2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)最新文献_第5页

Bayesian tracking of multiple objects with vision and radar 基于视觉和雷达的多目标贝叶斯跟踪

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838788

Michael Hoy, Chaoqun Weng, Junsong Yuan, J. Dauwels

引用次数: 5

Improving human body part detection using deep learning and motion consistency 利用深度学习和运动一致性改进人体部位检测

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838651

M. Ramanathan, W. Yau, E. Teoh

{"title":"Improving human body part detection using deep learning and motion consistency","authors":"M. Ramanathan, W. Yau, E. Teoh","doi":"10.1109/ICARCV.2016.7838651","DOIUrl":"https://doi.org/10.1109/ICARCV.2016.7838651","url":null,"abstract":"Body part segmentation and detection in videos is a useful analysis for many computer vision tasks such as action recognition and video search. Conventional methods mainly focus on body part detection assuming upright posture of the human body. Recently, a body part detection framework was proposed to include non-upright postures. This method consists of 2 parts, initial segmentation and computation of body part likelihood score for each segment. In this paper, we propose improvements to this approach. Firstly, we propose a novel motion based body part segmentation using kinematic features to identify segments which undergo similar motion in the video based on a consistency or error measure. Secondly, we replace the Extreme Learning Machine classifier in the original work with deep learning to investigate it's performance. For accurate detection, deep learning requires a lot of training data and it has so far been used only in high resolution images. Here we apply deep learning for body part detection in low resolution cases. We conduct experiments to study and analyse the effect of the improvements proposed.","PeriodicalId":128828,"journal":{"name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123813789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning 通过设计特殊的基函数对环境的对称性进行积分，实现强化学习中的值函数逼近

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838691

Guo-fang Wang, Zhou Fang, Bo Li, Ping Li

{"title":"Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning","authors":"Guo-fang Wang, Zhou Fang, Bo Li, Ping Li","doi":"10.1109/ICARCV.2016.7838691","DOIUrl":"https://doi.org/10.1109/ICARCV.2016.7838691","url":null,"abstract":"Reinforcement learning (RL) is usually regarded as tabula rasa learning, and the agent needs to randomly explore the environment, so the time consuming and data inefficiency will hinder RL from the real application. In order to accelerate learning speed and improve data efficiency, in this paper we expand the symmetry definition from finite state space to infinite state space and then propose designing a special type of symmetric basis functions for value function approximation to integrate the prior knowledge of symmetry about the environment for large or even infinite state space. After that, as an example, this particular approximate structure is incorporated into the policy evaluation phase of Least-Square Policy Iteration (LSPI), which we call symmetric LSPI (S-LSPI) and the convergence property is analyzed. Simulation results of chain walk and inverted pendulum balancing demonstrate that in contrast with regular LSPI (R-LSPI), the convergence speed of S-LSPI increases greatly and the computational burden decreases significantly simultaneously. It can illustrate the use of symmetric basis functions to capture the property of symmetry very well, and as a case study, it shows the promise to integrate symmetry of environment into RL agent.","PeriodicalId":128828,"journal":{"name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121359955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Water levels forecast in Thailand: A case study of Chao Phraya river 泰国水位预测:以湄南河为例

