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 2008.00948cs.CVcs.LG
收藏

帧间一致的语义分割

Frame-To-Frame Consistent Semantic Segmentation

Graz University of Technology(格拉茨技术大学)

Manuel Rebol, Patrick Knöbelreiter

摘要:

在这项工作中,我们的目标是时间上一致的语义分割在整个视频帧。许多语义分割算法单独地处理图像,这导致由于照明变化、遮挡和其他随时间的变化而导致不一致的场景解释。为了实现时间上一致的预测,我们训练卷积神经网络(CNN),其使用卷积长短期记忆(ConvLSTM)单元通过视频中的连续帧传播特征。除了时间特征传播之外,我们还在损失函数中惩罚不一致。我们在实验中表明,与单帧预测相比,利用视频信息时的性能有所提高。Cityscapes验证集上的平均交集(mIoU)度量从单帧的45.2%增加到视频数据的57.9%,这是在实现ConvLSTM以在ESPNet上通过时间传播特征之后。最重要的是,不一致性从4.5%下降到1.3%,减少了71.1%。我们的研究结果表明,增加的时间信息产生一个帧到帧的一致性和更准确的图像理解相比,单帧处理。代码和视频可在https://github.com/mrebol/f2f-consistent-semantic-segmentation上获得

英文摘要:

In this work, we aim for temporally consistent semantic segmentation throughout frames in a video. Many semantic segmentation algorithms process images individually which leads to an inconsistent scene interpretation due to illumination changes, occlusions and other variations over time. To achieve a temporally consistent prediction, we train a convolutional neural network (CNN) which propagates features through consecutive frames in a video using a convolutional long short term memory (ConvLSTM) cell. Besides the temporal feature propagation, we penalize inconsistencies in our loss function. We show in our experiments that the performance improves when utilizing video information compared to single frame prediction. The mean intersection over union (mIoU) metric on the Cityscapes validation set increases from 45.2 % for the single frames to 57.9 % for video data after implementing the ConvLSTM to propagate features trough time on the ESPNet. Most importantly, inconsistency decreases from 4.5 % to 1.3 % which is a reduction by 71.1 %. Our results indicate that the added temporal information produces a frame-to-frame consistent and more accurate image understanding compared to single frame processing. Code and videos are available at https://github.com/mrebol/f2f-consistent-semantic-segmentation

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。

↑