Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras
This addresses motion blur and saturation issues for autonomous driving systems, but is incremental as it adapts detection to a new sensor type.
The paper tackles object detection in autonomous driving under fast motion and extreme lighting by proposing EASD, an end-to-end spike camera detector, and introduces DSEC Spike, the first driving-oriented simulated spike detection benchmark, achieving unspecified results.
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.