专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2014085953A1 SYSTEM AND METHOD FOR DETECTING PEDESTRIANS USING A SINGLE NORMAL CAMERA 审中-公开
标题翻译：使用单一正常摄像机检测白菜的系统和方法
公开(公告)号：WO2014085953A1
公开(公告)日：2014-06-12
申请号：PCT/CN2012/085727
申请日：2012-12-03
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , ZHANG, Yankun , HONG, Chuyang , JIANG, Ruyi , ZHOU, Yun , WEYRICH, Norman
发明人： ZHANG, Yankun , HONG, Chuyang , JIANG, Ruyi , ZHOU, Yun , WEYRICH, Norman
IPC分类号： G06T7/00
CPC分类号： G06K9/00369 , G06K9/00805 , G06K9/52 , G06K2009/363 , G06T3/00 , G06T5/006 , G06T7/60 , G06T2207/30196 , G06T2207/30252 , H04N5/23293 , H04N5/357
摘要： The present application provides pedestrian detection system and method. A pedestrian detection method includes: obtaining an image captured by a camera; identifying a pedestrian candidate in the image; transforming the image into a top view image; calculating the actual height of the pedestrian candidate based on the top view image and extrinsic parameters of the camera; and determining whether the pedestrian candidate is a true positive by determining whether the actual height of the pedestrian candidate is within a predetermined pedestrian height range. The system and method of the present application have lower cost and higher accuracy compared with conventional technologies.
摘要翻译：本申请提供了行人检测系统和方法。行人检测方法包括：获取由照相机拍摄的图像; 识别图像中的行人候选人; 将图像转换为顶视图; 基于相机的顶视图和外在参数计算行人候选人的实际高度; 以及通过确定所述行人候选人的实际高度是否在预定的行人高度范围内来确定行人候选人是否为真正。与常规技术相比，本申请的系统和方法具有较低的成本和更高的精度。

2. 发明申请

WO2015024180A1 TRAFFIC LIGHT DETECTION 审中-公开
标题翻译：交通灯检测
公开(公告)号：WO2015024180A1
公开(公告)日：2015-02-26
申请号：PCT/CN2013/081842
申请日：2013-08-20
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
发明人： HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
IPC分类号： G08G1/097
CPC分类号： G06K9/00825 , G06K9/00818 , G06K9/3241 , G06K9/4647 , G06K9/6267 , G06T7/90 , G06T2207/10024 , G06T2207/30252 , G08G1/09623
摘要： A method and a system for traffic light detection are provided. The method may include: obtaining a color image; calculating pixel response values for pixels of the color image, respectively, where each of the pixel response values may be calculated using R, G, and B values of a corresponding pixel directly, such that pixel response values of red traffic light pixels are substantially distributed on a first side of a predetermined range and pixel response values of green traffic light pixels are substantially distributed on a second side of the predetermined range which is opposite to the first side; identifying pixels whose pixel response values are distributed on the first side or the second side as candidate pixels; identifying candidate blobs based on the candidate pixels; and verifying whether the candidate blobs are traffic lights. Efficiency and reliability may be improved.
摘要翻译：提供了一种用于交通信号灯检测的方法和系统。该方法可以包括：获得彩色图像; 分别计算彩色图像像素的像素响应值，其中可以使用直接对应像素的R，G和B值来计算每个像素响应值，使得红色红绿灯像素的像素响应值基本上分布在预定范围的第一侧上，绿色交通信号灯像素的像素响应值基本上分布在与第一侧相反的预定范围的第二侧上; 将其像素响应值分布在第一侧或第二侧上的像素识别为候选像素; 基于候选像素识别候选块; 并验证候选人是否是交通信号灯。可以提高效率和可靠性。

