Fpv-crash dataset locates exact moments drones crash in flight videos
FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos
Computer Vision and Pattern Recognition
Summary
Drones can crash while flying, and figuring out the exact moment a crash happens in drone video footage is important for studying what went wrong. The authors created FPV-CRASH, a collection of over 1,000 drone flight videos that show both crashes and normal flights, with labels marking the exact crash moment. They also developed a model to predict when a crash happens from the video frames, improving accuracy by about half a second. This helps engineers analyze crashes more precisely using the drone's own video recordings.
What this means in practice
- •For drone inspection teams: Pinpoint the exact frame in drone footage when a crash impact occurs to speed up failure diagnosis during aerial inspections.
- •For autonomous drone operators: Improve training of crash detection systems by incorporating detailed crash moment data from onboard video streams.
Authors
Jifan Zhang, Tingyu Wang, Qian Liu, Zhedong Zheng
Abstract
Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV) video recorded by a drone, thereby providing a temporal reference for retrospective crash analysis in aerial robotics. However, existing crash-video datasets predominantly target surveillance or dash-camera footage, and their annotation schemes and task formulations are not designed for temporal localization of the major physical impact in UAV onboard FPV videos. To address this gap, we present FPV-CRASH, a dataset and fixed-protocol reference evaluation for offline Crash Moment Localization in drone FPV videos. FPV-CRASH contains 1,052 drone FPV clips (526 Crash and 526 Normal); each Crash clip has a single-frame reference annotation for the Crash Moment, and every clip is paired with four English captions automatically generated from sampled frames and the known Crash/Normal label. Normal clips carry no timestamp target and provide training-time background supervision. The captions support an auxiliary Text-to-Video Retrieval task, whereas localization inference remains video-only. We further provide a heatmap-based reference model that estimates a continuous Crash Moment timestamp from sparsely sampled frames. Under the fixed, non-source-disjoint clip-level protocol, the reference model reduces MAE from 1.12 s for the strongest fixed timing-prior baseline to 0.56 s (a 50% relative reduction) and achieves a median absolute error (MedAE) of 0.33 s; the fraction of clips localized within 0.5 s rises from 37.14% to 65.71%. The release includes annotations, available source video identifiers and URLs, clipping metadata, fixed split lists, and preprocessing code so that the reportable portion can be reconstructed without redistributing source footage. At submission time, all source-compilation URLs remained accessible.