CVNEIVNov 6, 2023

Efficient and Low-Footprint Object Classification using Spatial Contrast

arXiv:2311.03422v1h-index: 13
AI Analysis

This work addresses efficient object classification for power-constrained edge devices, though it is incremental as it builds on existing event-based sensor paradigms.

The paper tackled object classification for edge computing by proposing spatial contrast as an alternative to temporal contrast in event-based vision sensors, achieving a 12X reduction in input data usage and 17.5X memory savings with only a ~2% loss in F1-score compared to RGB images.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes