Filters








2,024 Hits in 6.3 sec

TINYPHOON A Tiny Autonomous Mobile Robot

G. Novak, S. Mahlknecht
2005 Proceedings of the IEEE International Symposium on Industrial Electronics, 2005. ISIE 2005.  
In this paper the system architecture of a tiny autonomous mobile robot, called Tinyphoon, is described.  ...  An outstanding feature is its high-speed onboard vision system comprising a small digital CMOS camera and a very fast and low power signal processing unit.  ...  ACKNOWLEDGMENT This paper was written within the Center of Excellence for Autonomous Systems of the Vienna University of Technology (CEAS).  ... 
doi:10.1109/isie.2005.1529160 fatcat:c5izsx5cfbamff72jutmrzngca

FPGA-based module for SURF extraction

Tomáš Krajník, Jan Šváb, Sol Pedre, Petr Čížek, Libor Přeučil
2014 Machine Vision and Applications  
We present a complete hardware and software solution of an FPGA-based computer vision embedded module capable of carrying out SURF image features extraction algorithm.  ...  Thus, it allows to use the SURF algorithm in applications with power and spatial constraints, such as autonomous navigation of small mobile robots.  ...  and software solution of an FPGA-based computer vision embedded module capable of carrying out SURF image features extraction algorithm.  ... 
doi:10.1007/s00138-014-0599-0 fatcat:dj3ddob3xjeuroamg67olae46q

A concept of dynamically reconfigurable real-time vision system for autonomous mobile robotics

Aymeric De Cabrol, Thibault Garcia, Patrick Bonnin, Maryline Chetto
2008 International Journal of Automation and Computing  
In this article, we describe specific constraints of vision systems that are dedicated to be embedded in mobile robots.  ...  To answer this problem, we have developed a dynamically reconfigurable vision processing system, based on the innovative features of Cléopatre real-time applicative layer concerning scheduling and fault  ...  At last, if the role of the principal task was to extract some image features as regions or edges, it may be useful to mend the extracted features on the line of darn 3 , according to applicative context  ... 
doi:10.1007/s11633-008-0174-0 fatcat:xswdip5tmvd2xlg2qdwbxprz4q

Improved Approach to Global Localization based on Odometry Error Modeling for Mobile Robots

Jingdong Yang, Jinghui Yang
2014 Applied Mathematics & Information Sciences  
Therefore, an efficient approach to odometry error modeling is proposed regarding gentle drive type mobile robots.  ...  It is often the odometry accumulative error without bound after long-range movement that decreases the precision of global localization for wheeled mobile robots.  ...  And it is also supported by Innovation Program of Shang hai Municipal Education Commission(B51JG13R003, 13YZ075).Thanks for the help.  ... 
doi:10.12785/amis/080214 fatcat:diq7dz3j25c3rogmavpivgqr3u

Interhemispheric transport of viable fungi and bacteria from Africa to the Caribbean with soil dust

Joseph M. Prospero, Edmund Blades, George Mathison, Raana Naidu
2005 Aerobiologia  
In this article, we describe specific constraints of vision systems that are dedicated to be embedded in mobile robots.  ...  To answer this problem, we have developed a dynamically reconfigurable vision processing system, based on the innovative features of Cléopatre real-time applicative layer concerning scheduling and fault  ...  At last, if the role of the principal task was to extract some image features as regions or edges, it may be useful to mend the extracted features on the line of darn 3 , according to applicative context  ... 
doi:10.1007/s10453-004-5872-7 fatcat:c7i55hg3cfae3hrhi6tq2ara2e

Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning [article]

Liqi Yan and Dongfang Liu and Yaoxian Song and Changbin Yu
2020 arXiv   pre-print
Vision and voice are two vital keys for agents' interaction and learning.  ...  We have experimented with various functional features extracted from visual observation. Comparative experiments prove that our methods outperform state-of-the-art baselines.  ...  In order to fulfill various missions, it is imperative for the indoor mobile robot to be able to realize highly efficient search, plus location and approach tasks in restricted circumstances [1] [2  ... 
arXiv:2009.00402v1 fatcat:6ectbkhknvfb7dlgw5de7hawae

A deep learning based hazardous materials (HAZMAT) sign detection robot with restricted computational resources

Amir Sharifi, Ahmadreza Zibaei, Mahdi Rezaei
2021 Machine Learning with Applications  
In this research, we propose a CNN-Based pipeline called DeepHAZMAT for HAZMAT sign detection and segmentation in four steps: 1) Input data volume optimisation before feeding into the CNN network, 2) Application  ...  Rezaei, A deep learning based hazardous materials (HAZMAT) sign detection robot with restricted computational resources. Machine Learning with Applications (2021), doi: https://doi.  ...  In deep neural network based methods the models try to extract some common features of the HAZMAT sign during the training phase.  ... 
doi:10.1016/j.mlwa.2021.100104 fatcat:omplxqmnjfcqxcqihvj53betv4

Fast and Accurate Recognition for Codes on Complex Backgrounds for Real-Life Industrial Applications

