14,982 Hits in 4.1 sec


2012 International Journal of Uncertainty Fuzziness and Knowledge-Based Systems  
By applying least-squares fitting over groups of disparity maps columns to a linear model, free paths are detected by giving a certainty using a fuzzy rule.  ...  It is based on looking for linear variations of depth in disparity maps, which are obtained by processing a pair of rectified images from two stereo cameras.  ...  Free path detection offers an advantage over the obstacle detection: free pathways are easier to detect by looking at the pattern they follow in a disparity map obtained by processing two stereo images  ... 
doi:10.1142/s0218488512500122 fatcat:gqbkxokfrjcqfhq43lepdss2jq

Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images [article]

Lei Sun, Kailun Yang, Xinxin Hu, Weijian Hu, Kaiwei Wang
2020 arXiv   pre-print
Multi-dataset training is leveraged to incorporate unexpected small obstacle detection, enriching the recognizable classes required to face unforeseen hazards in the real world.  ...  However, few real-time RGB-D fusion semantic segmentation studies are carried out despite readily accessible depth information nowadays.  ...  For example, learning that all kinds of obstacles have some common contextual property, being of small dimensions and surrounded at least partly by free-space.  ... 
arXiv:2002.10570v2 fatcat:tfnxpu5mxbclla5icoe25vwys4

Improving wheelchair route planning through instrumentation and navigation systems

Dzenan Dzafic, Jorge L. Candiotti, Rory A. Cooper
2020 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)  
However, for people who use electric powered wheelchairs (EPW) as their primary means of mobility, the level of accessibility and EPW battery consumption are important during route planning.  ...  these layers of information to provide the shortest, most accessible, and most comfortable routes that consume the least amount of EPW battery.  ...  The contents of this paper do not represent the views of the Department of Veterans Affairs or the United States Government. BIBLIOGRAPHY  ... 
doi:10.1109/embc44109.2020.9176481 pmid:33019277 pmcid:PMC8883793 fatcat:lknkd3ogvbdl7no23qkjhsj4ny


K.Tasleem Banu, K Supriya, K Sony, M Chandana, M Bhavana, Baba Fakruddin Ali
2020 International Journal of Engineering Applied Sciences and Technology  
Our prototype can detect and identify traffic situations such as street crossings, traffic lamps, cars, cyclists, other people and low and high obstacles.  ...  The detection takes place in real time based on input data of sensors and optical cameras, the mobility of the user is aided with audio signals.  ...  The sparse depth map computed from a small set of feature points is only reliable at those point, and the usability obtained depth.  ... 
doi:10.33564/ijeast.2020.v04i12.127 fatcat:bbaamhcogzecrfyxgmof3uy46m

Depth and Motion Cues with Phosphene Patterns for Prosthetic Vision

Alejandro Perez-Yus, Jesus Bermudez-Cameo, Jose J. Guerrero, Gonzalo Lopez-Nicolas
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
We propose using a head-mounted RGB-D camera to detect free-space, obstacles and scene direction in front of the user.  ...  The main contribution is a new approach to represent depth information and provide motion cues by using particular phosphene patterns.  ...  This work was supported by Projects DPI2014-61792-EXP and DPI2015-65962-R (MINECO/FEDER, UE) and grant BES-2013-065834 (MINECO).  ... 
doi:10.1109/iccvw.2017.179 dblp:conf/iccvw/Perez-YusBGL17 fatcat:izmaj6cs5vcb7gnqb26eruc5cu

Computer Vision for the Visually Impaired: the Sound of Vision System

Simona Caraiman, Anca Morar, Mateusz Owczarek, Adrian Burlacu, Dariusz Rzeszotarski, Nicolae Botezatu, Paul Herghelegiu, Florica Moldoveanu, Pawel Strumillo, Alin Moldoveanu
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
Its main objective is to provide the users with a 3D representation of the environment around them, conveyed by means of the hearing and tactile senses.  ...  One of the biggest challenges for this system is to ensure pervasiveness, i.e., to be usable in any indoor or outdoor environments and in any illumination conditions.  ...  Acknowledgement This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 643636 "Sound of Vision".  ... 
doi:10.1109/iccvw.2017.175 dblp:conf/iccvw/CaraimanMOBRBHM17 fatcat:ab4p4aflnzhqvfvxtp7yqttcsu

3D Simulation of Navigation Problem of People with Cerebral Visual Impairment [chapter]

Yahya Qasim I. Al-Fadhili, Paul W. H. Chung, Baihua Li, Richard Bowman
2017 Advances in Intelligent Systems and Computing  
The hit-rays mean objects are detected; however, the non-hit rays mean objects are not detected.  ...  The lengths of each ray depend on the numerical value taken from the vision map and produce the Ray Map. The bigger values (means high percentage of opacity) are represented by short beam in length.  ... 
doi:10.1007/978-3-319-66939-7_23 fatcat:ujfx4pqh7bb6tphnddzdxzxg4m

Obstacle Detection System for Agricultural Mobile Robot Application Using RGB-D Cameras

