-
公开(公告)号：US08462218B2
公开(公告)日：2013-06-11
申请号：US12947077
申请日：2010-11-16
CPC分类号： G06T3/0006 , G06T7/66 , H04N5/23248 , H04N5/23254 , H04N5/23258 , H04N5/23264 , H04N5/23277
摘要： An apparatus and method for stabilizing image frames in a video data stream. A weighted average or centroid of the intensity or hue associated with pixels vs. the horizontal and vertical position of each pixel is calculated for a reference frame in the video data stream. A corresponding centroid is calculated for a subsequent frame in the stream. This image frame is then translated so that the centroid of the subsequent frame and the centroid of the reference frame coincide, reducing artifacts from shaking of the video capture device. Alternatively, the video stream frames may be divided into tiles and centroids calculated for each tile. The centroids of the tiles of a subsequent frame are curve fit to the centroids of tiles in a reference frame. An affine transform is then performed on the subsequent frame to reduce artifacts in the image from movements of the video capture device.
摘要翻译： 一种用于稳定视频数据流中的图像帧的装置和方法。 对于视频数据流中的参考帧，计算与像素相关的强度或色相的加权平均或重心相对于每个像素的水平和垂直位置。 为流中的后续帧计算相应的质心。 然后翻转该图像帧，使得后续帧的质心和参考帧的质心重合，从而减少视频捕捉设备抖动的伪影。 或者，视频流帧可以被划分为针对每个图块计算的图块和重心。 后续帧的瓦片的质心曲线拟合到参考帧中的瓦片的质心。 然后在随后的帧上执行仿射变换，以减少图像中的伪影从视频捕捉设备的移动。
-
公开(公告)号：US20120212477A1
公开(公告)日：2012-08-23
申请号：US13030534
申请日：2011-02-18
CPC分类号： G06T5/003 , G06T7/507 , G06T2207/10024 , G06T2207/10032
摘要： A computer-implemented method of processing digital input image data containing haze and having a plurality of color channels including at least a blue channel, to generate output image data having reduced haze, includes receiving in a first computer-implemented process, digital input image data, and generating, in a second computer-implemented process, digital output image data based on the digital input image data using an estimated transmission vector for the digital input image data. The estimated transmission vector is substantially equal to an inverse blue channel of the digital input image data, and the digital output image data contains less haze than the digital input image data. The method also includes outputting the digital output image data via an output device.
摘要翻译： 一种计算机实现的处理数字输入图像数据的方法，所述数字输入图像数据包含雾度并且具有包括至少蓝色通道的多个颜色通道，以生成具有降低的雾度的输出图像数据，包括在第一计算机实现的处理中接收数字输入图像数据 并且在第二计算机实现的处理中，使用所估计的数字输入图像数据的传输矢量，基于数字输入图像数据生成数字输出图像数据。 估计的传输矢量基本上等于数字输入图像数据的反蓝色通道，并且数字输出图像数据包含比数字输入图像数据更少的雾度。 该方法还包括经由输出装置输出数字输出图像数据。
-
公开(公告)号：US08228378B2
公开(公告)日：2012-07-24
申请号：US13085629
申请日：2011-04-13
IPC分类号： H04N7/12
摘要： An apparatus and method for preparing a composite image from a video data stream and for identifying changed features in two composite images. Frames from the video data stream are transformed to a projected 2D image, aligned with adjacent frames and overlapping areas are averaged to provide a higher apparent resolution. The composite image can be stored in real-time. As a second composite image is prepared of the same location at a later time, portions of the second image can be compared to corresponding portions of the stored image after the intensities of the images are equalized. Image areas whose absolute difference exceeds a threshold are again intensity equalized. Areas that are again above threshold can be flagged for further scrutiny, either by a human or by a machine that performs object recognition. In this way, composite video images of a scene can be prepared and compared in real-time.
摘要翻译： 一种用于从视频数据流准备合成图像并识别两个合成图像中的改变的特征的装置和方法。 来自视频数据流的帧被转换为与相邻帧对准的投影2D图像，并且重叠区域被平均以提供更高的视在分辨率。 合成图像可以实时存储。 由于第二合成图像在稍后的时间被制备为相同的位置，所以在图像的强度被均衡之后，第二图像的部分可以与存储的图像的相应部分进行比较。 其绝对差异超过阈值的图像区域再次强度相等。 再次高于阈值的区域可以由人或由执行对象识别的机器进行进一步检查。 以这种方式，可以准备并比较场景的复合视频图像。
-
4.发明授权Real-time capture and transformation of hemispherical video images to images in rectilinear coordinates 有权将半球形视频图像实时捕获并转换为直线坐标中的图像公开(公告)号：US08160394B2
公开(公告)日：2012-04-17
申请号：US11432774
申请日：2006-05-11
IPC分类号： G06K9/32
CPC分类号： H04N5/2628 , G06T3/0018 , H04N5/23238 , H04N7/181
摘要： A method of transforming an input image from a hemispherical source to an output image in rectilinear coordinates is disclosed. The method includes receiving data representative of an input image originating from a hemispherical camera and having a size defined by an input image height and an input image width. Once the data is received, an output image width and output image height representative of a size of a rectilinear output image is calculated based on the size of the input image. A rectilinear output image is then generated by mapping input image pixels to locations within the width and height of the output image, without reference to the optical characteristics of the hemispherical camera.