3. 发明申请

WO2015010320A1 TIME-TO-COLLISION ESTIMATION METHOD AND SYSTEM 审中-公开
标题翻译：时间碰撞估计方法和系统
公开(公告)号：WO2015010320A1
公开(公告)日：2015-01-29
申请号：PCT/CN2013/080182
申请日：2013-07-26
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , JIANG, Ruyi , ZHANG, Yankun , HONG, Chuyang , ZHOU, Yun
发明人： JIANG, Ruyi , ZHANG, Yankun , HONG, Chuyang , ZHOU, Yun
IPC分类号： G08G1/16
CPC分类号： G08G1/166 , B60W30/095 , B60W30/16 , B60W2420/42 , G06T7/246 , G06T7/536 , G06T2207/30261
摘要： A time-to-collision estimation method is provided. The method includes: obtaining a first image captured by a camera at a first time point and a second image captured by the camera at a second time point; selecting a point on an object in the first image; identifying the point in the second image; and calculating a first collision time based on a time interval between the first and second time points, a vertical position of the first point in the first image and a vertical position of the first point in the second image. No extrinsic parameter of the camera is required, thereby improving the efficiency.
摘要翻译：提供了一种时间到碰撞估计方法。该方法包括：在第一时间点获取由相机拍摄的第一图像和在第二时间点由相机拍摄的第二图像; 在第一图像中选择对象上的点; 识别第二个图像中的点; 并且基于第一和第二时间点之间的时间间隔，第一图像中的第一点的垂直位置和第二图像中的第一点的垂直位置来计算第一碰撞时间。不需要相机的外在参数，从而提高效率。

4. 发明申请

WO2015051697A1 IMAGE PROCESSING 审中-公开
标题翻译：图像处理
公开(公告)号：WO2015051697A1
公开(公告)日：2015-04-16
申请号：PCT/CN2014/087185
申请日：2014-09-23
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
发明人： HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
IPC分类号： G06K9/46
CPC分类号： G06K9/4642
摘要： An image processing method is provided. The method may include: obtaining an image; calculating a set of pixel gradients for each of a plurality of pixels in the image; obtaining feature values, including magnitude values and orientation values, of the calculated sets of pixel gradients based on a lookup table which includes a plurality of units storing all possible feature values respectively corresponding to all possible sets of pixel gradients; calculating a histogram of oriented gradients (HOG) based on the feature values of the calculated pixel gradients; and processing the image based on the calculated histogram of oriented gradients. Computation load for calculating the HOG may be reduced.
摘要翻译：提供了图像处理方法。该方法可以包括：获得图像; 计算图像中的多个像素中的每一个的像素梯度的集合; 基于包括存储分别对应于所有可能的像素梯度集合的所有可能特征值的多个单元的查找表来获得所计算的像素梯度组的特征值，包括幅度值和取向值; 基于计算的像素梯度的特征值计算定向梯度（HOG）的直方图; 并根据计算的定向梯度直方图处理图像。用于计算HOG的计算负载可能会减少。

5. 发明申请

WO2014117403A1 METHOD AND SYSTEM FOR DETECTING MOVING OBJECTS 审中-公开
标题翻译：检测移动物体的方法和系统
公开(公告)号：WO2014117403A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/071335
申请日：2013-02-04
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , ZHOU, Yun , HONG, Chuyang , ZHANG, Yankun , WEYRICH, Norman
发明人： ZHOU, Yun , HONG, Chuyang , ZHANG, Yankun , WEYRICH, Norman
IPC分类号： G06T7/20
CPC分类号： G06K9/00711 , G06T7/246 , G06T2207/10016 , G06T2207/20076 , G06T2207/30196 , G06T2207/30252 , G06T2207/30261
摘要： A moving objects detection method is disclosed. The method may include: identifying a plurality of feature points based on a plurality of video frames; selecting from the plurality of feature points to form a first and a second groups of feature points based on correlations between the plurality of feature points; and identifying in at least one video frame two segments based on the first and the second groups of feature points, respectively, as detected moving objects, where a correlation between two feature points may include a distance component and a movement difference component, where the distance component is related to a distance between the two feature points, and the movement difference component is related to a difference between corresponding movements of the two feature points. A moving objects detection system is also provided.
摘要翻译：公开了一种移动物体检测方法。该方法可以包括：基于多个视频帧来识别多个特征点; 基于所述多个特征点之间的相关性，从所述多个特征点中选择形成第一和第二特征点组; 以及分别基于所述第一和第二特征点组在至少一个视频帧中识别两个段作为检测到的运动对象，其中两个特征点之间的相关性可以包括距离分量和运动差分量，其中距离分量与两个特征点之间的距离相关，并且运动差分量与两个特征点的相应运动之间的差异相关。还提供了一种移动物体检测系统。

