Filters








6,764 Hits in 4.9 sec

Multi-object tracking via species based particle swarm optimization

Xiaoqin Zhang, Weiming Hu, Wei Li, Wei Qu, Steve Maybank
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
many species according to the number of objects, and each species searches for its object and maintains it.  ...  Most existing approaches concatenate the states of different objects, view the multi-object tracking as a joint motion estimation problem and search for the best state of the joint motion in a rather high  ...  Ming Yang for the help on implementing his algorithm. This work is partly supported by NSFC (Grant No. 60825204, 60672040)  ... 
doi:10.1109/iccvw.2009.5457581 dblp:conf/iccvw/ZhangHLQM09 fatcat:ygpgocsxtzddvnw4zlzqkjliwa

Multiple Object Tracking Via Species-Based Particle Swarm Optimization

Xiaoqin Zhang, Weiming Hu, Wei Qu, Steve Maybank
2010 IEEE transactions on circuits and systems for video technology (Print)  
according to the number of objects, and each species searches for its object and maintains track of it.  ...  Most existing approaches concatenate the states of different objects, view the multi-object tracking as a joint motion estimation problem and search for the best state of the joint motion in a rather high  ...  , in which the different species search for their associated objects (food) and track them once found.  ... 
doi:10.1109/tcsvt.2010.2087455 fatcat:s42ax7townggnlyvt56j2fbssi

Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

Junhua Gu, Chuanxin Lan, Wenbai Chen, Hu Han
2019 Applied Sciences  
Experimental results on the public-domain CUHK-SYSU Person Search Dataset show that the proposed approach outperforms the state-of-the-art methods for joint pedestrian and body part detection in the wild  ...  We also propose an Adaptive Joint Non-Maximum Suppression (AJ-NMS) to replace the original NMS algorithm widely used in object detection, leading to higher precision and recall for detecting overlapped  ...  The proposed approach advances the state-of-the-art in joint pedestrian and body part detection on the widely used CUHK-SYSU Person Search Dataset [25] .  ... 
doi:10.3390/app9040752 fatcat:4qmu4xrporfvbnzwk6hdmrogom

2D Human Pose Estimation in TV Shows [chapter]

Vittorio Ferrari, Manuel Marín-Jiménez, Andrew Zisserman
2009 Lecture Notes in Computer Science  
We propose an approach that progressively reduces the search space for body parts, to greatly facilitate the task for the pose estimator.  ...  Direct pose estimation on this uncontrolled material is often too difficult, especially when knowing nothing about the location, scale, pose, and appearance of the person, or even whether there is a person  ...  We thank Pawan Kumar for helpful discussions on probabilistic models, Varun Gulshan for the extended GrabCut, and Deva Ramanan for the image parsing code [23] .  ... 
doi:10.1007/978-3-642-03061-1_7 fatcat:fyg6x4rlyndujmyti44iscfznq

Human-robot Collaborative Navigation Search using Social Reward Sources [article]

Marc Dalmasso, Anaís Garrell, Pablo Jiménez, Alberto Sanfeliu
2019 arXiv   pre-print
This paper proposes a Social Reward Sources (SRS) design for a Human-Robot Collaborative Navigation (HRCN) task: human-robot collaborative search.  ...  We modelled task rewards based on unexplored area observability and isolation and evaluated the model through different levels of human-robot communication.  ...  no inference is done. c) The person indicates the robot to avoid searching through that zone, as either it is already explored or the person will do it on their own. d) The person finds the object, thus  ... 
arXiv:1909.04768v1 fatcat:cy6tskslszddjfc4w6wedavjqe

Multi-object Tracking Using Particle Swarm Optimization on Target Interactions [chapter]

Bogdan Kwolek
2013 Advances in Heuristic Signal Processing and Applications  
The objective function is built on region covariance matrix and multi-patch based object representation.  ...  In this work, a particle swarm optimization based algorithm for multitarget tracking is presented.  ...  In the approach mentioned above the object interactions are modeled as species competition and repulsion.  ... 
doi:10.1007/978-3-642-37880-5_4 fatcat:goukftihwnexler3uj6dec6r7i

ArtTrack: Articulated Multi-Person Tracking in the Wild

Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin, Siyu Tang, Evgeny Levinkov, Bjoern Andres, Bernt Schiele
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
onto a feed-forward convolutional architecture that is able to detect and associate body joints of the same person even in clutter.  ...  We use this model to generate proposals for body joint locations and formulate articulated tracking as spatio-temporal grouping of such proposals.  ...  This work has been supported by the Max Planck Center for Visual Computing and Communication. The authors thank Varvara Obolonchykova and Bahar Tarakameh for their help in creating the video dataset.  ... 
doi:10.1109/cvpr.2017.142 dblp:conf/cvpr/InsafutdinovAPT17 fatcat:fhq6gycafnaffadinnmhfwpx4a

Multiple Object Tracking by Efficient Graph Partitioning [chapter]

