Object Tracking Based on Satellite Videos: A Literature Review

Abstract

Video satellites have recently become an attractive method of Earth observation, providing consecutive images of the Earth’s surface for continuous monitoring of specific events. The development of on-board optical and communication systems has enabled the various applications of satellite image sequences. However, satellite video-based target tracking is a challenging research topic in remote sensing due to its relatively low spatial and temporal resolution. Thus, this survey systematically investigates current satellite video-based tracking approaches and benchmark datasets, focusing on five typical tracking applications: traffic target tracking, ship tracking, typhoon tracking, fire tracking, and ice motion tracking. The essential aspects of each tracking target are summarized, such as the tracking architecture, the fundamental characteristics, primary motivations, and contributions. Furthermore, popular visual tracking benchmarks and their respective properties are discussed. Finally, a revised multi-level dataset based on wpafb videos is generated and quantitatively evaluated for future development in the satellite video-based tracking area. In addition, 54.3% of the tracklets with lower ds are selected and renamed as the Easy group, while 27.2% and 18.5% of the tracklets are grouped into the Medium-ds group and the Hard-ds group, respectively.

Data pipeline of a multi-spectral satellite experiment for object detection and artificial intelligence-based processing

“…The more features a target provides, the greater the likelihood of detection and robust tracking. 43 Due to the small size of HGVs, with a projected area of only a few square meters and even with the zoomed GSD shown in the table 1, the radiation signature is only visible in one pixel. This is a fraction of about 0.0001 % of the total IR image.…”

“…Any object detection and tracking algorithm must be adapted to its actual use-case. 43 HGVs have a strong radiation signature in the MWIR spectrum during their glide phase. 2,4,5,44 Although this signature is comparatively strong due to their high surface temperature, the detection of these vehicles presents unique challenges.…”

“…• Multi-targets: A particular feature of certain detection and tracking algorithms is their ability to track multiple targets in a scene at the same time. 43 However, the likelihood of multiple HGVs appearing in a single image is very small and can be neglected.…”

“…With consecutive images and updated AOCS reference data, this procedure is repeated until the end of the operation is reached, which is for example when the requested slewing angle exceeds 30 For tracking object features in satellite imagery a variety of mathematical models exists. 43 The specific approach strongly depends on the intended application. Typical applications for remote tracking of artificial targets is the tracking of traffic, ships or aircraft.…”

“…Typical applications for remote tracking of artificial targets is the tracking of traffic, ships or aircraft. 43 Based on the outlined characteristics of HGVs in satellite imagery in section 4.2 a tracking model based on a Kernel Correlation Filter (KCF) is evaluated as most suitable on-board tracking method considering limited computational resources. Such a discriminative tracking method proves to be robust and accurate even under different conditions and for various tracking tasks 43,[51][52][53][54] including small IR targets.…”