# Wandering around: A bioinspired approach to visual attention through object motion sensitivity

arXiv: https://arxiv.org/abs/2502.06747 · HTML: https://mlsanity.com/paper/2502.06747/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 94 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 17 of 17)

- [Continuous-Time Visual-Inertial Odometry for Event Cameras](https://mlsanity.com/paper/1702.07389/) (2017)
- [A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)](https://mlsanity.com/paper/1708.04198/) (2017)
- [EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras](https://mlsanity.com/paper/1903.07520/) (2019)
- [The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticity](https://mlsanity.com/paper/2201.11063/) (2022)
- [Event-Based Angular Velocity Regression with Spiking Networks](https://mlsanity.com/paper/2003.02790/) (2020)
- [Optimizing the energy consumption of spiking neural networks for neuromorphic applications](https://mlsanity.com/paper/1912.01268/) (2019)
- [SpikeMS: Deep Spiking Neural Network for Motion Segmentation](https://mlsanity.com/paper/2105.06562/) (2021)
- [Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing](https://mlsanity.com/paper/2311.14641/) (2023)
- [Event-assisted Low-Light Video Object Segmentation](https://mlsanity.com/paper/2404.01945/) (2024)
- [Processing Data Where It Makes Sense: Enabling In-Memory Computation](https://mlsanity.com/paper/1903.03988/) (2019)
- [Exploiting Event Cameras for Spatio-Temporal Prediction of Fast-Changing Trajectories](https://mlsanity.com/paper/2001.01248/) (2020)
- [Enabling Depth-driven Visual Attention on the iCub Humanoid Robot: Instructions for Use and New Perspectives](https://mlsanity.com/paper/1509.06939/) (2015)
- [IRIS: Integrated Retinal Functionality in Image Sensors](https://mlsanity.com/paper/2208.12707/) (2022)
- [iCub Detecting Gazed Objects: A Pipeline Estimating Human Attention](https://mlsanity.com/paper/2308.13318/) (2023)
- [FPGA Implementation of An Event-driven Saliency-based Selective Attention Model](https://mlsanity.com/paper/2211.14060/) (2022)
- [Hardware-Algorithm Re-engineering of Retinal Circuit for Intelligent Object Motion Segmentation](https://mlsanity.com/paper/2408.08320/) (2024)
- [Retina-Inspired Object Motion Segmentation for Event-Cameras](https://mlsanity.com/paper/2408.09454/) (2024)

## Built on by (most cited first, 5 of 5)

- [VibES: Induced Vibration for Persistent Event-Based Sensing](https://mlsanity.com/paper/2508.19094/) (2025)
- [Realizing Fully-Integrated, Low-Power, Event-Based Pupil Tracking with Neuromorphic Hardware](https://mlsanity.com/paper/2511.20175/) (2025)
- [Neuromorphic visual attention for Sign-language recognition on SpiNNaker](https://mlsanity.com/paper/2605.06005/) (2026)
- [Efficient Semantic Understanding from Digital Foveation](https://mlsanity.com/paper/2609.04088/) (2026)
- [Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection](https://mlsanity.com/paper/2609.17134/) (2026)

## Abstract (arXiv)

Active vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision, which rely on large datasets and high computational resources. Biological selective attention mechanisms allow agents to focus on salient Regions of Interest (ROIs), reducing computational demand while maintaining real-time responsiveness. Event-based cameras, inspired by the mammalian retina, enhance this capability by capturing asynchronous scene changes enabling efficient low-latency processing. To distinguish moving objects while the event-based camera is in motion the agent requires an object motion segmentation mechanism to accurately detect targets and center them in the visual field (fovea). Integrating event-based sensors with neuromorphic algorithms represents a paradigm shift, using Spiking Neural Networks to parallelize computation and adapt to dynamic environments. This work presents a Spiking Convolutional Neural Network bioinspired attention system for selective attention through object motion sensitivity. The system generates events via fixational eye movements using a Dynamic Vision Sensor integrated into the Speck neuromorphic hardware, mounted on a Pan-Tilt unit, to identify the ROI and saccade toward it. The system, characterized using ideal gratings and benchmarked against the Event Camera Motion Segmentation Dataset, reaches a mean IoU of 82.2% and a mean SSIM of 96% in multi-object motion segmentation. The detection of salient objects reaches 88.8% accuracy in office scenarios and 89.8% in low-light conditions on the Event-Assisted Low-Light Video Object Segmentation Dataset. A real-time demonstrator shows the system's 0.12 s response to dynamic scenes. Its learning-free design ensures robustness across perceptual scenes, making it a reliable foundation for real-time robotic applications serving as a basis for more complex architectures.