{"title":"Manifold ranking-based kernel propagation for saliency estimation","authors":"Meng Jian, Lifang Wu, Xiangyin Zhang, Yonghao He","doi":"10.1109/ICCAR.2018.8384712","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384712","url":null,"abstract":"Saliency estimation becomes a hot research topic due to its wide and successful application in almost all vision related problems. However, it is still far from satisfactory in saliency estimation techniques due to the complex visual content and various requirements. In this paper, we propose a manifold ranking based kernel propagation (MRKP) approach for visual saliency estimation. MRKP begins to work on background seeds for manifold ranking on four image boundaries individually and select representative salient seeds. Pairwise constraints of must-link and cannot-link are formed with the boundary background seeds and selected salient seeds. Then, pairwise constraints guided saliency seed kernel learning and saliency kernel propagation are sequentially conducted in MRKP to estimate visual saliency of images. Experimental results demonstrate that the proposed MRKP has a good ability of learning discriminative kernel structure for saliency estimation.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116148278","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}
{"title":"Rotation correction for license plate recognition","authors":"P. Li, M. Nguyen, W. Yan","doi":"10.1109/ICCAR.2018.8384708","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384708","url":null,"abstract":"The license plate recognition (LPR) is always in operation with the needs of both quantity-and-quality-based approaches. The entire procedure of license plate recognition consists of six steps: image acquisition, image processing, plate locating, character segmentation, character recognition, result output. In real instances of license plate recognition, when a road is uneven with bends, a vehicle will be running with shaky. Consequently, the plate is also unstable and tilted with rotations. Generally, because a surveillance camera is fixed to capture a high-quality image, the plate is hard to be located and recognized. Due to these existing problems, the contributions of this paper are (1) rotation correction for license plate using Hough transform; (2) GNN (Genetic neural network)-based license plate recognition. The novelty of this paper is to recognize a license plate through rotation correction, especially when the border of this plate is not available. Therefore, we detect the straight lines passing through the top and bottom edges of the plate characters and treat them as the border lines. Our experimental results show the proposed method is robust and reliable in LPR correction and recognition.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130703624","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}
{"title":"ROS based service robot platform","authors":"Ruchik Mishra, A. Javed","doi":"10.1109/ICCAR.2018.8384644","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384644","url":null,"abstract":"The substitution of a human factor by an affordable low-cost robotic system has been increasing recently. The reason being, the robot is expected to do less errors than a human does and does not have a will of its own. This paper proposes a service robot platform that is capable of mapping, localizing itself and navigating in an indoor environment and is best suited for structured environment with static obstacles. The approach used for mapping is a ROS package which is a ROS wrapper of Real Time Appearance Based Mapping with the help of a low cost RGB-D camera, the Microsoft Kinect XBOX 360 with a turtlebot robot model for visualization. RTAB-Map takes into account loop closure in real time constraints with a memory management technique which makes the mapping process independent of time and size. Once the mapping is done and the 2D projection of the map is obtained of our real indoor environment of the lab, the simulation of the autonomous navigation of the robot model to the desired location is done on Gazebo. For the navigation to happen successfully, Adaptive Monte Carlo Localization is used for localizing the turtlebot model in the map. The simulation results were visualized using rviz and were found to be satisfactory.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131930038","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}
{"title":"Comprehensive evaluation of the performance of rescue robots using victim robots","authors":"Daniel Jeswin Nallathambi","doi":"10.1109/ICCAR.2018.8384645","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384645","url":null,"abstract":"With the explosion of applications for robots in the modern world, robots are becoming pervasive and are finding use in almost every field. Robots find applications in a variety of fields and recently have entered the field of search and rescue as well. With increasing occurrences of both man-made and natural disasters, robots may soon prove to be indispensable in this field. However, usage of robots for rescue operations requires them to be tested against exacting safety standards and requirements as their handling of victims should not worsen their condition. Therefore, a comprehensive testing strategy that can evaluate various aspects of the performance of the rescue robot is required. In this paper, one such strategy using robots to mimic victims of a disaster is discussed.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133887524","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}
{"title":"NURBS based trajectory generation for an industrial five axis needle winding robot","authors":"P. Herrmann, Martin Gerngross, C. Endisch","doi":"10.1109/ICCAR.2018.8384640","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384640","url":null,"abstract":"The needle winding technology is a promising alternative for the future production of electrical machines with distributed windings especially in the automotive environment. With its high flexibility and potential for full automation it is well suited to meet the demands of manufacturers for innovative production methods stemming from electrified mobility. Needle winding machines in their different kinematic versions are comparable to multi axes robots or NC machines. The trajectory of the needle is a major factor influencing the winding and therefore quality, efficiency and cost of the resulting electric machine. State of the art for the trajectory programming for needle winding machines is either point to point interpolation or the usage of cam disks. To improve the winding results and flexibility, a smooth trajectory planning algorithm was investigated. Beginning from an optimal winding pattern in the stator slots, the path and trajectory planning algorithm was presented.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133154498","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}
