Change Detection (CD) and Change Captioning (CC) are two core tasks for understanding land-cover evolution in remote sensing imagery. Existing approaches have explored CD-CC joint modeling through shared representations, task-specific decoding, feature interaction, and semantic guidance. However, the lack of explicit cross-task feedback mechanisms often leads to mutual interference, making it difficult to achieve both accurate detection and expressive descriptions. To address this issue, we propose the Learning to Change by Critique and Correction (LCCC) framework, which reformulates CD and CC as a critique-correction closed-loop process. In LCCC, CD and CC no longer passively share features but interact through bidirectional critique and correction: the CD task provides explicit spatial constraints for CC, and CC, in turn, supervises CD via a Text-Guided Critique Attention (TGCA) mechanism, establishing a synergistic relationship where both tasks act as critics and correctors. Furthermore, we design a Reciprocal Suppression and Enhancement (RSE) module to purify cross-task representations and propose a Key Complementary Feature Fusion (KCFF) mechanism to bridge the gap between high-level semantics and low-level visual features, ensuring a balance between task specialization and cross-task enhancement. Extensive experiments demonstrate that LCCC significantly outperforms existing methods in both detection accuracy and description quality, validating the effectiveness and generality of the proposed critique-correction paradigm for synergistic multi-task modeling. The code of the proposed method is available at https://github.com/Throb16/Lccc.

With the enormous scale of remote sensing imagery generation, on-orbit computing has become a crucial paradigm to enable near-real-time processing. Due to the limited onboard resources and on-orbit power supply, satellite edge computing (SEC) is developed for satellite-ground collaboration, aiding on-orbit computation. However, the intermittent satellite-to-ground transmission link poses an efficiency challenge when collaborating SEC resources. Therefore, this article proposes a satellite edge computing resource scheduling technique for on-orbit remote sensing imagery processing ($\textsf {SECORS}$). First, we design a remote sensing mission-specific SEC architecture, which involves an offline-online satellite working mode. Subsequently, a computational resource scheduling model ($\textsf {SEC}$-$\textsf {RSM}$) is established, including the directed acyclic graph (DAG) model and mathematical problem formulation. Next, to obtain effective scheduling solutions, we develop an end-to-end algorithm leveraging the multiagent proximal policy optimization and heuristic rule of the earliest finish time ($\textsf {SEC}$-$\textsf {MPH}$). Finally, we build a simulation SEC platform to carry out experiments and implement several methods as the comparison including multiobjective evolutionary algorithms, deep reinforcement learning approaches, and the scheme without optimization (baseline). Simulation results show that$\textsf {SECORS}$achieves 68.87% and 66.60% reductions in time and energy for on-orbit computation. Moreover, our method improves the energy efficiency ratio (EER) by three times and achieves high processing capacity with 548 pixels per unit of power (W) and time (ms).

Extremely constrained storage and computational resources are one of the difficulties of satellite-on-orbit computing, which leads to over-parametric high-performance models not performing properly on-orbit. Knowledge distillation (KD) is an effective method for model compression; yet, there is a gap in the study of the limits and laws of KD-based model compression. To bridge this gap, we propose a novel KD framework, pyramid KD (PKD) and define a knowledge explosion and knowledge offset. Specifically, the pyramid distillation framework is built by stacking multiple sets of deep mutual learning (DML) models, with the smaller models on the top of the larger ones, and the overall structure is like a pyramid; hence, it is called PKD. To avoid knowledge explosion, we design a hybrid online–offline smooth distillation (HOSD) strategy by combining online distillation and offline distillation and reducing the difference between models. To avoid knowledge offset, we design an adaptive multiteacher distillation method to obtain multiteacher weighted knowledge by adaptively learning the weight of each teacher’s knowledge. We introduce an evolutionary algorithm to automatically find the optimal PKD configuration. We conduct ablation experiments and compare PKD with state-of-the-art distillation methods using ResNet series networks and VGG series networks as base models on Aircraft and FGSC-23 datasets, respectively. The experimental results show the effectiveness and advancement of PKD and reveal the law that the object recognition accuracy varies with the model compression rate.

