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 2311.03422cs.CVcs.NEeess.IV
收藏

基于空间对比度的高效低占用目标分类

Efficient and Low-Footprint Object Classification using Spatial Contrast

University of Pittsburgh(匹兹堡大学)

Matthew Belding, Daniel C. Stumpp, Rajkumar Kubendran

AI总结:

本研究提出基于事件传感器的局部空间对比度分类范式,结合二值化DNN在GTSRB数据集上实现了数据与内存占用大幅降低,仅小幅损失精度,适合边缘部署。

摘要:

基于事件的视觉传感器传统上计算时间对比度,为低功耗、低延迟的感知与计算提供了潜力。本研究针对基于事件的传感器,探究了一种采用局部空间对比度(SC)的替代范式,该范式使用相对和绝对两种不同的阈值化技术。鉴于与基于时间的传感器相比,空间对比度技术发展尚不成熟,研究探索了此类硬件传感器的理论模拟输出。此外,研究使用德国交通标志数据集(GTSRB)与知名深度神经网络(DNNs),对交通标志分类任务进行了评估。研究表明,空间对比度能够有效捕获分类所需的显著图像特征,使用二值化DNN时,与高精度RGB图像及传统DNN相比,输入数据用量至少减少12倍,内存资源减少17.5倍,而宏F1值仅出现约2%的小幅下降。二值化MicronNet使用空间对比度时F1值达到94.4%,而使用RGB输入图像时仅为56.3%。因此,空间对比度(SC)在功耗与资源受限的边缘计算环境中具备极大的部署潜力。

英文摘要:

Event-based vision sensors traditionally compute temporal contrast that offers potential for low-power and low-latency sensing and computing. In this research, an alternative paradigm for event-based sensors using localized spatial contrast (SC) under two different thresholding techniques, relative and absolute, is investigated. Given the slow maturity of spatial contrast in comparison to temporal-based sensors, a theoretical simulated output of such a hardware sensor is explored. Furthermore, we evaluate traffic sign classification using the German Traffic Sign dataset (GTSRB) with well-known Deep Neural Networks (DNNs). This study shows that spatial contrast can effectively capture salient image features needed for classification using a Binarized DNN with significant reduction in input data usage (at least 12X) and memory resources (17.5X), compared to high precision RGB images and DNN, with only a small loss (~2%) in macro F1-score. Binarized MicronNet achieves an F1-score of 94.4% using spatial contrast, compared to only 56.3% when using RGB input images. Thus, SC offers great promise for deployment in power and resource constrained edge computing environments.

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。

↑