Saliency detection with moving camera via background model completion

TL;DR

This paper introduces a novel saliency detection framework for videos captured by moving cameras, utilizing background model completion and deep learning segmentation to improve accuracy in complex scenes.

Contribution

It is the first to apply video completion for background modeling and saliency detection in moving camera videos, enhancing robustness and accuracy.

Findings

Outperforms deep learning background subtraction models by over 11%.

Achieves more than 3% improvement over high-ranking background subtraction methods on challenging videos.

Effectively handles dynamic backgrounds and camouflage scenarios.

Abstract

To detect saliency in video is a fundamental step in many computer vision systems. Saliency is the significant target(s) in the video. The object of interest is further analyzed for high-level applications. The segregation of saliency and the background can be made if they exhibit different visual cues. Therefore, saliency detection is often formulated as background subtraction. However, saliency detection is challenging. For instance, dynamic background can result in false positive errors. In another scenario, camouflage will lead to false negative errors. With moving camera, the captured scenes are even more complicated to handle. We propose a new framework, called saliency detection via background model completion (SD-BMC), that comprises of a background modeler and the deep learning background/foreground segmentation network. The background modeler generates an initial clean background image from a short image sequence. Based on the idea of video completion, a good background frame can be synthesized with the co-existence of changing background and moving objects. We adopt the background/foreground segmenter, although pre-trained with a specific video dataset, can also detect saliency in unseen videos. The background modeler can adjust the background image dynamically when the background/foreground segmenter output deteriorates during processing of a long video. To the best of our knowledge, our framework is the first one to adopt video completion for background modeling and saliency detection in videos captured by moving camera. The results, obtained from the PTZ videos, show that our proposed framework outperforms some deep learning-based background subtraction models by 11% or more. With more challenging videos, our framework also outperforms many high ranking background subtraction methods by more than 3%.