Ratnesh Kumar, Guillaume Charpiat, Monique Thonnat
2015 Lecture Notes in Computer Science  
In this paper, we view multiple object tracking as a graph partitioning problem. Given any object detector, we build the graph of all detections and aim to partition it into trajectories.  ...  Competitive and stable results on varied videos demonstrate the robustness and efficiency of our approach.  ...  We also limit our search to only those subsets of variables which have a joint temporal distance of less than 20 frames, i.e. the maximum time scale in triplets.  ... 
doi:10.1007/978-3-319-16817-3_29 fatcat:gnbjdy3qtzfyfnoyfmf7g7rqdi

A Path Planning Algorithm Using Generalized Potential Model for Hyper-Redundant Robots with 2-DOF Joints

Chien-Chou Lin, Jen-Hui Chuang, Cheng-Tieng Hsieh
2011 International Journal of Advanced Robotic Systems  
The proposed approach computes repulsive force and torque between charged objects by using generalized potential model.  ...  A collision-free path can be obtained by locally adjusting the robot configuration to search for minimum potential configurations using these force and torque.  ...  The main advantages of using such a free space model include: (i) the repulsion among object, manipulators, and obstacles, in forms of force and torque, can be derived in closed form, (ii) the planned  ... 
doi:10.5772/10573 fatcat:23haqaawlrg7vo2f4h63ocs4ci

Social Robot Navigation Tasks: Combining Machine Learning Techniques and Social Force Model

Óscar Gil, Anaís Garrell, Alberto Sanfeliu
2021 Sensors  
Social robot navigation in public spaces, buildings or private houses is a difficult problem that is not well solved due to environmental constraints (buildings, static objects etc.), pedestrians and other  ...  The machine learning techniques are combined with the SFM to create navigation models that behave in a social manner when the robot is navigating in an environment with pedestrians or accompanying a person  ...  , and (v) the y component of the static object repulsive force.  ... 
doi:10.3390/s21217087 pmid:34770395 pmcid:PMC8587852 fatcat:tar6feetcrf37ps5kxgv3as3cq

Safe planning for human-robot interaction

D. Kulic, E. Croft
2004 IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004  
Simulations of the proposed planning strategy are presented for both 2D and 3D robots.  ...  This strategy is one part of the overall methodology for safe planning and control in human-robot interaction.  ...  ACKNOWLEDGMENTS This work is supported by the National Science and Research Council of Canada (NSERC).  ... 
doi:10.1109/robot.2004.1308098 dblp:conf/icra/KulicC04 fatcat:nz6tk2p5ljcpvj5dyewwxyffqy

Safe planning for human-robot interaction

Dana Kulić, Elizabeth A. Croft
2005 Journal of Robotic Systems  
Simulations of the proposed planning strategy are presented for both 2D and 3D robots.  ...  This strategy is one part of the overall methodology for safe planning and control in human-robot interaction.  ...  ACKNOWLEDGMENTS This work is supported by the National Science and Research Council of Canada (NSERC).  ... 
doi:10.1002/rob.20073 fatcat:ryhbej7ldve2xovkc5ie2gvpcq

ArtTrack: Articulated Multi-person Tracking in the Wild [article]

Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin, Siyu Tang, Evgeny Levinkov, Bjoern Andres, Bernt Schiele
2017 arXiv   pre-print
onto a feed-forward convolutional architecture that is able to detect and associate body joints of the same person even in clutter.  ...  We use this model to generate proposals for body joint locations and formulate articulated tracking as spatio-temporal grouping of such proposals.  ...  This work has been supported by the Max Planck Center for Visual Computing and Communication. The authors thank Varvara Obolonchykova and Bahar Tarakameh for their help in creating the video dataset.  ... 
arXiv:1612.01465v3 fatcat:ma6xy6jzxnc7hgqo6g4y3gkpvm

An Appearance-Based Tracking Algorithm for Aerial Search and Rescue Purposes

Abdulla Al-Kaff, María Gómez-Silva, Francisco Moreno, Arturo de la Escalera, José Armingol
2019 Sensors  
The automation of the Wilderness Search and Rescue (WiSAR) task aims for high levels of understanding of various scenery.  ...  of the point of view with respect to the target objects.  ...  Acknowledgments: This research is supported by Madrid Community project SEGVAUTO 4.0 P2018/EMT-4362) and by the Spanish Government CICYT projects ( TRA2015-63708-R and TRA2016-78886-C3-1-R), and Ministerio  ... 
doi:10.3390/s19030652 fatcat:435allfrvfcrzpqs5h55qjyhje

Global-Local Context Network for Person Search [article]

Peng Zheng, Jie Qin, Yichao Yan, Shengcai Liao, Bingbing Ni, Xiaogang Cheng, Ling Shao
2021 arXiv   pre-print
Specifically, re-ID embeddings and context features are enhanced simultaneously in a multi-stage fashion, ultimately leading to enhanced, discriminative features for person search.  ...  Our source codes, pre-trained models, and the new setting for character search are available at: https://github.com/ZhengPeng7/GLCNet.  ...  Joint person object- Yang, Zach DeVito, Martin Raison, Alykhan Tejani, ness and repulsion for person search. IEEE Trans.  ... 
arXiv:2112.02500v1 fatcat:zsx6j54ulra7bnt7zgtsytwywq
« Previous Showing results 1 — 15 out of 6,764 results