# Event-based Feature Extraction Using Adaptive Selection Thresholds

arXiv: https://arxiv.org/abs/1907.07853 · HTML: https://mlsanity.com/paper/1907.07853/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2019.

## Built on by (most cited first, 20 of 20)

- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [E-MLB: Multilevel Benchmark for Event-Based Camera Denoising](https://mlsanity.com/paper/2303.11997/) (2023)
- [How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels](https://mlsanity.com/paper/2206.13673/) (2022)
- [Embedded Graph Convolutional Networks for Real-Time Event Data Processing on SoC FPGAs](https://mlsanity.com/paper/2406.07318/) (2024)
- [Event Camera Meets Mobile Embodied Perception: Abstraction, Algorithm, Acceleration, Application](https://mlsanity.com/paper/2503.22943/) (2025)
- [Traffic Sign Detection With Event Cameras and DCNN](https://mlsanity.com/paper/2207.13345/) (2022)
- [An optimised deep spiking neural network architecture without gradients](https://mlsanity.com/paper/2109.12813/) (2021)
- [Density Invariant Contrast Maximization for Neuromorphic Earth Observations](https://mlsanity.com/paper/2304.14125/) (2023)
- [Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement](https://mlsanity.com/paper/2402.09270/) (2024)
- [A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations](https://mlsanity.com/paper/2307.02947/) (2023)
- [High-definition event frame generation using SoC FPGA devices](https://mlsanity.com/paper/2307.14177/) (2023)
- [Motion Segmentation for Neuromorphic Aerial Surveillance](https://mlsanity.com/paper/2405.15209/) (2024)
- [PowerYOLO: Mixed Precision Model for Hardware Efficient Object Detection with Event Data](https://mlsanity.com/paper/2407.08272/) (2024)
- [Programming molecular systems to emulate a learning spiking neuron](https://mlsanity.com/paper/2206.02519/) (2022)
- [Efficient Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA](https://mlsanity.com/paper/2305.19468/) (2023)
- [Event-based Vision for Early Prediction of Manipulation Actions](https://mlsanity.com/paper/2307.14332/) (2023)
- [Pedestrian detection with high-resolution event camera](https://mlsanity.com/paper/2305.18008/) (2023)
- [EROAM: Event-based Camera Rotational Odometry and Mapping in Real-time](https://mlsanity.com/paper/2411.11004/) (2024)
- [Event-Based Crossing Dataset (EBCD)](https://mlsanity.com/paper/2503.17499/) (2025)
- [Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision](https://mlsanity.com/paper/2601.10742/) (2026)

## Abstract (arXiv)

Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers. The feature extraction method is tested on both the N-MNIST benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage.