Filters








209 Hits in 5.1 sec

Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection [article]

Yuliang Liu, Tong He, Hao Chen, Xinyu Wang, Canjie Luo, Shuaitao Zhang, Chunhua Shen, Lianwen Jin
2021 arXiv   pre-print
Multi-orientation scene text detection has recently gained significant research attention. Previous methods directly predict words or text lines, typically by using quadrilateral shapes.  ...  Here we solve this problem by proposing a new method, Orderless Box Discretization (OBD), which first discretizes the quadrilateral box into several key edges containing all potential horizontal and vertical  ...  Multi-orientation scene text detection is one of the most important representations for the task of scene text detection because straight text occupies the majority of the scene text.  ... 
arXiv:1912.09629v3 fatcat:eur5ghyz4rde5d6muoqxj7shqu

What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels [article]

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
2021 arXiv   pre-print
Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data.  ...  In contrast to this practice, training STR models only on fewer real labels (STR with fewer labels) is important when we have to train STR models without synthetic data: for handwritten or artistic texts  ...  Omnidirectional scene text detec- tion with sequential-free box discretization. In IJCAI, 2019. 15 [35] Shangbang Long and Cong Yao.  ... 
arXiv:2103.04400v2 fatcat:nhheisp7jjcp7eh7hljautnm7q

Proceedings of the 1st Workshop on Robotics Challenges and Vision (RCV2013) [article]

Aitor Aladren, Sasa Bodiroza, Hamidreza Chitsaz, J.J. Guerrero, Verena Hafner, Kris Hauser, Aleksandar Jevtic, Moslem Kazemi, Bruno Lara, Gonzalo Lopez-Nicolas, Peer Neubert, Peter Protzel (+2 others)
2014 arXiv   pre-print
While ( C(Box(α)) = FREE) ⊳ Initialization If Box(α) has length < ε, Return ("No Path") Else Expand(Box(α)) While ( C(Box(β)) = FREE) ... do the same for β ... 2.  ...  Matching-free sequential hypothesis propagation This previous single image based algorithm shows good performance and it is robust to occlusions of the scene contours.  ... 
arXiv:1402.3213v1 fatcat:4j5z3btyyfcelf4zjhihonu3na

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art [article]

Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
2021 arXiv   pre-print
As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner.  ...  survey includes both the historically most relevant literature as well as the current state of the art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene  ...  Sequential pipelines as MNC [147] (upper row) use a detection and segmentation network sequentially.  ... 
arXiv:1704.05519v3 fatcat:xiintiarqjbfldheeg2hsydyra

Enactive Robot Vision

Mototaka Suzuki, Dario Floreano
2008 Adaptive Behavior  
I proceed further on this line of investigation and describe the application of this methodology in three situations, namely car driving with an omnidirectional camera, goal-oriented navigation of a humanoid  ...  However, computational models of active vision are very rare and often rely on architectures that are preprogrammed to detect certain characteristics of the environment.  ...  Once the road area is detected, the best evolved car with the omnidirectional camera perfectly drives as that with the pan-tilt camera does.  ... 
doi:10.1177/1059712308089183 fatcat:b2yjftrewnadpfwchfymglms6e

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D [article]

Yiyi Liao, Jun Xie, Andreas Geiger
2022 arXiv   pre-print
For efficient annotation, we created a tool to label 3D scenes with bounding primitives and developed a model that transfers this information into the 2D image domain, resulting in over 150k images and  ...  1B 3D points with coherent semantic instance annotations across 2D and 3D.  ...  In the first step, we apply volumetric fusion over a sequential of laser scans and search for 3D points located in (mostly) free regions.  ... 
arXiv:2109.13410v2 fatcat:dxqki3azibcobptngevkbz5ehq

A survey of deep learning techniques for autonomous driving

Sorin Grigorescu, Bogdan Trasnea, Tiberiu Cocias, Gigel Macesanu
2019 Journal of Field Robotics  
These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration and motion control algorithms.  ...  The comparison presented in this survey helps to gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices  ...  In order to facilitate common computer vision tasks, such as object detection and tracking, the providers annotated 25 object classes with accurate 3D bounding boxes at 2Hz over the entire dataset.  ... 
doi:10.1002/rob.21918 fatcat:pjyk4lwjavf63jz4pmc3mnuqe4

