检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:韦李涛 熊超然 项艳 WEI Litao;XIONG Chaoran;XIANG Yan(Shanghai Key Laboratory of Navigation and Location-based Services,Shanghai Jiao Tong University,Shanghai 200240)
机构地区:[1]上海交通大学上海市北斗导航与位置服务重点实验室,上海200240
出 处:《导航与控制》2024年第4期54-60,共7页Navigation and Control
基 金:国家自然科学基金的支持(编号62388101,62303311,62231010)。
摘 要:在事件相机事件帧的生成方式上,传统的固定时间间隔方法和固定事件数量方法产生的事件帧均会出现图像纹理过于稀疏和图像模糊的现象,导致基于这两种种方式生成的事件帧执行的视觉任务效果降低。针对上述问题,提出了一种异步感知信息的自主神经隐式事件帧生成方法,能够根据累计事件数据的信息量生成事件帧。首先,设计了基于残差网络的图像质量判别网络,用于异步感知事件时隐式判别事件帧所包含的语义信息量;然后,将基于质量判别网络定义的事件帧嵌入到语义分割任务中,在保证分割精度的情况下,降低了基于事件相机任务的信息获取延迟;最后,将提出的方法在公开数据集DSEC上进行了验证,相比传统方法,该事件帧生成方法在保持语义分割精度的生成每一帧事件帧的信息获取延迟降低了30 ms。Regarding the generation method of event frame mode for event cameras,the event frames generated by traditional fixed time interval methods and fixed event number methods are subject to the phenomena of overly sparse image texture and blurred images,which lead to the reduced effectiveness of the visual tasks performed by the event frames generated based on such methods.To address the above problems,an autonomic implicit event frame generation method with asynchronously perceiving information is proposed,which can generate event frames according to the amount of information of accumulated event data.First,an image quality discrimination network based on residual network is designed to implicitly discriminate the semantic information amount contained in event frames during asynchronous sensory events;second,the event frames defined by the quality discriminative network are embedded into the semantic segmentation task,which reduces the information acquisition latency of the event-based camera task while maintaining the segmentation accuracy;and third,the proposed method is verified on the public dataset DSEC.Compared with traditional methods,this event generation method reduces the information acquisition delay of each event frame by 30 ms while maintaining the semantic segmentation accuracy.
关 键 词:异步感知 事件相机 计算机视觉 事件帧 语义分割 信息获取延迟
分 类 号:TP3[自动化与计算机技术—计算机科学与技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.62