An event-driven framework for fly-inspired visual motion detection
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionNeural and Evolutionary Computing
AI summaryⓘ
The authors developed a motion detection system inspired by how flies process visual information. They combined event-based cameras, which detect changes in brightness very quickly and efficiently, with a neural network modeled after a fly's brain circuits. To deal with noise and distractions, they added a way to focus on important moving objects in the foreground. Their tests showed the system works well in real-world driving scenarios and is faster and simpler than some traditional methods. This approach blends fast sensing with a simple, natural way of processing visuals.
event-based sensingneural networkoptic lobemotion detectiontime-surface encodingbottom-up attentionevent camerasfeed-forward architectureforeground motion estimationbio-inspired computation
Authors
Qinbing Fu, Jingyu Huang, Yan Xie, Jigen Peng, Yuchao Tang
Abstract
Fast and reliable motion detection is essential for machine vision and autonomous systems operating in dynamic environments. This work integrates emerging event-based sensing with biologically structured neural computation to establish an efficient computational paradigm for visual motion detection. The proposed framework is built upon a recently developed fly-inspired neural network that emulates motion-processing circuits in the optic lobe. Owing to its feed-forward and training-free architecture, the neural model requires only a small number of interpretable parameters and is well suited for real-time embedded implementation. Event cameras provide low-latency, low-power, and high-dynamic-range visual sensing by asynchronously transmitting brightness-change events. However, their performance can be degraded by event noise, including temporal noise and junction-leakage-induced activity, particularly under low-light conditions. Moreover, effective integration between event-based visual representations and biologically inspired neural processing remains under-explored. To address these challenges, we propose an event-driven computational framework that combines time-surface encoding for front-end event representation with a fly optic-lobe-inspired neural network for foreground motion-direction estimation. A bottom-up attention mechanism is further incorporated to suppress background motion and enhance the saliency of foreground targets. The proposed method is evaluated on real-world ground-vehicle datasets and compared with a baseline frame-based model and an optimization-based approach. Experimental results demonstrate that the framework effectively combines the temporal advantages of event-driven vision with the efficiency and interpretability of bio-inspired neural processing.