Earth observation (EO) missions traditionally rely on transmitting raw or minimally processed imagery from satellites to ground stations for computationally intensive analysis. This paradigm is infeasible for CubeSat systems due to stringent constraints on the onboard embedded processors, energy availability, and communication bandwidth. To overcome these limitations, the paper presents a TinyML-based Convolutional Neural Networks (ConvNets) model optimization and deployment pipeline for onboard image classification, enabling accurate, energy-efficient, and hardware-aware inference under CubeSat-class constraints. Our pipeline integrates structured iterative pruning, post-training INT8 quantization, and hardware-aware operator mapping to compress models and align them with the heterogeneous compute architecture of the STM32N6 microcontroller from STMicroelectronics. This Microcontroller Unit (MCU) integrates a novel Arm Cortex-M55 core and a Neural-ART Neural Processing Unit (NPU), providing a realistic proxy for CubeSat onboard computers. The paper evaluates the proposed approach on three EO benchmark datasets (i.e., EuroSAT, RS_C11, MEDIC) and four models (i.e., SqueezeNet, MobileNetV3, EfficientNet, MCUNetV1). We demonstrate an average reduction in RAM usage of 89.55% and Flash memory of 70.09% for the optimized models, significantly decreasing downlink bandwidth requirements while maintaining task-acceptable accuracy (with a drop ranging from 0.4 to 8.6 percentage points compared to the Float32 baseline). The energy consumption per inference ranges from 0.68 mJ to 6.45 mJ, with latency spanning from 3.22 ms to 30.38 ms. These results fully satisfy the stringent energy budgets and real-time constraints required for efficient onboard EO processing.

翻译：地球观测任务传统上依赖将卫星获取的原始或轻度处理图像传输至地面站进行密集型计算分析。这一范式对立方星系统而言不可行，原因在于其板载嵌入式处理器、可获取能量及通信带宽均面临严格约束。为克服这些限制，本文提出一种基于TinyML的卷积神经网络模型优化与部署流水线，用于板载图像分类，在立方星级约束下实现高精度、高能效且感知硬件的推理。该流水线集成了结构化迭代剪枝、训练后INT8量化及硬件感知算子映射，以压缩模型并使其适配意法半导体STM32N6微控制器的异构计算架构。该微控制器单元集成了新型Arm Cortex-M55核心与Neural-ART神经网络处理单元，可作为立方星球载计算机的现实代理。本文在三个地球观测基准数据集（EuroSAT、RS_C11、MEDIC）及四个模型（SqueezeNet、MobileNetV3、EfficientNet、MCUNetV1）上评估了所提方法。经优化后的模型RAM使用量平均降低89.55%，Flash存储器使用量平均降低70.09%，在保持可接受任务精度（相比Float32基线精度下降0.4至8.6个百分点）的同时，显著降低了下行链路带宽需求。单次推理能耗范围为0.68 mJ至6.45 mJ，延迟范围为3.22 ms至30.38 ms。这些结果完全满足高效板载地球观测处理所需的严格能量预算与实时性约束。