arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.17023cs.CV
收藏

MF-MOS: 一种面向运动目标分割的运动聚焦模型

MF-MOS: A Motion-Focused Model for Moving Object Segmentation

South China Normal University(华南师范大学);Aberystwyth University(阿伯里斯特威斯大学);Hong Kong University of Science and Technology(香港科技大学);Jiangnan University(江南大学);National University of Defense Technology(国防科技大学);Tongji University(同济大学)

Jintao Cheng, Kang Zeng, Zhuoxu Huang, Xiaoyu Tang, Jin Wu, Chengxi Zhang, Xieyuanli Chen, Rui Fan

AI总结:

针对激光雷达运动目标分割任务,提出双分支结构的MF-MOS模型,分别从残差图提取运动特征、从距离图像生成语义引导,在SemanticKITTI数据集上取得76.7%的IoU,达到当前最优水平。

摘要:

运动目标分割(Moving object segmentation,MOS)为交通参与者检测提供了可靠的解决方案,因此在自动驾驶领域受到广泛关注。动态信息捕获始终是MOS问题中的关键环节。现有方法直接从距离图像中提取运动特征。与之不同,我们认为残差图在运动信息表征上具有更大潜力,而距离图像包含丰富的语义引导信息。基于这一思路,我们提出MF-MOS,一种针对激光雷达运动目标分割的新型运动聚焦双分支结构模型。该方法创新性地解耦时空信息:从残差图中提取运动特征,同时从距离图像中生成语义特征,作为运动分支的可移动目标引导。这种简洁且独特的方案能够充分利用距离图像与残差图的信息,从而大幅提升基于激光雷达的MOS任务性能。值得注意的是,提交时MF-MOS在SemanticKITTI数据集的MOS排行榜上取得了76.7%的领先IoU,展现了当前最优的性能表现。MF-MOS的实现代码已发布于https://github.com/SCNU-RISLAB/MF-MOS。

英文摘要:

Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