检索结果-内蒙古大学图书馆

Coral reef mosaicking using Teardrop and Fast Image Labeling

学校读者我要写书评

暂无评论

Coral reef mosaicking using Teardrop and Fast Image Labeling

OCEANS - Europe

作者： Francis James Corpuz Prospero Naval Eusebio Capili Jaylord Jauod Roel John Judilla Maricor Soriano Vision and Image Processing Group Instrumentation Physics Laboratory National Institute of Physics Computer Vision and Machine Intelligence Group Department of Computer Science College of Engineering University of Philippines Quezon Philippines Computer Vision and Machine Intelligence Group Department of Computer Science College of Engineering University of Philippines Quezon Philippines Mapua Robotics Center Special Projects Laboratory Institutional Laboratory Mgmt Office Mapua Institute of Technology Manila Philippines Vision and Image Processing Group Instrumentation Physics Laboratory National Institute of Physics University of Philippines Quezon Philippines

In this paper, we present an inexpensive system for diverless video capture and fast image stitching of image frames for rapid reef assessment of shallow coral reefs. Our system has two main components: 1) Teardrop, a boat-towable, winged hull apparatus designed to house a commercial digital camera, and 2) a mosaicking algorithm to stitch the coral reef video into mosaics for further appreciation and analysis. The captured reef video is then separated into image frames which are to be stitched sequentially using Fast Image Labeling. The overlap between image frames is estimated using Single-Step DFT, an efficient sub-pixel estimation algorithm. The estimated overlap is used to compute for the area to be added to the mosaic space. The overlapping section between succeeding image-pairs are stitched along a seam determined by a minimal-cost path using dynamic programming. The visibility of the seam boundaries is further minimized by utilizing blending on multi-resolution splines. Experimental results on automated reef mosaics creation from actual coral reef video taken using Teardrop shows the performance of the system described. The main contribution of this work is the demonstration of a rapid reef visualization system using a diverless system and commercially available, non-research-grade imaging equipment.

关键词： Image segmentation Sea measurements Cameras Labeling Discrete Fourier transforms Sea floor

Policy-Guided Lazy Search with Feedback for Task and Motion Planning

学校读者我要写书评

暂无评论

Policy-Guided Lazy Search with Feedback for Task and Motion ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Mohamed Khodeir Atharv Sonwane Ruthrash Hari Florian Shkurti Robot Vision and Learning Lab University of Toronto Robotics Institute Dept. of Computer Science University of BITS Pilani Dept. of Mathematical and Computational Sciences University of Toronto

PDDLStream solvers have recently emerged as viable solutions for Task and Motion Planning (TAMP) problems, extending PDDL to problems with continuous action spaces. Prior work has shown how PDDLStream problems can be reduced to a sequence of PDDL planning problems, which can then be solved using off-the-shelf planners. However, this approach can suffer from long runtimes. In this paper we propose LAZY, a solver for PDDLStream problems that maintains a single integrated search over action skeletons, which gets progressively more geometrically informed, as samples of possible motions are lazily drawn during motion planning. We explore how learned models of goal-directed policies and current motion sampling data can be incorporated in LAZY to adaptively guide the task planner. We show that this leads to significant speed-ups in the search for a feasible solution evaluated over unseen test environments of varying numbers of objects, goals, and initial conditions. We evaluate our TAMP approach by comparing to existing solvers for PDDLStream problems on a range of simulated 7DoF rearrangement/manipulation problems. Code can be found at https://***/learning-based-tamp.

关键词：

Webvision challenge: Visual learning and understanding with web data

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Li, Wen Wang, Limin Li, Wei Agustsson, Eirikur Berent, Jesse Gupta, Abhinav Sukthankar, Rahul van Gool, Luc Computer Vision Laboratory ETH Zurich Switzerland Google Research Zurich Switzerland Robotics Institute Carnegie Mellon University Pittsburgh United States Google Research United States

We present the 2017 Webvision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the spirit of previous vision challenges, such as ILSVRC [1], Places2 [2] and PASCAL VOC [3], which have played critical roles in the development of computer vision by contributing to the community with large scale annotated data for model designing and standardized benchmarking, we contribute with this challenge a large scale web images dataset, and a public competition with a workshop co-located with CVPR 2017. The Webvision dataset contains more than 2.4 million web images crawled from the Internet by using queries generated from the 1, 000 semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information is also included. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. The 2017 Webvision challenge consists of two tracks, the image classification task on Webvision test set, and the transfer learning task on PASCAL VOC 2012 dataset. In this paper, we describe the details of data collection and annotation, highlight the characteristics of the dataset, and introduce the evaluation metrics. Copyright © 2017, The Authors. All rights reserved.