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Roziere, B., +, TIP 2021 4036-Multi-Temporal Scene Classification and Scene Change Detection With Heating systems spectral Imagery.  ...  Sequential Instance Refinement for Cross-Domain Object Detection in Images. Chen, J., +, TIP 2021 3970-3984 Shadow Removal by a Lightness-Guided Network With Training on Unpaired Data.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Peter Sturm
2010 Foundations and Trends in Computer Graphics and Vision  
, with free space between neighboring elements [290] .  ...  Bottom: Slit imaging with a tilted 1D sensor, the so-called "cloud camera" and an image acquired with it (see text).  ... 
doi:10.1561/0600000023 fatcat:i5puai3btrb4vfcvc5zgqgwz3u

Emergence of exploratory look-around behaviors through active observation completion

Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman
2019 Science Robotics  
Nonetheless, it could be interesting to adapt to free-range actions with action-specific costs by allowing the agent to sample any action (continuous or discrete) and penalizing it based on the cost of  ...  SUN360 dataset for scenes For this dataset, our limited field-of-view (60°) agent attempts to complete an omnidirectional scene. SUN360 (33) has spherical panoramas of 26 diverse categories.  ... 
doi:10.1126/scirobotics.aaw6326 pmid:33137723 fatcat:yzljqiulo5fybekdzwkdhttlhi

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
: Detection Utilizing Enhancement for Text in Scanned or Captured Documents DAY 3 -Jan 14, 2021 Zhu, Anna; Du, Hang; Xiong, ShengWu 1828 Scene Text Detection with Selected Anchors DAY 3 -Jan  ...  for Domain Adaptive Scene Text Detection DAY 2 -Jan 13, 2021 Track 5: Imaging and Deep Image Processing PS T5.3 Poster Gather Town 12:00 PM 1:00 PM Ismail Elezi ismail.elezi@gmail.com DAY  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Indoor positioning and wayfinding systems: a survey

Jayakanth Kunhoth, AbdelGhani Karkar, Somaya Al-Maadeed, Abdulla Al-Ali
2020 Human-Centric Computing and Information Sciences  
In particular, the paper reviews different computer vision-based indoor navigation and positioning systems along with indoor scene recognition methods that can aid the indoor navigation.  ...  The article concludes with a brief insight into future directions in indoor positioning and navigation systems.  ...  A text localization model was designed by considering that texts have shapes with closed boundaries and a maximum of two holes.  ... 
doi:10.1186/s13673-020-00222-0 fatcat:m7lt5zdcjbbsvlh7fwatjvpx6y

User Interfaces for Mobile Augmented Reality Systems [article]

Steve Feiner
2003 International Conference on Vision, Video and Graphics  
The ultimate goal is to have a free-to-walk, eyes-free, and hands-free interface with miniature computing devices worn as part of the clothing.  ...  Labels and text in popup windows and dialog boxes are to be displayed in such a fashion as to stay legible for the current user.  ...  This machine included a 133MHz Pentium, 64Mbyte main memory, 512K cache, a 2GB harddisk, and a card cage with expansion slots for three ISA and three PCI cards.  ... 
doi:10.2312/vvg.20031017 dblp:conf/vvg/Feiner03 fatcat:5mztekgvszg33ag6lyoyvxkit4

Fast Autonomous Flight in Warehouses for Inventory Applications

Marius Beul, David Droeschel, Matthias Nieuwenhuisen, Jan Quenzel, Sebastian Houben, Sven Behnke
2018 IEEE Robotics and Automation Letters  
The MAV navigates along warehouse aisles and detects the placed stock in the shelves alongside its path with a multimodal sensor setup containing an RFID reader and two high-resolution cameras.  ...  Experiments were performed in an operative warehouse of a logistics provider, in which an external warehouse management system provided the MAV with high-level inspection missions that are executed fully  ...  box volume ratio of 1:12.  ... 
doi:10.1109/lra.2018.2849833 dblp:journals/ral/BeulDNQHB18 fatcat:asdym5jidrhtxjhdx4xbud7kn4

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, Andre Dietrich, Charles Fox
2020 IEEE transactions on intelligent transportation systems (Print)  
Unlike static obstacles, pedestrians are active agents with complex, interactive motions.  ...  Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds  ...  [67] presented a model-free detection and tracking of dynamic objects with 3D lidar data in complex environments.  ... 
doi:10.1109/tits.2020.3006768 fatcat:awa5dgk4rbazteetyyqrndbgxq
« Previous Showing results 1 — 15 out of 209 results