This work proposes a "Summarize First, Download Later" paradigm that exploits recent advances in onboard edge computing and Vision-Language Models (VLMs) and substantially reduces bandwidth consumption while accelerating time-to-insight for time-sensitive missions.
Abstract
Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downlink capacity remains a critical bottleneck -- often causing significant latency or the loss of valuable observations within limited contact windows. We propose a"Summarize First, Download Later"paradigm that exploits recent advances in onboard edge computing and Vision-Language Models (VLMs). Rather than indiscriminately downlinking raw imagery, the system follows a three-phase interaction protocol: the satellite first transmits concise natural language summaries generated by a quantized onboard VLM; ground operators then issue targeted Visual Question Answering (VQA) queries to verify scene relevance (e.g., wildfires or maritime anomalies); and full-resolution images are downloaded only when critical information is confirmed. This transforms the downlink from passive bulk transfer into an active, semantics-aware dialogue. We implement and evaluate the system on a resource-constrained NVIDIA Jetson platform, and experiments on diverse remote sensing scenes show that the proposed strategy substantially reduces bandwidth consumption while accelerating time-to-insight for time-sensitive missions.
CoOrbit is presented, a collaborative EO system that conserves onboard storage by retaining only changed and non-overlapping regions and achieves over 108.6× reduction in storage cost and 41.6× reduction in communication size compared to existing EO pipelines.
Ruichen Li, Yufan Wu, Zhengyi Hu et al.· Conference on Applications,...· 0 citations
Efficient processing is becoming increasingly important in infrared remote sensing, where satellite constellations produce large volumes of observations under constrained detector resolution, power, and downlink bandwidth. Multi-frame super-resolution (MFSR) offers a software-based route to spatial enhancement, but its evaluation in infrared sensing remains fragmented across private datasets and ad-hoc protocols. Existing benchmarks do not explicitly capture the thermal contrast, sensor noise, weak texture, and platform-induced frame-to-frame variation that characterize infrared video. We introduce IR275K, a curated benchmark containing 594 infrared video sequences and 275,196 frames. It provides sequence-level train/validation/test splits and a reproducible X4 evaluation protocol. As an initial architectural probe, we further evaluate CGMamba, a lightweight state-space model with 10.90M parameters and 112.14G FLOPs. CGMamba combines 2D rotary position encoding (2D~RoPE) with center-guided cross-Mamba (CGCM) fusion for implicit multi-frame reconstruction. It achieves 33.19dB PSNR, outperforming infrared single-image super-resolution references by 0.35--0.52~dB at substantially lower computational cost. Ablation results show that removing 2D~RoPE from CGCM causes a 1.53dB drop and severe grid-like artifacts. This indicates that explicit spatial anchoring is critical for stabilizing SSM-based cross-frame gating under infrared conditions. IR275K provides a reproducible foundation for accuracy--efficiency evaluation of infrared MFSR methods, while the architectural analysis offers a concrete starting point for spatially aware SSM design under resource-constrained infrared sensing. Dataset and evaluation resources are available at: https://github.com/InfraRecon7/IR275K.
Jie Deng, Heyang Wang, Changxin Wang et al.· arXiv.org· 0 citations
In nanosatellite Earth observation, transmitting cloud-occluded imagery—about 67% of captures—wastes scarce onboard energy and downlink bandwidth. This letter presents an onboard AI framework that performs real-time on-orbit cloud detection, enabling selective transmission of only valid imagery. To counter the domain shift between public training data and onboard sensor observations, we adopt an unsupervised domain adaptation (UDA) scheme based on diffusion-driven style transfer, which produces sensor-stylized training data reflecting sensor-specific characteristics without any labeled onboard imagery, enabling robust cloud detection under real operational conditions. Hardware-in-the-loop (HIL) testing on a flight-representative Jetson Xavier NX confirms a full-image inference latency of 0.359 s, well within the 12.11-s interframe interval at 550-km altitude, supporting continuous real-time operation. The proposed approach reduces per-image energy consumption by 66.7%, with inference overhead accounting for only 0.97% of the total, and orbital simulation shows that fewer communication passes deliver equivalent valid imagery, yielding a $9.09\times $ improvement in valid-image throughput.
