计算机科学
人工智能
计算机视觉
分割
对象(语法)
图像分割
冗余(工程)
视频跟踪
水准点(测量)
模式识别(心理学)
大地测量学
地理
操作系统
作者
Bo Miao,Mohammed Bennamoun,Yongsheng Gao,Ajmal Mian
出处
期刊:IEEE transactions on image processing
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:33: 2639-2651
标识
DOI:10.1109/tip.2024.3381445
摘要
Current semi-supervised video object segmentation (VOS) methods often employ the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we introduce a Region Aware Video Object Segmentation (RAVOS) approach, which predicts regions of interest (ROIs) for efficient object segmentation and memory storage. RAVOS includes a fast object motion tracker to predict object ROIs in the next frame. For efficient segmentation, object features are extracted based on the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects. In addition to RAVOS, we also propose a large-scale occluded VOS dataset, dubbed OVOS, to benchmark the performance of VOS models under occlusions. Evaluation on DAVIS and YouTube-VOS benchmarks and our new OVOS dataset show that our method achieves state-of-the-art performance with significantly faster inference time, e.g., 86.1 J & F at 42 FPS on DAVIS and 84.4 J & F at 23 FPS on YouTube-VOS. Project page: ravos.netlify.app.
科研通智能强力驱动
Strongly Powered by AbleSci AI