Abstract
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.
Abstract (translated)
我们介绍了HyperCam，这是一种节能的图像分类管道，可在低功耗物联网摄像头系统上执行计算机视觉任务。HyperCam利用超维度计算在低功耗微控制器上高效地进行训练和推理。我们使用现成的硬件实现了一个低功耗无线摄像头平台，并展示了HyperCam能够在MNIST、Fashion-MNIST、人脸检测和人脸识别任务中分别达到93.60%、84.06%、92.98% 和72.79% 的准确率，同时在资源效率上远超其他分类器。具体而言，在峰值状态下，它实现了0.08-0.27秒的推理延迟，并使用了42.91-63.00KB的闪存和22.25KB的RAM。与其他机器学习分类器（如SVM、xgBoost、MicroNets、MobileNetV3 和MCUNetV3）相比，HyperCam是唯一一个在保持竞争性准确率的同时，还能够满足低功耗摄像头系统资源需求的记忆占用和推理延迟要求的分类器。
URL
https://arxiv.org/abs/2501.10547
