2026-10-13T02:06:09Z https://www.scidb.cn/oai

10.57760/sciencedb.46325 2026-08-20T15:12:19Z

2026-08-20 BatonTrack1.0: A Benchmark for Multi-Object Tracking Based on Multi-Satellite Cooperative Observation doi:10.57760/sciencedb.46325 en Multi-satellite cooperative observation overcomes the short continuous staring duration of a single satellite and significantly improves the spatiotemporal continuity of target observation. Existing satellite video multi-object tracking datasets are mainly designed for single-satellite continuous observation, focusing on object localization and frame-to-frame association within individual observation segments, and are therefore insufficient for long-term target tracking research. To address this limitation, we construct BatonTrack1.0, a benchmark dataset for multi-object tracking under multi-satellite cooperative observation. BatonTrack1.0 is built from real successive observations acquired by three Jilin-1 video satellites (GF03C01, GF03C02, and GF03C03) at two representative aviation hubs, Abu Dhabi Airport and New Delhi Airport, with coverage spanning key functional areas, including runways, taxiways, aprons, and arrival and departure zones. Each video segment lasts approximately 14 s and has a frame rate of 5 frames per second (fps). Since the satellite overpasses are not temporally contiguous, adjacent video segments contain observation gaps ranging from approximately 1 min 44 s to 2 min 1 s. To preserve the continuity of object motion across successive satellite observations, we construct cross-satellite multi-object tracking sequences by dynamically cropping each segment according to the locations of the objects, rather than extracting the same fixed geographic area across all segments. Each sequence is annotated with both standard multi-object tracking labels and cross-segment spatiotemporal annotations, including object locations, identity labels, frame timestamps, and inter-segment projection transformations. Overall, BatonTrack1.0 contains 8 multi-object tracking sequences with annotations for 192 aircraft targets, covering typical operational states such as takeoff, landing and taxiing.It provides a standardized foundation to develop, validate, and compare advanced algorithms capable of preserving object identities across spatial-temporal gaps. object detection; object tracking; multi-object tracking; satellite video; multi-satellite cooperative observation Xu Fang Xu Jian Yang Wen Xia Guisong PUBLIC https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank