Detecting Tiny Moving Vehicles in Satellite Videos
This addresses a new computer vision task for satellite video analysis, enabling efficient detection of small vehicles in city-scale scenes, which is incremental as it builds on existing detection methods but adapts them to a specific domain challenge.
The paper tackles the problem of detecting tiny moving vehicles in satellite videos, where targets are only a few pixels and background noise is significant due to satellite motion, and proposes a novel detection algorithm based on local noise modeling and multi-morphological-cue discrimination, achieving advantages over state-of-the-art baselines as demonstrated through manual annotation and systematic evaluation.
In recent years, the satellite videos have been captured by a moving satellite platform. In contrast to consumer, movie, and common surveillance videos, satellite video can record the snapshot of the city-scale scene. In a broad field-of-view of satellite videos, each moving target would be very tiny and usually composed of several pixels in frames. Even worse, the noise signals also existed in the video frames, since the background of the video frame has the subpixel-level and uneven moving thanks to the motion of satellites. We argue that this is a new type of computer vision task since previous technologies are unable to detect such tiny vehicles efficiently. This paper proposes a novel framework that can identify the small moving vehicles in satellite videos. In particular, we offer a novel detecting algorithm based on the local noise modeling. We differentiate the potential vehicle targets from noise patterns by an exponential probability distribution. Subsequently, a multi-morphological-cue based discrimination strategy is designed to distinguish correct vehicle targets from a few existing noises further. Another significant contribution is to introduce a series of evaluation protocols to measure the performance of tiny moving vehicle detection systematically. We annotate a satellite video manually and use it to test our algorithms under different evaluation criterion. The proposed algorithm is also compared with the state-of-the-art baselines, and demonstrates the advantages of our framework over the benchmarks.