arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.04573cs.CV
收藏

基于掩码传播的视频目标分类、分割和跟踪

Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation

Facebook AI(脸书人工智能研究院)

Gedas Bertasius, Lorenzo Torresani

摘要:

我们介绍了一种方法,同时分类,分割和跟踪对象实例的视频序列。我们的方法名为MaskProp,通过添加掩码传播分支将流行的Mask R-CNN适应视频,该分支将帧级对象实例掩码从每个视频帧传播到视频剪辑中的所有其他帧。这使得我们的系统能够预测剪辑级实例轨道相对于对象实例分割在中间帧的剪辑。剪辑级实例轨道生成密集的序列中的每一帧,最后聚合产生视频级对象的实例分割和分类。我们的实验表明,我们的剪辑级实例分割,使我们的方法在视频中的运动模糊和对象遮挡鲁棒。MaskProp在YouTube-VIS数据集上实现了最佳报告准确性,优于ICCV 2019年视频实例分割挑战赛冠军,尽管它更简单,使用的标记数据数量级更少(130万与1B图像和860 K与14 M边界框)。

英文摘要:

We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence. Our method, named MaskProp, adapts the popular Mask R-CNN to video by adding a mask propagation branch that propagates frame-level object instance masks from each video frame to all the other frames in a video clip. This allows our system to predict clip-level instance tracks with respect to the object instances segmented in the middle frame of the clip. Clip-level instance tracks generated densely for each frame in the sequence are finally aggregated to produce video-level object instance segmentation and classification. Our experiments demonstrate that our clip-level instance segmentation makes our approach robust to motion blur and object occlusions in video. MaskProp achieves the best reported accuracy on the YouTube-VIS dataset, outperforming the ICCV 2019 video instance segmentation challenge winner despite being much simpler and using orders of magnitude less labeled data (1.3M vs 1B images and 860K vs 14M bounding boxes).

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。

↑