6. 发明授权

US08848978B2 Fast obstacle detection 有权
标题翻译：快速障碍物检测
公开(公告)号：US08848978B2
公开(公告)日：2014-09-30
申请号：US13234499
申请日：2011-09-16
申请人： Zhang Yankun , Hong Chuyang , Norman Weyrich
发明人： Zhang Yankun , Hong Chuyang , Norman Weyrich
IPC分类号： G06T1/00 , G06K9/00 , G06T7/20
CPC分类号： G06K9/00805 , G06T7/194 , G06T7/254 , G06T2207/10016 , G06T2207/20224 , G06T2207/30261
摘要： Systems and methods for detecting obstacles using a single camera positioned on an apparatus in motion over an area of motion, or stationary over a moving area of motion. In an example method, a video stream of images is captured of the area of motion. The images in the video stream may be corrected for lens distortion prior to further processing. An Nth image frame is selected from a sequence of N images in the video stream. A set of N−1 difference images is calculated by subtracting each of the N−1 previous images from the Nth image. The N−1 difference images are added to one another to generate a combined difference image. A perspective transformation is performed on the combined difference image to generate a transformed image. The transformed image is analyzed to detect edges of obstacles in the transformed image. A signal indicating detection of an obstacle in the area of motion may then be generated.
摘要翻译：使用位于运动区域上的装置上的单个照相机来检测障碍物的系统和方法，或者在运动的运动区域上静止。在示例性方法中，捕获运动区域的视频图像流。视频流中的图像可以在进一步处理之前针对透镜畸变进行校正。从视频流中的N个图像的序列中选择第N个图像帧。通过从第N图像中减去N-1个先前图像中的每一个来计算一组N-1个差分图像。将N-1个差分图像彼此相加以生成组合差分图像。对组合的差分图像执行透视变换以产生变换图像。分析变换图像以检测变换图像中的障碍物的边缘。然后可以产生指示运动区域中的障碍物的检测的信号。

7. 发明申请

WO2015006935A1 TEXTURELESS WALL DETECTION 审中-公开
标题翻译：无纹壁检测
公开(公告)号：WO2015006935A1
公开(公告)日：2015-01-22
申请号：PCT/CN2013/079508
申请日：2013-07-17
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , JIANG, Ruyi , ZHANG, Yankun , HONG, Chuyang , ZHOU, Yun
发明人： JIANG, Ruyi , ZHANG, Yankun , HONG, Chuyang , ZHOU, Yun
IPC分类号： G06K9/48
CPC分类号： G06K9/48 , G06K2009/363
摘要： A textureless wall detection system and a method thereof are provided. A textureless wall detection method includes: obtaining an image captured by a camera; obtaining a feature vector of the image based on edge point distribution of the image; and using a trained model to determine whether there is a textureless wall in the image based on the feature vector.
摘要翻译：提供了一种无纹理的墙体检测系统及其方法。无纹理墙体检测方法包括：获得由照相机拍摄的图像; 基于图像的边缘点分布获得图像的特征向量; 并使用经过训练的模型来确定基于特征向量的图像中是否存在无纹理的壁。