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838716

Kitsuchart Pasupa, Siripen Jungjareantrat

{"title":"Water levels forecast in Thailand: A case study of Chao Phraya river","authors":"Kitsuchart Pasupa, Siripen Jungjareantrat","doi":"10.1109/ICARCV.2016.7838716","DOIUrl":"https://doi.org/10.1109/ICARCV.2016.7838716","url":null,"abstract":"It is always desirable to be able to manage level of water in river, dam, and reservoir. Models have been constructed for predicting the level of these bodies of water, and good models can help increase the effectiveness of water management. Presently, the model that is employed by the Hydrographic Department of the Royal Thai Navy for predicting the level of water in Chao Phraya river is a harmonic method of tidal modeling. This model can predict the overall trend well but with high individual prediction error. Many machine learning algorithms for making predictions have also been introduced in recent years. Therefore, it was attempted in this study to compare the prediction performance of several machine learning models to that of the Royal Thai Navys model. These models were the following: linear regression, kernel regression, support vector regression, k-nearest neighbors, and random forest. The data input into these models were water level time series data of past 24, 48, and 72 hours measured at the Royal Thai Navy headquarters station, Phra Chulachomklao Fort, thirteen other stations along the river, and the output were predictions for the next 24 hours. It was found that all of the machine learning techniques were able to achieve better performances than that of the harmonic method of tidal modeling. The support vector regression model with Radial basis function kernel and 72-hour past time series data yielded prediction results with the least errors, at 0.117 m and 0.116 m for the water levels at the Royal Thai Navy headquarters station and Phra Chulachomklao Fort, respectively.","PeriodicalId":128828,"journal":{"name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122387485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Indoor navigation assistance system for visually impaired people using multimodal technologies 使用多模式技术的视障人士室内导航辅助系统

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838771

T. Dao, Thanh-Hai Tran, Thi-Lan Le, Hai Vu, Viet-Tung Nguyen, Dang-Khoa Mac, Ngoc-Diep Do, Thanh-Thuy Pham

引用次数: 12

Research on controls of sub crawlers for climbing up stairs with LRF for rescue robots 基于LRF的救援机器人爬楼梯副履带控制研究

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838672

M. Hatano, Yuki Kitahara

{"title":"Research on controls of sub crawlers for climbing up stairs with LRF for rescue robots","authors":"M. Hatano, Yuki Kitahara","doi":"10.1109/ICARCV.2016.7838672","DOIUrl":"https://doi.org/10.1109/ICARCV.2016.7838672","url":null,"abstract":"This paper presents an autonomous control method for rescue robots climbing up stairs using LRF. In disaster areas caused by earthquakes, rescue robots are needed to find injured people from under broken buildings instead of rescue workers. Then, the robots require high skills to be controlled, because the robots are operated by remote controls with wireless cameras. Especially, in case of climbing up stairs to find victims, it is hard to recognize a depth between robots and steps for operators with wireless cameras. Then we have proposed the method to estimate slope angles of stairs using LRF and an angle control method for sub crawlers of rescue robots. Here, we try to develop the estimation system with small and low-cost sensors instead of commercial ranging sensors that are too large to be attached on rescue robots. In this paper, we present the validity of the proposed method for actual stairs in a building. First, we present a method for estimating a slope angle of stairs using LRF. Second, a selection method of measured points for an accurate estimation for the slope angle is considered. Third, it is shown that our constructed rescue robot estimates the angle of the slope and climbs up the actual stairs with controlling postures of the robot with sub crawlers.","PeriodicalId":128828,"journal":{"name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131250793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Reaction-diffusion based level set method with local entropy thresholding for melasma image segmentation 基于反应扩散的局部熵阈值水平集方法在黄褐斑图像分割中的应用

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838823

Xu Zhang, Yunfeng Liang, Dongyun Lin, Zhiping Lin, S. Thng, E. Y. Gan, E.Y. Tay

引用次数: 2

Model predictive control strategy for plug-in hybrid electric vehicles 插电式混合动力汽车模型预测控制策略

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838781

Yi-Min Hsieh, Yen‐Chen Liu

引用次数: 2

Visually servoed trajectory tracking of quadrotors with the kinematic model 基于运动学模型的四旋翼机视觉伺服轨迹跟踪

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838743

Penghong Lin, Kai Wang

引用次数: 1

Optimization of concentric-tube robot design for deep anterior brain tumor surgery 脑深部前路肿瘤手术同心管机器人的优化设计

2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV) Pub Date : 2016-11-01 DOI: 10.1109/ICARCV.2016.7838563

M. Boushaki, Chao Liu, B. Herman, V. Trévillot, M. Akkari, P. Poignet

引用次数: 9