Magda Skoczeń, Marcin Ochman, Krystian Spyra, Maciej Nikodem, Damian Krata, Marcin Panek, Andrzej Pawłowski
2021 Sensors  
The results show that the proposed image and depth data processing pipeline introduces an additional distortion of 38 cm.  ...  This assumption significantly limits the number of mapping, path planning, and navigation algorithms to be used in this application.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21165292 pmid:34450732 pmcid:PMC8399919 fatcat:f3aozifv6vegvgohdwb3sfaxqy

Scene perception system for visually impaired based on object detection and classification using multimodal deep convolutional neural network

Baljit Kaur, Jhilik Bhattacharya
2019 Journal of Electronic Imaging (JEI)  
The system classifies the detected objects along with its distance from the user and provides a voice output. Experimental results provided in this paper use outdoor traffic scenes.  ...  The object detection and classification framework exploits a multi-modal fusion based faster RCNN using motion, sharpening and blurring filters for efficient feature representation.  ...  Kanwal et al.(2015)[23] Detect Wall-like obstacles (pillar, people) and their depth kinect Harris & Stephens corner detection Alarden et al.(2016)[24] Provide Obstacle free path RGB-D camera  ... 
doi:10.1117/1.jei.28.1.013031 fatcat:tqrienpl5ff7ddymmbsilmruhy

Indoor/outdoor navigation system based on possibilistic traversable area segmentation for visually impaired people

Jihen Frikha, Dorra Sellami, Imen Khanfir Kallel
2016 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
Then fusing these maps allows making a fair model definition of the traversable area. Performance of the proposed system was evaluated on public databases, at indoor and outdoor environments.  ...  An efficient way of updating the traversable area model in each environment condition is to consider traversable area samples from the same processed image for building its possibility maps.  ...  The depth map is provided by RGB-D sensor. In [7] , authors exploit the depth-maps given by a Kinect sensor to estimate the ground plane.  ... 
doi:10.5565/rev/elcvia.818 fatcat:j3br4s246bhapkmg54miwluoei

Vision-based Mobile Indoor Assistive Navigation Aid for Blind People

Bing Li, Juan Pablo Munoz, Xuejian Rong, Qingtian Chen, Jizhong Xiao, Yingli Tian, Aries Arditi, Mohammed Yousuf
2018 IEEE Transactions on Mobile Computing  
Using the on-board RGB-D camera, we develop an efficient obstacle detection and avoidance approach based on a time-stamped map Kalman filter (TSM-KF) algorithm.  ...  The system detects dynamic obstacles and adjusts path planning in real-time to improve navigation safety.  ...  Based on the assumption that obstacle-free pathway is at the bottom of the depth image, CASBliP detects the obstacle-free pathway as the bottom partition of the image which has small disparities.  ... 
doi:10.1109/tmc.2018.2842751 pmid:30774566 pmcid:PMC6371975 fatcat:kojyg56levdepmpqodseopqkfe

An architecture for a VLSI sensory–motor system for obstacle avoidance

David Claveau, Chunyan Wang
2005 Robotics and Autonomous Systems  
It differs from existing systems by using a special foveation scheme to facilitate the detection of realworld objects.  ...  From this, a motor control signal is produced by using a biologically inspired technique of aligning sensory and motor maps.  ...  Finally, by summing the scaled derivatives a continuous signal is produced to indicate the extent of the free pathway.  ... 
doi:10.1016/j.robot.2004.06.005 fatcat:dnnr3tmhx5dnvmxbnj2b2lupqa

Learned Enrichment of Top-View Grid Maps Improves Object Detection [article]

Sascha Wirges, Ye Yang, Sven Richter, Haohao Hu, Christoph Stiller
2020 arXiv   pre-print
Our goal in the joint model is to improve generalization by regularizing towards structural knowledge in form of a map fused from multiple adjacent range sensor measurements.  ...  We propose an object detector for top-view grid maps which is additionally trained to generate an enriched version of its input.  ...  The height of obstacles above ground is modeled by independent normal distributions p (z|µ i , σ i ) with mean µ i = z i,max.obs. + z i,max.det. 2 and variance σ 2 i = z i,max.obs. − z i,max.det. which  ... 
arXiv:2003.00710v2 fatcat:nbq4vbmbkvf4hin72wr2aywjpm


Jackie (Junrui) Yang, Christian Holz, Eyal Ofek, Andrew D. Wilson
2019 Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology - UIST '19  
The debug image result from DreamWalker's tracking, showing the detected ad-hoc and dynamic (people) obstacles in white cubes and colored cylinders and illustrates the three tracking sources: depth height  ...  collision-free.  ...  ACKNOWLEDGMENTS We thank all the participants of our study for their time and useful comments after evaluating our system.  ... 
doi:10.1145/3332165.3347875 dblp:conf/uist/Yang0OW19 fatcat:ng44mz4r2rez3l4z2op6ki344q

Robotic control and motion planning

2012 2012 IEEE International Symposium on Industrial Electronics  
of obstacle in it, that have to be avoided.  ...  Robot is based on various control motions which is controlled by planning, Electronic sensor, Digital signals, Computer mechanics, Coordination, Actuation, Learning and adaptation.  ...  The robot is surrounded by an environment consisting of known pathways and pathway intersections. 2. The robot may only travel along a defined set of pathways. 3.  ... 
doi:10.1109/isie.2012.6237269 fatcat:y4pln2356ba3hmtjgrfpkanzdu
« Previous Showing results 1 — 15 out of 14,982 results