arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.01271cs.CV
收藏

利用传感器内计算实现节能地球观测

Exploiting In-Sensor Computing for Energy-Efficient Earth Observation

Interdisciplinary Transformation University of Austria(跨学科转型奥地利大学);ETH Zurich(苏黎世联邦理工学院);University of Verona(威尼斯大学)

Luigi Capogrosso, Pietro Bonazzi, Loris Hoxhaj, Michele Magno

AI总结:

针对卫星数据下行带宽瓶颈,提出基于TinyML和索尼IMX500传感器的传感器内计算框架,在8MB约束下达到96.68%精度和42.26 GMAC/J能效。

摘要:

卫星产业的快速增长推动了地理空间数据获取的大幅增加,凸显了一个关键瓶颈:收集的传感器数据量与地面站有限的可用下行带宽之间的严重不匹配。虽然星载计算通过在轨预处理数据帮助解决了这一问题,但本文通过引入传感器内计算框架进一步推进了这一范式。我们通过将TinyML技术与索尼IMX500智能视觉传感器集成,提出了一种针对严格计算约束优化的端到端地球观测流水线。具体来说,我们的方法将处理直接转移到传感器级别,减轻了主嵌入式设备的计算负担,并有效减少了噪声或无关数据的下行传输。我们在EuroSAT数据集上评估了几种高效的卷积神经网络,即SqueezeNet、ShuffleNetV2和MCUNetV1。实验结果表明,尽管部署在IMX500平台上需要优化,我们的模型在其8 MB约束内保持了具有竞争力的96.68%准确率。具体来说,模型达到平均处理吞吐量17.40 FPS,延迟27.43 ms。此外,我们的系统配置文件表现出高能效,每次推理的低能耗为14.19 mJ,能效评级为42.26 GMAC/J,证明了其在传感器内部署的可行性。

英文摘要:

The rapid growth of the satellite industry has driven a significant increase in geospatial data acquisition, highlighting a critical bottleneck: the severe disparity between the volume of collected sensor data and the limited downlink bandwidth available to ground stations. While On-Board Computing (OBC) has helped address this by pre-processing data in orbit, this article further advances the paradigm by introducing an in-sensor computing framework. We present an optimized end-to-end Earth Observation (EO) pipeline tailored for strict computational constraints by integrating TinyML techniques with the Sony IMX500 Intelligent Vision Sensor. Specifically, our approach shifts processing directly to the sensor level, offloading the computation from the primary embedded device, and effectively mitigating the downlink transmission of noisy or irrelevant data. We evaluated several efficient Convolutional Neural Networks (ConvNets), i.e., SqueezeNet, ShuffleNetV2, and MCUNetV1, on the EuroSAT dataset. Experimental results show that, despite the optimizations required for deployment on the IMX500 platform, our models maintain a competitive 96.68% accuracy while operating within its 8 MB constraints. Specifically, the models reach an average processing throughput of 17.40 FPS with a latency of 27.43 ms. Furthermore, our system profile exhibits high energy efficiency, with a low energy footprint of 14.19 mJ per inference and an efficiency rating of 42.26 GMAC/J, demonstrating its viability for in-sensor deployment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