Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras

TL;DR

This paper introduces EASD, an end-to-end spike camera object detector utilizing entropy-guided attention and a dual-branch architecture, addressing challenges in processing sparse spike data for autonomous driving detection tasks.

Contribution

It presents a novel dual-branch detector architecture and introduces DSEC Spike, the first driving-oriented spike detection benchmark for autonomous driving.

Findings

EASD effectively detects objects in spike camera data.

DSEC Spike benchmark enables standardized evaluation of spike detection methods.

The proposed method outperforms existing approaches in spike-based object detection.

Abstract

Object detection in autonomous driving suffers from motion blur and saturation under fast motion and extreme lighting. Spike cameras, offer microsecond latency and ultra high dynamic range for object detection by using per pixel asynchronous integrate and fire. However, their sparse, discrete output cannot be processed by standard image-based detectors, posing a critical challenge for end to end spike stream detection. We propose EASD, an end to end spike camera detector with a dual branch design: a Temporal Based Texture plus Feature Fusion branch for global cross slice semantics, and an Entropy Selective Attention branch for object centric details. To close the data gap, we introduce DSEC Spike, the first driving oriented simulated spike detection benchmark.