关键词： Image classification

Towards robust monocular visual odometry for flying robots on planetary missions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wudenka, Martin Müller, Marcus G. Demmel, Nikolaus Wedler, Armin Triebel, Rudolph Cremers, Daniel Stürzl, Wolfgang Institute of Robotics and Mechatronics German Aerospace Center DLR Computer Vision Group Department of Informatics Technical University of Munich Germany Autonomous Systems Lab ETH Zurich Switzerland

In the future, extraterrestrial expeditions will not only be conducted by rovers but also by flying robots. The technical demonstration drone Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by terrain traversability. Robust self-localization is crucial for that. Cameras that are lightweight, cheap and information-rich sensors are already used to estimate the ego-motion of vehicles. However, methods proven to work in man-made environments cannot simply be deployed on other planets. The highly repetitive textures present in the wastelands of Mars pose a huge challenge to descriptor matching based approaches. In this paper, we present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking to obtain feature correspondences between images and a refined keyframe selection criterion. In contrast to most other approaches, our framework can also handle rotation-only motions that are particularly challenging for monocular odometry systems. Furthermore, we present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix. This way we obtain an implicit measure of uncertainty. We evaluate the validity of our approach on all sequences of a challenging real-world dataset captured in a Mars-like environment and show that it outperforms state-of-the-art approaches. The source code is publicly available at: https://***/DLR-RM/granite. Copyright © 2021, The Authors. All rights reserved.

关键词： Principal component analysis

O 2 CA 2 : A New Hybrid Control Architecture for a Low Cost AUV

学校读者我要写书评

暂无评论

IFAC Proceedings Volumes 2001年第7期34卷 311-316页

作者： P. Ridao M. Carreras J. Batlle J. Amat Computer Vision and Robotics Group Institute of Informatics and Applications University of Girona Edifici Politècnica II Campus Montilivi 17071 Girona Spain Department of Automatic Control and Computer Engineering Politechnical University of Catalunya. Pau Gargallo n°5 08028 Barcelona (Spain).

The Object Oriented Control Architecture for Autonomy (O 2 CA 2 ) is a control architecture being developed at the University of Girona for the GARBI underwater vehicle. Conceived as a hybrid, it is organised in three layers (Deliberative, Control Execution and Reactive) merging the deliberation mechanisms of planning with reactive behaviours in charge of controlling the robot. The aim of this paper is to provide an overall description of the whole architecture and an in depth description of the Reactive-layer. The concepts of the architecture have been tested with the simulation of a simple mission consisting of navigating through a sequence of way-points while avoiding contact with obstacles.

关键词： Autonomous Vehicles Control architectures behaviour fuzzy systems guidance navigation marine systems

Multi-Scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

学校读者我要写书评

暂无评论

Multi-Scale Dynamic and Hierarchical Relationship Modeling f...

Conference on computer vision and Pattern Recognition (CVPR)

作者： Zihan Wang Siyang Song Cheng Luo Songhe Deng Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Universiry of Leicester Monash University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hi-erarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatiotemporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and mag-nitude in different AUs' activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR.

关键词： Gold Adaptation models computer vision Graphical models Codes Adaptive systems Computational modeling

Delving into the Scale Variance Problem in Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Junliang Zhao, Xiaodong Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale input. The capability of traditional convolution with a fixed receptive field in dealing with such a scale variance problem, is thus limited. Multi-scale feature representation has been proven to be an effective way to mitigate the scale variance problem. Recent researches mainly adopt partial connection with certain scales, or aggregate features from all scales and focus on the global information across the scales. However, the information across spatial and depth dimensions is ignored. Inspired by this, we propose the multi-scale convolution (MSConv) to handle this problem. Taking into consideration scale, spatial and depth information at the same time, MSConv is able to process multi-scale input more comprehensively. MSConv is effective and computationally efficient, with only a small increase of computational cost. For most of the single-stage object detectors, replacing the traditional convolutions with MSConvs in the detection head can bring more than 2.5% improvement in AP (on COCO 2017 dataset), with only 3% increase of FLOPs. MSConv is also flexible and effective for two-stage object detectors. When extended to the mainstream two-stage object detectors, MSConv can bring up to 3.0% improvement in AP. Our best model under single-scale testing achieves 48.9% AP on COCO 2017 test-dev split, which surpasses many state-of-the-art methods. © 2022, CC BY.

关键词： Object detection

Corrigendum to “PSFHS challenge report: pubic symphysis and fetal head segmentation from intrapartum ultrasound images” [Medical Image Analysis 99 (2025),103353]

学校读者我要写书评

暂无评论

Medical Image Analysis 2025年

作者： Jieyun Bai Zihao Zhou Zhanhong Ou Gregor Koehler Raphael Stock Klaus Maier-Hein Marawan Elbatel Robert Martí Xiaomeng Li Yaoyang Qiu Panjie Gou Gongping Chen Lei Zhao Jianxun Zhang Yu Dai Fangyijie Wang Guénolé Silvestre Kathleen Curran Hongkun Sun Jing Xu Karim Lekadir Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization Jinan University Guangzhou China Auckland Bioengineering Institute The University of Auckland Auckland New Zealand Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Department of Computer Science and Engineering The Chinese University of Hong Kong China Computer Vision and Robotics Group University of Girona Girona Spain Canon Medical Systems (China) Co. LTD Beijing China College of Artificial Intelligence Nankai University Tianjin China College of Computer Science and Electronic Engineering Hunan University Changsha China School of Medicine University College Dublin Dublin Ireland School of Computer Science University College Dublin Dublin Ireland School of Statistics & Mathematics Zhejiang Gongshang University Hangzhou China Departament de Matemàtiques i Informàtica Universitat de Barcelona Barcelona Spain Institució Catalana de Recerca i Estudis Avançats (ICREA) Barcelona Spain

Selective Multi-Scale Learning for Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Junliang Lu, Weizeng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8% improvement in AP (from 39.1% to 40.9%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0% improvement in AP. © 2022, CC BY.

关键词： Object detection