Nowadays, the proliferation of small satellites brings the skyrocketing rise in space data, especially the shift to on-orbit computing needs. On one hand, with the increasing volume of data generation, like high-resolution remote sensing images, on-orbit computing produces near real-time onboard solutions and quick responses. However, constrained by the limited size and energy supply of satellites, achieving energy-efficient on-orbit computing remains a crucial challenge. In this article, an on-orbit remote sensing image processing complex task scheduling model facing heterogeneous multiprocessor system (HMPS) is proposed. First, aiming at accelerating image processing, we establish a novel parallel task execution model using directed acyclic graph (DAG) to universally describe typical missions, i.e., cloud detection, geometric correction, and image classification. Subsequently, a mathematical task scheduling formulation is defined to calculate the makespan, and total energy consumption (TEC) required when executing DAG on HMPS. Second, a new Pareto-based iterated greedy optimizer (PIGO) is devised to complete the energy- and time-efficient task execution and resource allocation on HMPS through confined inserting mutation, destruction-reconstruction, and local search. Finally, we build an emulated on-orbit HMPS to conduct experiments. The results show that, in comparison with the scheme without model scheduling, the most savings of around 51% and 54% in makespan and TEC, respectively, are achieved by the proposed model. Moreover, the HMPS configured with our methodology can obtain 2.2× improvement in energy efficiency and process up to 2.56×105pixels per unit of power (W) and time (s).

In recent years, the performance of the deep learning based object detection models for remote sensing images improves with the increase of the hyperparameter scale. However, the state of the art of detection models are generally too cumbersome to adapt to the resource-constrained satellite platforms, and even general lightweight detection models cannot satisfy performance requirements. To solve those problems, a lightweight and accurate oriented object detection network for satellite on-orbit computing (SOCDet) is proposed from three levels. At the computing unit level, we propose an efficient computing unit Single-kernel Omni-dimensional Dynamic Convolution to make SOCDet feature extraction more efficient. At the network module level, we design a structural reparameterization block based on composite structure reparameterization to improve inference accuracy. A guided attention module for guiding SOCDet is designed to extract object features. We design a lightweight and concise one-stage detection architecture at the network architecture level to accommodate satellite platforms with extremely constrained computing and storage resources. We conduct ablation experiments on the ground server and compare experiments with the state-of-the-art methods on embedded GPU, using DOTA, HRSC2016 and FAIR1M. The experiment results show that SOCDet can achieve 2.36 times faster than the baseline in inference speed with 10.78 more mAP, 72.6% fewer Params and 92.56% fewer floating point operations. Compared with state-of-the-art methods, SOCDet improves the inference speed and derives competitive mAP results with affordable computing capability.

High-quality remote sensing images not only provide opportunities for deep learning-based image interpretation, but also challenge satellite edge devices for storage, processing and downlinking to the ground server. Satellite on-orbit object recognition is an effective measure to solve this challenge. However, there is an insurmountable gap between the extremely limited computing and storage resources of satellites and the demand for those of deep learning. To solve this problem, a fast and lightweight intelligent satellite-on-orbit computing network (SOCNet) is proposed. First, the overall network architecture based on the idea of flat multi-branch feature extraction is proposed to accelerate model inference and reduce the network depth. Second, we propose the idea of exchanging a larger receptive field for network depth and combine the idea of depthwise separable convolution to further reduce the amount of parameters. We design a feature extraction method of coupled fine-coarse-grained for efficient feature extraction. Finally, global average pooling is used for feature fusion to further reduce network parameters amount and computational complexity. We have performed multiple sets of ablation experiments and some state-of-the-art comparison experiments on the server and carried out experimental verification on the NVIDIA Jetson TX2 mobile device to mimic the resource-constrained environment on the satellite. SOCNet with parameters of 0.21 MB, model size of 1.22 MB and computation cost of 50.81 MB floating point operations has achieved 99% comprehensive accuracy, 2.45 ms latency and 408 images per second throughput on 30 types of aircraft datasets with the 224 × 224 remote sensing images.

Main research in this paper is the DA(data acquisition) system design which based on the USB and MMC. According a USB's chip correlation hardware information, USB protocol, DA systematic structure and singlechip computer information, a hardware development solution was come out in the design. This solution consists of the data acquisition module hardware development design, singlechip computer data acquisition program development , USB's installation interface design and debug, embedded software(SW) and file system design. Finally we achieves the DA system which is more speedly, without delay and more dependable.