Qiaokang Liang, National Engineering Laboratory for Robot Vision Perception and Control, Hunan University, Changsha 410082, China, Qiao Ge, Wei Sun, Dan Zhang, Yaonan Wang, Kunlin Zou, National Engineering Laboratory for Robot Vision Perception and Control, Hunan University, Changsha 410082, China, National Engineering Laboratory for Robot Vision Perception and Control, Hunan University, Changsha 410082, China, Department of Mechanical Engineering, York University, Toronto, ON M3J 1P3, Canada, National Engineering Laboratory for Robot Vision Perception and Control, Hunan University, Changsha 410082, China, Department of Mechanical Engineering, York University, Toronto, ON M3J 1P3, Canada
2021 Maǧallaẗ al-abḥāṯ al-handasiyyaẗ  
This work presents an efficient and accurate inkjet code recognition system based on the combination of the deep learning and traditional image processing methods.  ...  ., the characters region extraction by modified YOLOv3-tiny network, the character processing by the traditional image processing methods such as binarization and the modified character projection segmentation  ...  a fast and efficient solution for code character recognition on complex packaging.  ... 
doi:10.36909/jer.10603 fatcat:cswxpotnefhdjiuycs7k6bgzgq

Eyes of Things

Oscar Deniz, Noelia Vallez, Jose Espinosa-Aranda, Jose Rico-Saavedra, Javier Parra-Patino, Gloria Bueno, David Moloney, Alireza Dehghani, Aubrey Dunne, Alain Pagani, Stephan Krauss, Ruben Reiser (+8 others)
2017 Sensors  
Intelligent computing aims to solve problems for which no efficient exact algorithm can exist or for which we cannot conceive an exact algorithm.  ...  Central to such intelligence is Computer Vision (CV), i.e., extracting meaning from images and video.  ...  • Feature point extraction algorithm Figure 14 shows two examples that used Libccv.  ... 
doi:10.3390/s17051173 pmid:28531141 pmcid:PMC5470918 fatcat:pbckuydmefcapgx6a6w2rogoqy

On-Device Object Detection for More Efficient and Privacy-Compliant Visual Perception in Context-Aware Systems

Ivan Rodriguez-Conde, Celso Campos, Florentino Fdez-Riverola
2021 Applied Sciences  
Ambient Intelligence (AmI) encompasses technological infrastructures capable of sensing data from environments and extracting high-level knowledge to detect or recognize users' features and actions, as  ...  Framed in that novel paradigm, this work presents a review of the recent advances made along those lines in object detection, providing a comprehensive study of the most relevant lightweight CNN-based  ...  Compact and Efficient Vision-Based Detection Frameworks Nowadays, whether we tackle the cross-domain on-device space involving compact and efficient solutions or more specific research focused just on  ... 
doi:10.3390/app11199173 fatcat:cncucjelmrgv3mdortgxax2qly

Extended Spectral Regression for efficient scene recognition

Liyuan Li, Weixun Goh, Joo Hwee Lim, Sinno Jialin Pan
2014 Pattern Recognition  
This paper proposes a novel method based on Spectral Regression (SR) for efficient scene recognition.  ...  Then, an efficient Bag-of-Words (BOW) based method is developed which employs ESR to encapsulate local visual features with their semantic, spatial, scale, and orientation information for scene recognition  ...  These lead to an efficient approach for real-time scene recognition on a portable mobile platform with limited memory and computational resources.  ... 
doi:10.1016/j.patcog.2014.03.012 fatcat:qmywq66dsbg5hknv5jgximwnqe

A NEW CONTROL FRAMEWORK FOR ROBOT SOCCER SYSTEM

Dong-Hun Lee, Seung-Min Baek, Tae-Kyung Moon, Chae-Wook Chung, Tae-Yong Kuc
2005 IFAC Proceedings Volumes  
This paper presents a new control framework for robotic soccer system which consists of a group of 11 micro-robots, external vision system, ultrasonic GPS sensor network, RF communication modules, and  ...  main computer to perform a distributed sensing and control for successful soccer game in X-large league Mirosot of FIRA [11] .  ...  The Vision System In the MiroSot, an external color vision system is used to provide the raw data of planar ground for visual information extraction.  ... 
doi:10.3182/20050703-6-cz-1902.02090 fatcat:jebfmr6h3vcm3l3nshmjcrxj2m

Frontiers of research and future directions in information and communication technology

Angel G. Jordan
2008 Technology in society  
The convergence of computer vision and graphics has offered new opportunities for frontier research on image-based rendering, and physics-based and data-driven modeling and animation.  ...  Advances are being made in: performance improvements in application-specific memory, to close the ever-growing gap between memory system and processor performance; novel memory systems that extract streams  ... 
doi:10.1016/j.techsoc.2008.05.002 fatcat:lmemejqecrfuhc7sxpex37eyoe

Overview of 3D registration techniques including loop minimization for the complete acquisition of large manufactured parts and complex environments

E. Batlle, C. Matabosch, J. Salvi, David Fofi, Fabrice Meriaudeau
2007 Eighth International Conference on Quality Control by Artificial Vision  
community for quality control applications but also in the robotics field for solving problems such as robot navigation and registration of large surfaces.  ...  This paper presents a survey of the techniques used by the robotics and computer vision communities in which every approach has been compared pointing out their pros and cons and their potential applications  ...  Some of the most common methods are the corner detector proposed by Harris for 2D images 23 and the straight line-based method proposed by Stamos 3 for 3D views; and b) point-to-feature approach when an  ... 
doi:10.1117/12.736695 fatcat:low5zdt7ezba3ncb4myclqmrtq

APES: Attentively Perceiving Robot

Ç Soyer, H. I. Bozma, Y. İstefanopulos
2006 Autonomous Robots  
Robot vision systems -inspired by human-like vision -are required to employ mechanisms similar to those that have proven to be crucial in human visual performance.  ...  for guiding eye movements and modeling the environment.  ...  robot in a natural and efficient way.  ... 
doi:10.1007/s10514-006-5538-0 fatcat:ekgd5rpw4jch7djmcy5vdkp5ia
« Previous Showing results 1 — 15 out of 2,024 results