challenging datasets such as "MPI Sintel Final Pass," "Monkaa" and "Flying Chairs" where abrupt and large displacement of the moving objects in consecutive frames is the main challenge.

关键词： Motion prediction optical flow prediction Feature pyramid LSTM

来源：评论

学校读者我要写书评

暂无评论

Subspace-PnP: A Geometric Constraint Loss for Mutual Assistance of Depth and optical flow Estimation

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2022年第12期130卷 3054-3069页

作者： Chi, Cheng Hao, Tianyu Wang, Qingjie Guo, Peng Yang, Xin Huazhong Univ Sci & Technol Wuhan Peoples R China

Unsupervised optical flow and stereo depth estimation are two fundamental tasks in computer vision. Current studies (Tosi et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4654-4665, 2020;Ranjan et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12240-12249, 2019;Wang et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8071-8081, 2019;Yin and Shi, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1983-1992, 2018) demonstrate that jointly learning networks for optical flow and stereo depth estimation via the geometric constraints can mutually benefit the two tasks and in turn yield large accuracy improvements. However, most of these methods generate geometric constraints based on estimated camera pose, which are not applicable to scenarios with moving objects that have different motions from the camera. In addition, errors of estimated camera pose would yield inaccurate constraints for the two tasks. In this paper, we propose a novel and universal geometric loss function, named Subspace-PnP, which is based on the Perspective-n-Points (PnP) and union-of-subspaces theory (Ji et al., in: IEEE Winter conference on applications of computer vision, pp 461-468, 2014) to jointly estimate the optical flow and stereo depth. The construction of Subspace-PnP dose not rely on the camera pose, but implicitly contains information of camera pose and motions of all moving objects. Our experiments show that the Subspace-PnP loss can mutually guide the estimation of optical flow and depth, enabling better robustness and greater accuracy even in dynamic scenes. In addition, we propose a motion-occlusion simulation method to handle occlusions caused by moving objects in optical flow estimation, which in turn can yield further performance improvement. Our method achieves the state-of-the-art performance for joint

关键词： Stereo depth estimation optical flow prediction Subspace-clustering Perspective-n-Point

来源：评论

学校读者我要写书评

暂无评论

Learning From Images: A Distillation Learning Framework for Event Cameras

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 4919-4931页

作者： Deng, Yongjian Chen, Hao Chen, Huiying Li, Youfu City Univ Hong Kong Dept Mech Engn Hong Kong Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 211189 Peoples R China Hong Kong Polytech Univ Dept Ind & Syst Engn Hong Kong Peoples R China

Event cameras have recently drawn massive attention in the computer vision community because of their low power consumption and high response speed. These cameras produce sparse and non-uniform spatiotemporal representations of a scene. These characteristics of representations make it difficult for event-based models to extract discriminative cues (such as textures and geometric relationships). Consequently, event-based methods usually perform poorly compared to their conventional image counterparts. Considering that traditional images and event signals share considerable visual information, this paper aims to improve the feature extraction ability of event-based models by using knowledge distilled from the image domain to additionally provide explicit feature-level supervision for the learning of event data. Specifically, we propose a simple yet effective distillation learning framework, including multi-level customized knowledge distillation constraints. Our framework can significantly boost the feature extraction process for event data and is applicable to various downstream tasks. We evaluate our framework on high-level and low-level tasks, i.e., object classification and optical flow prediction. Experimental results show that our framework can effectively improve the performance of event-based models on both tasks by a large margin. Furthermore, we present a 10K dataset (CEP-DVS) for event-based object classification. This dataset consists of samples recorded under random motion trajectories that can better evaluate the motion robustness of the event-based model and is compatible with multi-modality vision tasks.

关键词： Task analysis Feature extraction Cameras Data models Streaming media Trajectory Power demand Event-based vision dynamic vision sensor object categorization optical flow prediction

来源：评论

学校读者我要写书评

暂无评论

A cascade reconstruction model with generalization ability evaluation for anomaly detection in videos

引用

PATTERN RECOGNITION 2022年 122卷 108336-108336页

作者： Zhong, Yuanhong Chen, Xia Jiang, Jinyang Ren, Fan Chongqing Univ Sch Microelect & Commun Engn Chongqing 400030 Peoples R China State Grid Chongqing Elect Power Res Inst Chongqing 401123 Peoples R China Changan Automobile Corp Changan Software Technol Co Chongqing 401120 Peoples R China