8. 发明申请

WO2013004012A1 APPARATUS AND METHOD FOR RE-SAMPLING AND PROCESSING DIGITAL IMAGES 审中-公开
标题翻译：重新采样和处理数字图像的装置和方法
公开(公告)号：WO2013004012A1
公开(公告)日：2013-01-10
申请号：PCT/CN2011/076899
申请日：2011-07-06
申请人： HARMAN INTERNATIONAL (SHANGHAI) MANAGEMENT CO., LTD. , WANG, Charles Chuanming , ZHANG, Yankun , HONG, Chuyang
发明人： WANG, Charles Chuanming , ZHANG, Yankun , HONG, Chuyang
IPC分类号： G06T5/00
CPC分类号： G06T3/40
摘要： A method of the invention relates to image re-sampling, which comprises the steps of inputting original image data; generating an initial output from the original image data with a transformation operator; feeding-back a current output and generating a back-calculated input data based on the current output with an approximate reverse transformation operator; calculating a difference between the original image data and the back-calculated input data; obtaining a compensator based on the difference and optimizing the current output with the compensator; and outputting the optimized output. A system of the invention contains the respective corresponding units for performing the aforesaid method.
摘要翻译：本发明的方法涉及图像重采样，其包括输入原始图像数据的步骤; 用变换算子从原始图像数据生成初始输出; 反馈电流输出，并使用近似反向变换算子基于当前输出产生反向计算的输入数据; 计算原始图像数据和反向计算输入数据之间的差; 基于差异获得补偿器，并用补偿器优化当前输出; 并输出优化的输出。本发明的系统包含用于执行上述方法的各自相应的单元。

9. 发明申请

WO2015074173A1 OBJECT TRACKING 审中-公开
标题翻译：对象追踪
公开(公告)号：WO2015074173A1
公开(公告)日：2015-05-28
申请号：PCT/CN2013/087381
申请日：2013-11-19
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
发明人： HONG, Chuyang , ZHANG, Yankun , JIANG, Ruyi , ZHOU, Yun
IPC分类号： G06T7/20
CPC分类号： G06T7/277 , G06T7/246 , G06T2207/20016 , G06T2207/30261
摘要： An object tracking method and system is provided. The method may include: obtaining a classifier for tracking an object; obtaining a first image captured at a first time point; defining a first set of regions with a same shape and different scales in the first image; calculating a feature vector for each of the first set of regions; and determining the scale of the object in the first image based on the classifier and the feature vectors of the first set of regions. By using the method, the computation load for tracking the object is reduced.
摘要翻译：提供了一种对象跟踪方法和系统。该方法可以包括：获得用于跟踪对象的分类器; 获得在第一时间点捕获的第一图像; 在第一图像中定义具有相同形状和不同尺度的第一组区域; 计算所述第一组区域中的每一个的特征向量; 以及基于所述第一组区域的所述分类器和所述特征向量来确定所述第一图像中的对象的比例。通过使用该方法，减少了跟踪物体的计算负荷。

10. 发明申请

WO2014078979A1 METHOD AND SYSTEM FOR DETECTING TRAFFIC LIGHTS 审中-公开
标题翻译：检测交通灯的方法和系统
公开(公告)号：WO2014078979A1
公开(公告)日：2014-05-30
申请号：PCT/CN2012/084862
申请日：2012-11-20
申请人： HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED , ZHANG, Yankun , HONG, Chuyang , JIANG, Ruyi , ZHOU, Yun , WEYRICH, Norman
发明人： ZHANG, Yankun , HONG, Chuyang , JIANG, Ruyi , ZHOU, Yun , WEYRICH, Norman
IPC分类号： G08G1/00 , G06K9/00
CPC分类号： G06K9/00825 , G06K9/4652 , G06T1/0007 , G06T2207/10004 , G06T2207/10024 , G06T2207/30252
摘要： A method for detecting traffic lights is provided. The method includes: obtaining a color image captured by a camera; converting the color image into a first monochrome scale image; converting the first monochrome scale image into a first binary image; identifying a first set of candidate blobs in the first binary image based on at least one predetermined geometric parameter; and determine whether a first region in the color image, which first region corresponds to one of the first set of candidate blobs, is a green traffic light using a green traffic light classifier. The accuracy and efficiency may be improved.
摘要翻译：提供了一种检测交通灯的方法。该方法包括：获得由相机拍摄的彩色图像; 将彩色图像转换成第一单色刻度图像; 将所述第一单色刻度图像转换为第一二进制图像; 基于至少一个预定几何参数来识别所述第一二进制图像中的第一组候选块; 并且确定所述彩色图像中的第一区域是否是使用绿色交通信号灯分类器的绿色交通信号灯，所述第一区域与所述第一组候选斑块中的一个对应。可以提高精度和效率。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式