Filters








5,135 Hits in 3.7 sec

Iterative Visual Recognition for Learning Based Randomized Bin-Picking [article]

Kensuke Harada, Weiwei Wan, Tokuo Tsuji, Kohei Kikuchi, Kazuyuki Nagata, Hiromu Onda
2016 arXiv   pre-print
This paper proposes a iterative visual recognition system for learning based randomized bin-picking.  ...  detecting the poses of objects just by using a part of visual image taken at the current picking trial where it is different from the visual image taken at the previous picking trial.  ...  Conclusions In this paper, we discussed the visual recognition system for learning based randomized bin-picking.  ... 
arXiv:1608.00334v1 fatcat:rkd57sbn5ve5noot6vg7vayu7y

Experiments on learning-based industrial bin-picking with iterative visual recognition

Kensuke Harada, Weiwei Wan, Tokuo Tsuji, Kohei Kikuchi, Kazuyuki Nagata, Hiromu Onda
2018 Industrial robot  
This paper shows experimental results on learning based randomized bin-picking combined with iterative visual recognition.  ...  We use the random forest to predict whether or not a robot will successfully pick an object for given depth images of the pile taking the collision between a finger and a neighboring object into account  ...  Learning Based Bin-Picking This section explains our learning based randomized bin-picking (Harada, 2016a) .  ... 
doi:10.1108/ir-01-2018-0013 fatcat:zrtyrotmnzdvzkqydlbk3ulbau

Prediction of the configuration of objects in a bin based on synthetic sensor data

Shan Fur, Bilel Boughattas, Alexander Verl, Andreas Pott
2020 Procedia CIRP  
Abstract Bin picking describes a robot system that picks unsorted objects from a bin based on sensor data. The object recognition is one of the main difficulties when calculating the grasping pose.  ...  Abstract Bin picking describes a robot system that picks unsorted objects from a bin based on sensor data. The object recognition is one of the main difficulties when calculating the grasping pose.  ...  Acknowledgements The authors would like to thank the German State Ministry of Baden-Wuerttemberg for Sciences, Research and Arts and the German Research Foundation (DFG) for financial support of the preparatory  ... 
doi:10.1016/j.procir.2020.05.010 fatcat:fagv4nibxzbkldhxxt5xatpls4

Fast Object Pose Estimation Using Adaptive Threshold for Bin-picking

Wu Yan, Zhihao Xu, Zhihao Xu, XueFeng Zhou, Qianxin Su, Shuai Li, Hongmin Wu
2020 IEEE Access  
INDEX TERMS Robotic bin-picking, learning-based pose estimation, adaptive threshold, point pair features, multilayer segmentation, 3D sensing.  ...  fast objects pose estimation and can be applied to robotic random bin-picking tasks.  ...  CONCLUSION AND FUTURE WORK This paper proposes a CAD-based 6-DoF pose estimation pipeline for robotic random bin-picking tasks using the 3D camera.  ... 
doi:10.1109/access.2020.2983173 fatcat:qsj7bh5nofhlfox6xy2bjycokq

Depth Image–Based Deep Learning of Grasp Planning for Textureless Planar-Faced Objects in Vision-Guided Robotic Bin-Picking

Ping Jiang, Yoshiyuki Ishihara, Nobukatsu Sugiyama, Junji Oaki, Seiji Tokura, Atsushi Sugahara, Akihito Ogawa
2020 Sensors  
In this paper, we propose a novel depth image–based vision-guided robot bin-picking system for textureless planar-faced objects.  ...  Bin-picking of small parcels and other textureless planar-faced objects is a common task at warehouses.  ...  Benefits of Depth-Image-Based Visual-Guided Bin-Picking System One benefit of a depth-image-based visually guided bin-picking system is that it does not require texture features, which are sensitive to  ... 
doi:10.3390/s20030706 pmid:32012874 pmcid:PMC7038393 fatcat:kw4amlhmxbbvfo7um2calp54oa

Learning Based Industrial Bin-picking Trained with Approximate Physics Simulator

Ryo Matsumura, Kensuke Harada, Yukiyasu Domae, Weiwei Wan
2018 arXiv   pre-print
Since complex physical phenomena of contact among objects and fingers makes it difficult to perform the bin-picking with high success rate, we consider introducing a learning based approach.  ...  In this paper, we first formulate the learning based robotic bin-picking by using CNN (Convolutional Neural Network). We also obtain the optimum grasping posture of parallel jaw gripper by using CNN.  ...  LEARNING BASED APPROACH This section explains our learning based approach for randomized bin-picking introduced in this research. A.  ... 
arXiv:1805.08936v1 fatcat:otl2vup4ozbshjb34thbylp6ny

Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter [article]

Quanquan Shao, Jie Hu, Weiming Wang, Yi Fang, Wenhai Liu, Jin Qi, Jin Ma
2019 arXiv   pre-print
And it makes robotic picking system learn picking skills from scratch. At the same time, we train the network end to end with online samples.  ...  Because of the diversity of poses, types of stack and complicated background in bin picking situation, it is much difficult to recognize and estimate their pose before grasping them.  ...  ACKNOWLEDGMENT This research is supported by Special Program for Innovation Method of the Ministry of Science and Technology.  ... 
arXiv:1904.07402v2 fatcat:g2qw5p3luzh2thc6krseqqiupe

