{"title":"基于估计姿态和遮挡误差的目标硬样本合成改进的目标姿态估计","authors":"Alan Li;Angela P. Schoellig","doi":"10.1109/LRA.2024.3520436","DOIUrl":null,"url":null,"abstract":"6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where objects may be textureless and in difficult poses, and occlusion between objects of the same type may cause confusion even in well-trained models. We propose a novel method of hard example synthesis that is model-agnostic, using existing simulators and the modeling of pose error in both the camera-to-object viewsphere and occlusion space. Through evaluation of the model performance with respect to the distribution of object poses and occlusions, we discover regions of high error and generate realistic training samples to specifically target these regions. With our training approach, we demonstrate an improvement in correct detection rate of up to 20% across several ROBI-dataset objects using state-of-the-art pose estimation models.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"1281-1288"},"PeriodicalIF":4.6000,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation\",\"authors\":\"Alan Li;Angela P. Schoellig\",\"doi\":\"10.1109/LRA.2024.3520436\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where objects may be textureless and in difficult poses, and occlusion between objects of the same type may cause confusion even in well-trained models. We propose a novel method of hard example synthesis that is model-agnostic, using existing simulators and the modeling of pose error in both the camera-to-object viewsphere and occlusion space. Through evaluation of the model performance with respect to the distribution of object poses and occlusions, we discover regions of high error and generate realistic training samples to specifically target these regions. With our training approach, we demonstrate an improvement in correct detection rate of up to 20% across several ROBI-dataset objects using state-of-the-art pose estimation models.\",\"PeriodicalId\":13241,\"journal\":{\"name\":\"IEEE Robotics and Automation Letters\",\"volume\":\"10 2\",\"pages\":\"1281-1288\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Robotics and Automation Letters\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10810662/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ROBOTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Robotics and Automation Letters","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10810662/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}
Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation
6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where objects may be textureless and in difficult poses, and occlusion between objects of the same type may cause confusion even in well-trained models. We propose a novel method of hard example synthesis that is model-agnostic, using existing simulators and the modeling of pose error in both the camera-to-object viewsphere and occlusion space. Through evaluation of the model performance with respect to the distribution of object poses and occlusions, we discover regions of high error and generate realistic training samples to specifically target these regions. With our training approach, we demonstrate an improvement in correct detection rate of up to 20% across several ROBI-dataset objects using state-of-the-art pose estimation models.
期刊介绍:
The scope of this journal is to publish peer-reviewed articles that provide a timely and concise account of innovative research ideas and application results, reporting significant theoretical findings and application case studies in areas of robotics and automation.