论文阅读 [TPAMI-2022] Real-Time High Speed Motion Prediction Using Fast Aperture-Robust Event-Driven Visual Flow
论文搜索(studyai.com)
搜索论文: Real-Time High Speed Motion Prediction Using Fast Aperture-Robust Event-Driven Visual Flow
搜索论文: http://www.studyai.com/search/whole-site/?q=Real-Time+High+Speed+Motion+Prediction+Using+Fast+Aperture-Robust+Event-Driven+Visual+Flow
关键字(Keywords)
Visualization; Cameras; Heuristic algorithms; Vehicle dynamics; Apertures; Robot sensing systems; Event driven; neuromorphic; optical flow; motion prediction
机器视觉; 机器人/无人机
自主机器人; 运动捕捉; 运动估计; 光流
摘要(Abstract)
Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots.
光流是动态场景早期视觉处理特征空间的关键组成部分,尤其是在自动驾驶车辆、无人机和自动机器人等新应用中。.
The dynamic vision sensors are well suited for such applications because of their asynchronous, sparse and temporally precise representation of the visual dynamics.
动态视觉传感器非常适合此类应用,因为它们异步、稀疏且在时间上精确地表示视觉动态。.
Many algorithms proposed for computing visual flow for these sensors suffer from the aperture problem as the direction of the estimated flow is governed by the curvature of the object rather than the true motion direction.
为计算这些传感器的视觉流量而提出的许多算法都存在孔径问题,因为估计流量的方向取决于对象的曲率,而不是真实的运动方向。.
Some methods that do overcome this problem by temporal windowing under-utilize the true precise temporal nature of the dynamic sensors.
一些通过时间窗口来克服这一问题的方法利用了动态传感器真正精确的时间特性。.
In this paper, we propose a novel multi-scale plane fitting based visual flow algorithm that is robust to the aperture problem and also computationally fast and efficient.
在本文中,我们提出了一种新的基于多尺度平面拟合的视觉流算法,该算法对孔径问题具有鲁棒性,并且计算速度快、效率高。.
Our algorithm performs well in many scenarios ranging from fixed camera recording simple geometric shapes to real world scenarios such as camera mounted on a moving car and can successfully perform event-by-event motion estimation of objects in the scene to allow for predictions of upto 500 ms i.e., equivalent to 10 to 25 frames with traditional cameras…
我们的算法在许多场景中表现良好,从记录简单几何形状的固定摄像头到安装在移动汽车上的摄像头等真实场景,并且可以成功地对场景中的对象进行逐事件的运动估计,以实现高达500 ms的预测,即,相当于传统摄像头的10到25帧。。.
作者(Authors)
[‘Himanshu Akolkar’, ‘Sio-Hoi Ieng’, ‘Ryad Benosman’]