已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

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

作者
Giulia Veronica D'Angelo,Victoria Clerico,Chiara Bartolozzi,Matej Hoffmann,P. Michael Furlong,Alexander Hadjiivanov
出处
期刊:Neuromorphic computing and engineering [IOP Publishing]
卷期号:5 (2): 024019-024019 被引量:1
标识
DOI:10.1088/2634-4386/addc90
摘要

Abstract Active vision enables dynamic and robust visual perception, offering an alternative to the static, passive nature of feedforward architectures commonly used in computer vision, which depend 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, further enhance this capability by capturing asynchronous scene changes, enabling efficient, low-latency processing. To distinguish moving objects while the event-based camera is also in motion, the agent requires an object motion segmentation mechanism to accurately detect targets and position them at the centre of the visual field (fovea). Integrating event-based sensors with neuromorphic algorithms represents a paradigm shift, using spiking neural networks (SNNs) to parallelise 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, characterised using ideal gratings and benchmarked against the event camera motion segmentation dataset, reaches a mean IoU of 82.2% and a mean structural similarity index of 96% in multi-object motion segmentation. Additionally, the detection of salient objects reaches an accuracy of 88.8% in office scenarios and 89.8% in challenging indoor and outdoor low-light conditions, as evaluated on the event-assisted low-light video object segmentation dataset. A real-time demonstrator showcases the system’s capabilities of detecting the salient object through object motion sensitivity in 0.124 s in dynamic scenes. Its learning-free design ensures robustness across diverse perceptual scenes, making it a reliable foundation for real-time robotic applications and serving as a basis for more complex architectures. Media : The accompanying video can be found online 7 7 https://youtu.be/dcAJlDgVR0o . .

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
木华发布了新的文献求助10
刚刚
刚刚
胡图图完成签到 ,获得积分20
刚刚
酷波er的应助被无情妙菡采纳,获得10
1秒前
1秒前
科研通AI6.3的应助被积极北上采纳,获得10
1秒前
时老完成签到 ,获得积分10
2秒前
2秒前
Parker发布了新的文献求助10
4秒前
4秒前
hmv发布了新的文献求助10
5秒前
Arvin发布了新的文献求助10
5秒前
ar发布了新的文献求助10
6秒前
魏魏完成签到,获得积分10
6秒前
6秒前
zhzhzh发布了新的文献求助10
7秒前
Owen的应助被杨家南采纳,获得10
8秒前
8秒前
不吃鸭梨完成签到,获得积分10
10秒前
砍柴少年发布了新的文献求助10
10秒前
无限的含羞草完成签到,获得积分10
11秒前
12秒前
清风携来春夏完成签到,获得积分10
13秒前
Ava的应助被谦让的语儿采纳,获得10
13秒前
OK的应助被林夕采纳,获得80
13秒前
砰砰里完成签到,获得积分10
14秒前
阿狸完成签到 ,获得积分10
15秒前
哈哈哈哈哈哈完成签到 ,获得积分10
15秒前
mm完成签到,获得积分10
15秒前
田様的应助被lmd采纳,获得10
17秒前
我爱科研完成签到 ,获得积分10
18秒前
18秒前
伶俐初蓝完成签到 ,获得积分10
19秒前
20秒前
科研通AI6.3的应助被Parker采纳,获得10
21秒前
molihuakai的应助被杨希采纳,获得10
22秒前
23秒前
kskfjs完成签到,获得积分10
23秒前
23秒前
李煜东完成签到,获得积分10
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8179104
求助须知:如何正确求助?哪些是违规求助? 9569680
关于积分的说明 21806134
捐赠科研通 7774263
什么是DOI,文献DOI怎么找? 3433003
关于科研通互助平台的介绍 2556897
邀请新用户注册赠送积分活动 2478643