公开(公告)号：US09821813B2

公开(公告)日：2017-11-21

申请号：US14879264

申请日：2015-10-09

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Vikas Dhiman

IPC: B60W40/04 ,  G06T17/00 ,  H04N7/18 ,  H04N5/225 ,  G06T7/20 ,  G06K9/00 ,  G06T7/579 ,  G06T7/215 ,  G06T7/277

CPC classification number: B60W40/04 ,  B60R2300/108 ,  B60R2300/804 ,  G06K9/00798 ,  G06K9/00805 ,  G06T7/215 ,  G06T7/277 ,  G06T7/579 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/30241 ,  G06T2207/30252 ,  H04N5/225 ,  H04N7/183

Abstract: Systems and methods are disclosed for road scene understanding of vehicles in traffic by capturing images of traffic with a camera coupled to a vehicle; generating a continuous model of occlusions with a continuous occlusion mode for traffic participants to enhance point track association accuracy without distinguishing between moving and static objects; applying the continuous occlusion model to handle visibility constraints in object tracks; and combining point track association and soft object track modeling to improve 3D localization accuracy.

公开(公告)号：US20160137206A1

公开(公告)日：2016-05-19

申请号：US14879264

申请日：2015-10-09

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Vikas Dhiman

IPC: B60W40/04 ,  G06T17/00 ,  H04N7/18 ,  H04N5/225 ,  G06T7/20 ,  G06K9/00

CPC classification number: B60W40/04 ,  B60R2300/108 ,  B60R2300/804 ,  G06K9/00798 ,  G06K9/00805 ,  G06T7/215 ,  G06T7/277 ,  G06T7/579 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/30241 ,  G06T2207/30252 ,  H04N5/225 ,  H04N7/183

Abstract: Systems and methods are disclosed for road scene understanding of vehicles in traffic by capturing images of traffic with a camera coupled to a vehicle; generating a continuous model of occlusions with a continuous occlusion mode for traffic participants to enhance point track association accuracy without distinguishing between moving and static objects; applying the continuous occlusion model to handle visibility constraints in object tracks; and combining point track association and soft object track modeling to improve 3D localization accuracy.

Abstract translation: 公开了通过使用耦合到车辆的照相机捕获交通图像来进行交通车辆道路现场理解的系统和方法; 以连续遮挡模式为流量参与者生成连续的闭塞模型，以增强点轨道关联精度，而不区分移动和静态对象; 应用连续遮挡模型来处理物体轨迹中的可视约束; 并结合点轨道关联和软物体轨迹建模来提高3D定位精度。