Changmin Lee, Minsu Kim, Chanhee Jung et al.· IEEE Geoscience and Remote S...· 0 citations
General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained visual encoders are built around three-channel natural images and do not directly accommodate observations such as native multispectral measurements or synthetic aperture radar (SAR). Adapting VLMs to these sensors typically requires dedicated encoders and domain pretraining, slowing the reuse of stronger general-purpose checkpoints. We show that the multi-image interface of general-purpose VLMs offers a lightweight alternative. Our protocol renders each observation as five optical views and one SAR view, names them in the prompt, and adapts the language network and selected visual transformer blocks with LoRA. This exposes band composites, spectral indices, and radar backscatter through an existing visual interface. For land-cover recognition, structured supervision couples predicted classes with sensor evidence. We further construct preference pairs in which a true label is omitted while its supporting evidence is retained, encouraging complete predictions that remain consistent with the observations. On a balanced six-class land-cover benchmark derived from BigEarthNet-v2, the adapted Qwen3-VL reaches 0.8275 micro F1. The same input and adaptation protocol improves all four tested VLM architectures and transfers to Sen1Floods11 flood verification and BigEarthNet.txt captioning. Image removal and mismatch controls show that the adapted models use the supplied sensor observations. Together, these results demonstrate that VLMs can be repurposed for multispectral and SAR tasks through rendered inputs and compact LoRA adaptation, without training a new foundation model.
Shan-Ji Liu, Ke-Lu Yao, Jun-Xiao Xue et al.· 0 citations
On-board processing is emerging as a key enabler for Earth observation (EO) missions, reducing downlink requirements and supporting more autonomous, event-driven operations. Deep convolutional neural networks (CNNs) deliver state-of-the-art performance on many EO tasks, but their memory footprint and computational demands remain challenging for space-qualified hardware. Classical machine learning (CML) pipelines based on hand-crafted spectral and textural features offer a lighter alternative, yet it is unclear how they compare with modern compressed deep models under deployment-relevant efficiency metrics. This work introduces a unified experimental framework that jointly evaluates compressed deep learning (CDL) models and CML ensembles on two representative EO benchmarks: EuroSAT for land-cover classification and HYPERVIEW for hyperspectral soil-property regression. Starting from a common CNN baseline, we evaluate pruning and post-training quantization, and use the selected baseline as the teacher in family-conditioned KD experiments. We contrast the resulting models with optimized tree-based ensembles trained on engineered features. For the benchmark comparisons we measure predictive efficacy, inference time and serialized model size, enabling a systematic comparison of the trade-offs between accuracy, runtime and storage. In our experiments, quantization provides the largest observed storage reduction among the tested CDL variants, moderate pruning can preserve predictive performance more closely in some settings, and the effectiveness of knowledge distillation depends more strongly on the dataset, student design, and distillation setting. Classical ensembles remain attractive when low prediction-stage latency or small serialized models are required and a moderate loss in accuracy is acceptable. For raw-input deployment, their runtime benefit also depends on the cost and implementation of descriptor extraction. The proposed analysis provides empirical guidance for selecting model families and compression strategies when designing future on-board EO systems.
G. Di Palma, Alessio Pardini, Lan-Pei Li et al.· Pattern Analysis and Applica...· 0 citations
Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, actions, interactions, and scene changes that cannot be captured by isolated images. Existing models primarily target single images or discrete temporal observations spanning a long time range. However, a unified evaluation setting for assessing vision-language models on continuous remote-sensing video understanding remains lacking. We introduce RSVideo-10K, a remote-sensing video dataset comprising 10,773 instances, 1.47 million frames, and 17.02 hours of footage, containing both unmanned aerial vehicles and satellite platforms. Its fixed evaluation benchmark, RSVideo-Bench, contains 2,731 test instances and evaluates two complementary aspects of remote-sensing video understanding: L1 Perception and L2 Reasoning, spanning seven capability groups and 17 tasks. Evaluations show that current vision-language models still struggle to recover small local evidence, track short-lived states, and use scene-constrained spatial relations. Based on this analysis, we further propose RSVideo, a reinforcement learning framework for small-target spatiotemporal focusing that selects question-relevant regions across frames and suppresses redundant background tokens. RSVideo achieves a maximum absolute improvement of 9.01% with InternVL3.5-14B and attains the highest accuracy of 40.63% with Qwen3.6-27B across 26 open-source vision-language backbones. Codes will be available at https://github.com/HongjieZhou0329/RSVideo.
Hongjie Zhou, Shiqin Wang, Haoyang Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