{"title":"Multi-robotic arms automated production line","authors":"Jeng-Dao Lee, Wei-Chuan Li, Jyun-Han Shen, Ching-Wei Chuang","doi":"10.1109/ICCAR.2018.8384639","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384639","url":null,"abstract":"In response to the booming industrial automation, three commonly used industrial robots including one parallel type robot, one gantry type robot, and two six-axis serial robots will be self-developed in this study. The six-axis robot arm can be controlled by using Kinematics method. Furthermore, a fifth-order-polynomials method is used to limit accelerations and velocity on each joint to achieve continuity. Arc path of the robotic arm can be achieved by the three-points-arc interpolation. Therefore, trajectories for gluing path planning will be successfully generated. Moreover, vision devices are used to inspect the work pieces after the laser engraving. In addition, the storage system provides storage of unassembled and finished workpieces. Finally, the system integration of all equipment will be completed to achieve a customized multifunction gluing and assembly line by self-developed robotic arms.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121237882","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}
{"title":"Design of automatic assembly system for rectifier","authors":"Meng Xu, Ming-xing Lin, Zhen Wang, Xiaojun Ju, Xiaojian Wu","doi":"10.1109/ICCAR.2018.8384656","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384656","url":null,"abstract":"In order to change current situation (most of bending is made by manual bending or universal bending machine for several steps) in the assembly and bending steps of the rectifier. In this paper, according to the characteristics of rectifier assembly, the assembly process requirements are analyzed. An assembly system which can be accomplished through the linear reciprocating motion of a single spindle is designed for the bending and leveling of rectifier copper plates. The design and motion control of each part of the system are described. Finally, ANSYS is used to analyze the key parts of the system to verify its reliability. This system is suitable for assembly operation with bending process, which can improve assembly efficiency and assembly quality.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131947973","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}
{"title":"Flame detection using deep learning","authors":"D. Shen, Xin Chen, M. Nguyen, W. Yan","doi":"10.1109/ICCAR.2018.8384711","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384711","url":null,"abstract":"Flame detection is an increasingly important issue in intelligent surveillance. In fire flame detection, we need to extract visual features from video frames for training and test. Based on them, a group of shallow learning models have been developed to detect flames, such as color-based model, fuzzy-based model, motion and shape-based model, etc. Deep learning is a novel method which could be much efficient and accurate in flame detection. In this paper, we use YOLO model to implement flame detection and compare it with those shallow learning methods so as to determine the most efficient one for flame detection. Our contribution of this paper is to make use of the optimized YOLO model for flame detection from video frames. We collected the dataset and trained them using Google platform TensorFlow, the obtained accuracy of our proposed flame detection is up to 76%.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115662320","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}
{"title":"Demand-based dimensioning of compressed air systems for energy optimization and flexibility","authors":"T. Javied, Florian Kimmig, J. Franke","doi":"10.1109/ICCAR.2018.8384726","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384726","url":null,"abstract":"Due to high energy prices in Germany, manufacturing companies have an incentive to increase energy efficiency in production. Compressed air systems (CAS) offer high energy savings potentials. Studies show that CAS are poorly dimensioned in most cases. This paper describes the energy saving potential of compressed air systems. Additionally the importance of not only energy efficiency but energy flexibility is considered. To optimize the current systems and to determine need-based determination of CAS, a Software-tool was developed based on visual basic for application and MS Access. This tool is described in this paper. Different studies estimate a savings potentials due to efficient dimensioning at more than 15%. The described tool helps users identify their energy saving and flexibility potential and suggests CAS configuration to utilize the given potential. It illustrates different investment scenarios based on user-specific requirements. Users can evaluate alternatives that suit their needs based on different KPIs. This tool is designed for SMEs in order to allow them to analyze their CAS without requiring costly external consultation. Energy flexible CAS can enable users to Buy energy at lower costs and use it when prices are high. A smart factory can manage these control challenges independently and utilize the form of energy which is situationally most favorable. Thereby, both economical advantage and energy flexibility can be ensured.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133617048","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}
{"title":"Analysis of using an active artificial spine in a quadruped robot","authors":"D. Kuehn, A. Dettmann, F. Kirchner, F. Kirchner","doi":"10.1109/ICCAR.2018.8384641","DOIUrl":"https://doi.org/10.1109/ICCAR.2018.8384641","url":null,"abstract":"With increasing mechanization of our daily lives, the expectations and demands in robotic systems increase in the general public and in scientists alike. Especially disaster scenarios shows that the robotic systems not only have to face a variety of different tasks during operation but also have to deal with different demands regarding the robot's mobility characteristics. To be able to cope with future requirements, it seems necessary to develop kinematically complex systems that feature several operating modes. Often disregarded in robotics, yet extensively used in nature, are the degrees of freedom introduced by the spine. This paper presents the latest work on the hominid robot Charlie, whose morphology is oriented on chimpanzees and which has the possibility due to its electromechanical structure and the degrees of freedom to walk with different gaits in different postures. Besides its degrees of freedom in its limbs, the robot features an active artificial spine, equipped with sensors in the structure to allow a dual use; both as a structural part as well as a 6-DoF force/torque sensor. This paper analyses the benefits of an active spine experimentally. The results show, that the exploration of the range of motion is improved and that less requirements on joint velocities are lowered.","PeriodicalId":106624,"journal":{"name":"2018 4th International Conference on Control, Automation and Robotics (ICCAR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372690","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}