Anomaly detection plays an important role in surveillance video since it maintains public safety efficiently with low cost. In current works, anomaly detection methods based on reconstruction with deep learning has been extensively studied for the powerful representation capacity. These methods use convolutional neural networks to learn model for describing normality at training and detect anomalies according to reconstruction error at testing. However, excessive representation capacity of neural networks will also bring disadvantages to anomaly detection when it is powerful enough to reconstruct abnormal infor-mation. For this reason, we proposed two solutions;firstly, a cascade model which conducts pixel recon-struction followed by optical flow prediction is designed. The conversion from frame to optical flow learns the correlation between object appearance and motion, while pixel reconstruction enlarges the optical flow prediction error to conduct effective anomaly detection. Secondly, the generalization ability evalua-tion based on pseudo-anomaly is proposed, which is used to evaluate the ability of model to represent anomaly, thus selecting an optimal model for anomaly detection. The selected model achieves AUC 88.9% on Avenue, 82.6% on Ped1, 97.7% on Ped2, and 70.7% on ShanghaiTech datasets. Extensive ablation ex-periments have verified the effectiveness of our method. Code will be released at https://***/Xia-Chen/Cascade_Reconstruction. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： Anomaly detection pixel reconstruction optical flow prediction generalization ability evaluation

来源：评论

学校读者我要写书评

暂无评论

Every Pixel Counts plus plus : Joint Learning of Geometry and Motion with 3D Holistic Understanding

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2020年第10期42卷 2624-2641页

作者： Luo, Chenxu Yang, Zhenheng Wang, Peng Wang, Yang Xu, Wei Nevatia, Ram Yuille, Alan Baidu Res Inst Sunnyvale CA 94089 USA Johns Hopkins Univ Baltimore MD 21218 USA Univ Southern Calif Los Angeles CA 90007 USA

Learning to estimate 3D geometry in a single frame and optical flow from consecutive frames by watching unlabeled videos via deep convolutional network has made significant progress recently. Current state-of-the-art (SoTA) methods treat the two tasks independently. One typical assumption of the existing depth estimation methods is that the scenes contain no independent moving objects. while object moving could be easily modeled using optical flow. In this paper, we propose to address the two tasks as a whole, i.e., to jointly understand per-pixel 3D geometry and motion. This eliminates the need of static scene assumption and enforces the inherent geometrical consistency during the learning process, yielding significantly improved results for both tasks. We call our method as "Every Pixel Counts++" or "EPC++". Specifically, during training, given two consecutive frames from a video, we adopt three parallel networks to predict the camera motion (MotionNet), dense depth map (DepthNet), and per-pixel optical flow between two frames (OptflowNet) respectively. The three types of information, are fed into a holistic 3D motion parser (HMP), and per-pixel 3D motion of both rigid background and moving objects are disentangled and recovered. Various loss terms are formulated to jointly supervise the three networks. An effective adaptive training strategy is proposed to achieve better performance and more efficient convergence. Comprehensive experiments were conducted on datasets with different scenes, including driving scenario (KITTI 2012 and KITTI 2015 datasets), mixed outdoor/indoor scenes (Make3D) and synthetic animation (MPI Sintel dataset). Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods, demonstrating the effectiveness of each module of our proposed method. Code will be available at: https://***/chenxuluo/EPC.

关键词： Estimation optical imaging Three-dimensional displays Cameras Videos Geometry Task analysis Depth estimation optical flow prediction unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis

引用

ACM TRANSACTIONS ON GRAPHICS 2019年第6期38卷 175-175页

作者： Endo, Yuki Kanamori, Yoshihiro Kuriyama, Shigeru Univ Tsukuba Tsukuba Ibaraki Japan Toyohashi Univ Technol Toyohashi Aichi Japan

Automatic generation of a high-quality video from a single image remains a challenging task despite the recent advances in deep generative models. This paper proposes a method that can create a high-resolution, long-term animation using convolutional neural networks (CNNs) from a single landscape image where we mainly focus on skies and waters. Our key observation is that the motion (e.g., moving clouds) and appearance (e.g., time-varying colors in the sky) in natural scenes have different time scales. We thus learn them separately and predict them with decoupled control while handling future uncertainty in both predictions by introducing latent codes. Unlike previous methods that infer output frames directly, our CNNs predict spatially-smooth intermediate data, i.e., for motion, flow fields for warping, and for appearance, color transfer maps, via self-supervised learning, i.e., without explicitly-provided ground truth. These intermediate data are applied not to each previous output frame, but to the input image only once for each output frame. This design is crucial to alleviate error accumulation in long-term predictions, which is the essential problem in previous recurrent approaches. The output frames can be looped like cinemagraph, and also be controlled directly by specifying latent codes or indirectly via visual annotations. We demonstrate the effectiveness of our method through comparisons with the state-of-the-arts on video prediction as well as appearance manipulation. Resultant videos, codes, and datasets will be available at http://***/similar to endo/projects/AnimatingLandscape.

关键词： Single-image video synthesis Time-lapse video Convolutional neural networks optical flow prediction Appearance manipulation

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：