Latent-Class Hough Forests for 6 DoF Object Pose Estimation [article]

Rigas Kouskouridas, Alykhan Tejani, Andreas Doumanoglou, Danhang Tang, Tae-Kyun Kim
2016 arXiv   pre-print
We adapt a state of the art template matching feature into a scale-invariant patch descriptor and integrate it into a regression forest using a novel template-based split function.  ...  In this paper we present Latent-Class Hough Forests, a method for object detection and 6 DoF pose estimation in heavily cluttered and occluded scenarios.  ...  Patches 2/3, use a forest of 10 trees and set the number of iterations to were sampled from the negative data, pushed through the 10, while for our Bin-picking Dataset, we investigate  ... 
arXiv:1602.01464v1 fatcat:osbaggxogbhdlkrvh4yu7ls5uy

Learning context for collective activity recognition

Wongun Choi, Khuram Shahid, Silvio Savarese
2011 CVPR 2011  
In this paper we present a framework for the recognition of collective human activities.  ...  Our scheme is constructed upon a Random Forest structure which randomly samples variable volume spatio-temporal regions to pick the most discriminating attributes for classification.  ...  We perform the estimation using Gibbs Sampling (with 500 iterations for burn-in and 1000 iterations for sampling).  ... 
doi:10.1109/cvpr.2011.5995707 dblp:conf/cvpr/ChoiSS11 fatcat:jxffxuaohndf3bqeralszik4ti

A 2D-3D Hybrid Vision System For Robotic Manipulation Of Randomly Oriented Objects

Moulay A. Akhloufi
2012 Zenodo  
The extracted 3D pose is then sent to the robot manipulator for picking. The tests show that the proposed system achieves high performances  ...  This paper presents an new vision technique for robotic manipulation of randomly oriented objects in industrial applications.  ...  This is done for each object to manipulate, making the random bin picking a timeconsuming task.  ... 
doi:10.5281/zenodo.1073041 fatcat:bgfasw4cdfboxfyv5refn3pbkq

3D Object Segmentation for Shelf Bin Picking by Humanoid with Deep Learning and Occupancy Voxel Grid Map [article]

Kentaro Wada, Masaki Murooka, Kei Okada, Masayuki Inaba
2020 arXiv   pre-print
We evaluated the method with the picking task experiment for target objects in narrow shelf bins.  ...  Picking objects in a narrow space such as shelf bins is an important task for humanoid to extract target object from environment.  ...  If the voxels for target object are generated with this recognition stage, the picking motion of humanoid robot to the object is generated based on depth value of the centroid of computed from the generated  ... 
arXiv:2001.05406v2 fatcat:7soulr5wwfbe3p7htdse5fjrdy

Recovering 6D Object Pose: A Review and Multi-modal Analysis [chapter]

Caner Sahin, Tae-Kyun Kim
2019 Lecture Notes in Computer Science  
(iii) Template-based methods and random forest-based learning algorithms underlie object detection and 6D pose estimation.  ...  Recent paradigm is to learn deep discriminative feature representations and to adopt CNNs taking RGB images as input.  ...  Template-based vs. Random forest-based.  ... 
doi:10.1007/978-3-030-11024-6_2 fatcat:n5cmm5342fdsjae2ukkpvpfita

Recovering 6D Object Pose: A Review and Multi-modal Analysis [article]

Caner Sahin, Tae-Kyun Kim
2018 arXiv   pre-print
(iii) Template-based methods and random forest-based learning algorithms underlie object detection and 6D pose estimation.  ...  Recent paradigm is to learn deep discriminative feature representations and to adopt CNNs taking RGB images as input.  ...  Template-based vs. Random forest-based.  ... 
arXiv:1706.03285v2 fatcat:rh7277cwrnbsnjtgx2fvvgyqk4

Learning Sampling Policies for Domain Adaptation [article]

Yash Patel, Kashyap Chitta, Bhavan Jasani
2018 arXiv   pre-print
Our experiments show that learned sampling policies construct labeled sets that improve accuracies of visual classifiers over baselines.  ...  We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning.  ...  Introduction Dataset bias [1] is a well-known drawback of supervised approaches to visual recognition tasks.  ... 
arXiv:1805.07641v1 fatcat:hqo4md4fujfuxjfbhuyqyphnem

Supervised Learning and Codebook Optimization for Bag-of-Words Models

Mingyuan Jiu, Christian Wolf, Christophe Garcia, Atilla Baskurt
2012 Cognitive Computation  
This type of models is frequently used in visual recognition tasks like object class recognition or human action recognition.  ...  In this paper, we present a novel approach for supervised codebook learning and optimization for bag-ofwords models.  ...  perceptron (MLP) weights for class recognition.  ... 
doi:10.1007/s12559-012-9137-4 fatcat:l5mfsv7uxraj5lbdgtvqi5adsy
« Previous Showing results 1 — 15 out of 5,135 results