Images of Balls Transported on a Conveyor Belt - Recording 4
收藏资源简介：
This data set comprises images of balls on a conveyor belt. The images were recorded on the small-scale optical belt sorter Tablesort. A thorough description of the Tablesort system can be found in <em>Georg Maier, Florian Pfaff, Christoph Pieper, Robin Gruna, Benjamin Noack, Harald Kruggel-Emden, Thomas Längle, Uwe D. Hanebeck, Jürgen Beyerer,</em> <strong>Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking</strong>, Transactions on Industrial Electronics, February 2020. See also the project website. This dataset is part of a batch of recordings on optical sorters. Please use the search function with the keyword "Tobias Hornberger" (in quotes) to find them or use the list at https://doi.org/10.5281/zenodo.5506551 (conveyor belt data sets only). The camera was recorded on a Bonito CL-400C. The calibration image for the extrinsic parameters can be found in calibration_extrinsics.png for the extrinsics and calibration_color.png for the color calibration. Please see the debayer script on GitHub<strong>.</strong> Each pixel is approximately 0.056 mm long in world coordinates. The frame rate is 192.9 Hz. Algorithms for two key challenges can be developed and evaluated on the data sets: Multitarget tracking for predicting the particle’s motion. This can be used to enhance the separation of optical sorters. For further details on this, see the publications <em>Florian Pfaff, Marcus Baum, Benjamin Noack, Uwe D. Hanebeck, Robin Gruna, Thomas Längle, Jürgen Beyerer,</em><br> <strong>TrackSort: Predictive Tracking for Sorting Uncooperative Bulk Materials,</strong><br> Proceedings of the 2015 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2015), San Diego, California, USA, September 2015. <em>Florian Pfaff, Christoph Pieper, Georg Maier, Benjamin Noack, Robin Gruna, Harald Kruggel-Emden, Uwe D. Hanebeck, Siegmar Wirtz, Viktor Scherer, Thomas Längle, Jürgen Beyerer,</em><br> <strong>Predictive Tracking with Improved Motion Models for Optical Belt Sorting</strong>,<br> at – Automatisierungstechnik, April 2020. Classification of particles. The classification may use a multitarget tracker to accumulate visual features over time. One can also use the information on the trajectory to classify the particles. For information on this, refer to <em>Georg Maier, Florian Pfaff, Florian Becker, Christoph Pieper, Robin Gruna, Benjamin Noack, Harald Kruggel-Emden, Thomas Längle, Uwe D. Hanebeck, Siegmar Wirtz, Viktor Scherer, Jürgen Beyerer,</em><br> <strong>Improving Material Characterization in Sensor-Based Sorting by Utilizing Motion Information,</strong><br> Proceedings of the 3rd Conference on Optical Characterization of Materials (OCM 2017), Karlsruhe, Germany, March 2017. <em>Georg Maier, Florian Pfaff, Florian Becker, Christoph Pieper, Robin Gruna, Benjamin Noack, Harald Kruggel-Emden, Thomas Längle, Uwe D. Hanebeck, Siegmar Wirtz, Viktor Scherer, Jürgen Beyerer,</em><br> <strong>Motion-Based Material Characterization in Sensor-Based Sorting,</strong> <br> tm – Technisches Messen, De Gruyter, October 2017. <br> To this date, publications that used these data include <em>Daniel Pollithy, Marcel Reith-Braun, Florian Pfaff, Uwe D. Hanebeck,</em><br> <strong>Estimating Uncertainties of Recurrent Neural Networks in Application to Multitarget Tracking</strong>,<br> Proceedings of the 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2020), Virtual, September 2020. CSV-files with already associated particle tracks are available at https://doi.org/10.5281/zenodo.5506551. <strong>Acknowledgment</strong> The IGF project 20354 N of the research association Forschungs-Gesellschaft Verfahrens-Technik e.V. (GVT) was supported via the AiF in a program to promote the Industrial Community Research and Development (IGF) by the Federal Ministry for Economic Affairs and Energy on the basis of a resolution of the German Bundestag.
