超低功耗摄像头用上智能视觉，准确率超90%且不占内存
HyperCam: Low-Power Onboard Computer Vision for IoT Cameras
- 用高维计算在微控制器上高效训练与推理
- 四类任务准确率最高达93.6%，延迟仅0.27秒
- 适合资源受限的物联网摄像头部署
我们提出HyperCam，一种能在低功耗物联网摄像头系统上运行的高效图像分类流水线。该系统利用高维计算，在低功耗微控制器上实现高效的训练与推理。我们使用现成硬件搭建了低功耗无线摄像头平台，并验证其在MNIST、Fashion-MNIST、人脸检测和人脸识别任务上的准确率分别为93.60%、84.06%、92.98%和72.79%。相比SVM、xgBoost、MicroNets、MobileNetV3和MCUNetV3等其他机器学习分类器，HyperCam在资源效率上显著更优：推理延迟为0.08–0.27秒，峰值占用42.91–63.00KB闪存和22.25KB RAM。它是唯一在保持竞争力内存占用和推理延迟的同时，仍能实现较高准确率的分类器，满足低功耗摄像头系统的资源要求。
原文摘要 · Abstract (English)
We present HyperCam, an energy-efficient image classification pipeline that enables computer vision tasks onboard low-power IoT camera systems. HyperCam leverages hyperdimensional computing to perform training and inference efficiently on low-power microcontrollers. We implement a low-power wireless camera platform using off-the-shelf hardware and demonstrate that HyperCam can achieve an accuracy of 93.60%, 84.06%, 92.98%, and 72.79% for MNIST, Fashion-MNIST, Face Detection, and Face Identification tasks, respectively, while significantly outperforming other classifiers in resource efficiency. Specifically, it delivers inference latency of 0.08-0.27s while using 42.91-63.00KB flash memory and 22.25KB RAM at peak. Among other machine learning classifiers such as SVM, xgBoost, MicroNets, MobileNetV3, and MCUNetV3, HyperCam is the only classifier that achieves competitive accuracy while maintaining competitive memory footprint and inference latency that meets the resource requirements of low-power camera systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。