公开(公告)号：US20160300114A1

公开(公告)日：2016-10-13

申请号：US15085082

申请日：2016-03-30

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： DAN LEVI

IPC: G06K9/00 ,  G06T7/20 ,  G06T7/00 ,  G06K9/52 ,  G06T7/60

CPC classification number: G06K9/00805 ,  G06T7/246 ,  G06T7/50 ,  G06T2207/30252

Abstract: Methods and system for detecting an object are provided. In one embodiment, a method includes: receiving, by a processor, image data from a single camera, the image data representing an image of scene; determining, by the processor, stixel data from the image data; detecting, by the processor, an object based on the stixel data; and selectively generating, by the processor, an alert signal based on the detected object.

Abstract translation: 提供了一种用于检测物体的方法和系统。 在一个实施例中，一种方法包括：由处理器接收来自单个相机的图像数据，所述图像数据表示场景的图像; 由所述处理器确定来自所述图像数据的stixel数据; 由所述处理器检测基于所述stixel数据的对象; 以及由所述处理器选择性地根据所检测的对象产生警报信号。

公开(公告)号：US20160117560A1

公开(公告)日：2016-04-28

申请号：US14918267

申请日：2015-10-20

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： DAN LEVI ,  SHAI SILBERSTEIN

IPC: G06K9/00 ,  B60R11/04 ,  H04N7/18

CPC classification number: B60R11/04 ,  B60R1/00 ,  B60R2300/307 ,  G06K9/00805

Abstract: Systems and methods for detecting objects from a moving platform are provided. The method includes receiving, from a camera coupled to the moving platform, first and second image frames, wherein the second image frame is subsequent in time to the first image frame. Within the first image frame, a first target is defined characterizing the location of an object detected in the first image frame. A first score associated with the first target and a second score associated with the second target are determined, and a first predicted target is determined based on a tracking process applied to the first target. A third score associated with the first predicted target is determined. The method determines a merged target corresponding to the second target when the second score is greater than the third score and a proximity measure between the second target and the first predicted target is above a threshold.

Abstract translation: 提供了用于从移动平台检测物体的系统和方法。 该方法包括从耦合到移动平台的照相机接收第一和第二图像帧，其中第二图像帧在时间上跟随第一图像帧。 在第一图像帧内，定义表征在第一图像帧中检测到的对象的位置的第一目标。 确定与第一目标相关联的第一分数和与第二目标相关联的第二分数，并且基于应用于第一目标的跟踪过程来确定第一预测目标。 确定与第一预测目标相关联的第三分数。 当第二分数大于第三分数时，该方法确定与第二目标相对应的合并目标，并且第二目标与第一预测目标之间的接近度量度高于阈值。

公开(公告)号：US20160217335A1

公开(公告)日：2016-07-28

申请号：US15092853

申请日：2016-04-07

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： DAN LEVI ,  NOA GARNETT

IPC: G06K9/00 ,  G06K9/66 ,  B60R11/04 ,  G06T7/00

CPC classification number: G06K9/00805 ,  G06K9/4628 ,  G06K9/6272 ,  G06T7/77 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/30261

Abstract: Methods and systems are provided for detecting an object in an image. In one embodiment, a method includes: receiving, by a processor, data from a single sensor, the data representing an image; dividing, by the processor, the image into vertical sub-images; processing, by the processor, the vertical sub-images based on deep learning models; and detecting, by the processor, an object based on the processing.

Abstract translation: 提供了用于检测图像中的对象的方法和系统。 在一个实施例中，一种方法包括：由处理器接收来自单个传感器的数据，表示图像的数据; 由处理器将图像划分成垂直子图像; 由处理器处理基于深度学习模型的垂直子图像; 以及由所述处理器基于所述处理检测对象。

公开(公告)号：US20150199579A1

公开(公告)日：2015-07-16

申请号：US14156702

申请日：2014-01-16

Applicant: GM Global Technology Operations LLC

Inventor： INNA STAINVAS OLSHANSKY ,  IGAL BILIK ,  DAN LEVI

IPC: G06K9/00 ,  G06T7/00 ,  G06K9/46 ,  G06T5/00

CPC classification number: G06K9/4661 ,  G06K9/00791 ,  G06K9/4642 ,  G06T5/008 ,  G06T5/40 ,  G06T2207/30252

Abstract: A method of creating a shadow-reduced image from a captured image. An image of a scene exterior of a vehicle is captured by a vehicle-based image capture device. A first object profile of an object in the captured image is identified by a processor. A second object profile of the object is detected using a non-vision object detection device. Shadows in the captured image are removed by the processor as a function of the first object profile and the second object profile. A shadow reduced image is utilized in a vehicle-based application.

Abstract translation: 从捕获的图像创建阴影缩小图像的方法。 车辆的场景外观的图像由基于车辆的图像捕获装置捕获。 捕获图像中的对象的第一对象简档由处理器识别。 使用非视觉对象检测装置检测对象的第二对象轮廓。 捕获的图像中的阴影作为第一对象轮廓和第二对象轮廓的函数被处理器移除。 在基于车辆的应用中使用阴影缩小图像。