首页|New Robotics Findings from National Taiwan University of Science and Technology Described (Road Anomaly Detection with Unknown Scenes Using DifferNet-Based Auto matic Labeling Segmentation)
New Robotics Findings from National Taiwan University of Science and Technology Described (Road Anomaly Detection with Unknown Scenes Using DifferNet-Based Auto matic Labeling Segmentation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ro botics. According to news reporting from Taipei, Taiwan, by NewsRx journalists, research stated, "Obstacle avoidance is essential for the effective operation of autonomous mobile robots, enabling them to detect and navigate around obstacles in their environment." Funders for this research include Ministry of Science And Technology, Taiwan. The news journalists obtained a quote from the research from National Taiwan Uni versity of Science and Technology: "While deep learning provides significant ben efits for autonomous navigation, it typically requires large, accurately labeled datasets, making the data's preparation and processing time-consuming and labor -intensive. To address this challenge, this study introduces atransfer learning (TL)-based automatic labeling segmentation (ALS) framework. This framework util izes a pretrained attention-based network, DifferNet, to efficiently perform sem antic segmentation tasks on new, unlabeled datasets. DifferNet leverages prior k nowledge from the Cityscapes dataset to identify high-entropy areas as road obst acles by analyzing differences between the input and resynthesized images. The r esulting road anomaly map was refined using depth information to produce a robus t drivable area and map of road anomalies. Several off-the-shelf RGB-D semantic segmentation neural networks were trained using pseudo-labels generated by the A LS framework, with validation conducted on the GMRPD dataset."
National Taiwan University of Science an d TechnologyTaipeiTaiwanAsiaEmerging TechnologiesMachine LearningNan o-robotRobotics
NETL
NSTL