本数据集包含传送带上物料球的图像，所有图像均由小型光学带式分选机Tablesort采集录制。关于Tablesort系统的详细说明可参阅以下文献：Georg Maier、Florian Pfaff、Christoph Pieper、Robin Gruna、Benjamin Noack、Harald Kruggel-Emden、Thomas Längle、Uwe D. Hanebeck、Jürgen Beyerer，《面向预测性实时多目标跟踪的新型传感器分选方法的实验评估》，《工业电子汇刊》，2020年2月。此外可访问项目官网获取更多信息。 本数据集属于光学分选机录制数据集批次的一部分。可通过搜索关键词"Tobias Hornberger"（需加引号）检索相关数据集，或访问https://doi.org/10.5281/zenodo.5506551获取仅包含传送带数据集的列表。 本次采集使用的相机为Bonito CL-400C。外参标定图像可参见calibration_extrinsics.png，色彩标定图像可参见calibration_color.png。相关去拜耳化脚本可在GitHub平台获取。在世界坐标系下，每个像素对应实际长度约为0.056 mm。图像帧率为192.9 Hz。 本数据集可用于开发并评估两类核心挑战的算法：一是预测物料运动的多目标跟踪算法，该算法可用于提升光学分选机的分选性能。相关细节可参阅以下两篇文献： 1. Florian Pfaff、Marcus Baum、Benjamin Noack、Uwe D. Hanebeck、Robin Gruna、Thomas Längle、Jürgen Beyerer，《TrackSort：面向非合作散装物料分选的预测性跟踪》，2015年IEEE多传感器融合与智能系统国际会议（MFI 2015）论文集，美国加利福尼亚州圣地亚哥，2015年9月。 2. Florian Pfaff、Christoph Pieper、Georg Maier、Benjamin Noack、Robin Gruna、Harald Kruggel-Emden、Uwe D. Hanebeck、Siegmar Wirtz、Viktor Scherer、Thomas Längle、Jürgen Beyerer，《面向光学带式分选的改进运动模型预测性跟踪》，《Automatisierungstechnik（自动化技术）》，2020年4月。 二是物料分类算法。该分类任务可借助多目标跟踪器随时间累积视觉特征，也可利用物料轨迹信息完成分类。相关细节可参阅以下两篇文献： 1. Georg Maier、Florian Pfaff、Florian Becker、Christoph Pieper、Robin Gruna、Benjamin Noack、Harald Kruggel-Emden、Thomas Längle、Uwe D. Hanebeck、Siegmar Wirtz、Viktor Scherer、Jürgen Beyerer，《基于运动信息的传感器分选物料特性表征优化》，第三届材料光学表征会议（OCM 2017）论文集，德国卡尔斯鲁厄，2017年3月。 2. Georg Maier、Florian Pfaff、Florian Becker、Christoph Pieper、Robin Gruna、Benjamin Noack、Harald Kruggel-Emden、Thomas Längle、Uwe D. Hanebeck、Siegmar Wirtz、Viktor Scherer、Jürgen Beyerer，《传感器分选场景下基于运动的物料特性表征》，《tm – Technisches Messen（技术测量）》，De Gruyter出版社，2017年10月。 截至目前，使用本数据集的已发表文献包括：Daniel Pollithy、Marcel Reith-Braun、Florian Pfaff、Uwe D. Hanebeck，《循环神经网络在多目标跟踪任务中的不确定性估计》，2020年IEEE多传感器融合与智能系统国际会议（MFI 2020）论文集，虚拟会议，2020年9月。已完成轨迹关联的粒子跟踪CSV文件可访问https://doi.org/10.5281/zenodo.5506551获取。 **致谢** 德国流程技术研究协会（Forschungs-Gesellschaft Verfahrens-Technik e.V.，简称GVT）的IGF项目20354 N由联邦经济事务与能源部基于德国联邦议院决议，通过AiF的工业共同体研究与发展（IGF）资助计划提供支持。