摘要翻译： 公开了一种将输入图像从半球源转换为直线坐标中的输出图像的方法。 该方法包括接收表示源自半球形摄像机的输入图像并具有由输入图像高度和输入图像宽度限定的大小的数据。 一旦接收到数据，就根据输入图像的大小来计算表示直线输出图像的尺寸的输出图像宽度和输出图像高度。 然后通过将输入图像像素映射到输出图像的宽度和高度内的位置，而不参考半球形相机的光学特性，生成直线输出图像。
-
公开(公告)号：US20110188762A1
公开(公告)日：2011-08-04
申请号：US13085629
申请日：2011-04-13
IPC分类号： G06K9/68
摘要： An apparatus and method for preparing a composite image from a video data stream and for identifying changed features in two composite images. Frames from the video data stream are transformed to a projected 2D image, aligned with adjacent frames and overlapping areas are averaged to provide a higher apparent resolution. The composite image can be stored in real-time. As a second composite image is prepared of the same location at a later time, portions of the second image can be compared to corresponding portions of the stored image after the intensities of the images are equalized. Image areas whose absolute difference exceeds a threshold are again intensity equalized. Areas that are again above threshold can be flagged for further scrutiny, either by a human or by a machine that performs object recognition. In this way, composite video images of a scene can be prepared and compared in real-time.
摘要翻译： 一种用于从视频数据流准备合成图像并识别两个合成图像中的改变的特征的装置和方法。 来自视频数据流的帧被转换为与相邻帧对准的投影2D图像，并且重叠区域被平均以提供更高的视在分辨率。 合成图像可以实时存储。 由于第二合成图像在稍后的时间被制备为相同的位置，所以在图像的强度被均衡之后，第二图像的部分可以与存储的图像的相应部分进行比较。 其绝对差异超过阈值的图像区域再次强度相等。 再次高于阈值的区域可以由人或由执行对象识别的机器进行进一步检查。 以这种方式，可以准备并比较场景的复合视频图像。
-
公开(公告)号：US07859569B2
公开(公告)日：2010-12-28
申请号：US11209172
申请日：2005-08-22
CPC分类号： G06T3/0006 , G06T7/66 , H04N5/23248 , H04N5/23254 , H04N5/23258 , H04N5/23264 , H04N5/23277
摘要： An apparatus and method for stabilizing image frames in a video data stream. A weighted average or centroid of the intensity or hue associated with pixels vs. the horizontal and vertical position of each pixel is calculated for a reference frame in the video data stream. A corresponding centroid is calculated for a subsequent frame in the stream. This image frame is then translated so that the centroid of the subsequent frame and the centroid of the reference frame coincide, reducing artifacts from shaking of the video capture device. Alternatively, the video stream frames may be divided into tiles and centroids calculated for each tile. The centroids of the tiles of a subsequent frame are curve fit to the centroids of tiles in a reference frame. An affine transform is then performed on the subsequent frame to reduce artifacts in the image from movements of the video capture device.
摘要翻译： 一种用于稳定视频数据流中的图像帧的装置和方法。 对于视频数据流中的参考帧，计算与像素相关的强度或色相的加权平均或重心相对于每个像素的水平和垂直位置。 为流中的后续帧计算相应的质心。 然后翻转该图像帧，使得后续帧的质心和参考帧的质心重合，从而减少视频捕捉设备抖动的伪影。 或者，视频流帧可以被划分为针对每个图块计算的图块和重心。 后续帧的瓦片的质心曲线拟合到参考帧中的瓦片的质心。 然后在随后的帧上执行仿射变换，以减少图像中的伪影从视频捕捉设备的移动。
-
公开(公告)号：US07668402B2
公开(公告)日：2010-02-23
申请号：US10982386
申请日：2004-11-05
CPC分类号： G06T11/00
摘要： A method for generating a composite image includes receiving a separate image into a computer system, comparing the separate image to the composite image so as to generate a mismatch value, and modifying at least one of the composite image and the separate image to reduce the mismatch value.
摘要翻译： 一种用于生成合成图像的方法包括：将单独的图像接收到计算机系统中，将分离的图像与合成图像进行比较，以便产生不匹配值，以及修改合成图像和分离图像中的至少一个以减少不匹配 值。
-
公开(公告)号：US08189690B2
公开(公告)日：2012-05-29
申请号：US12905751
申请日：2010-10-15
IPC分类号： H04N7/12
CPC分类号： H04N21/4307 , G01C11/025 , G01S5/16 , G06F17/30241 , G06F17/30817 , G06F17/3087 , H04N21/2146
摘要： A system to parse both telemetry data and corresponding encoded video data wherein the telemetry and video data are subsequently synchronized based upon temporal information, such as a time stamp. The telemetry data and the video data are originally unsynchronized and the data for each is acquired by a separate device. The acquiring devices may be located within or attached to an aerial vehicle. The system receives the telemetry data and the encoded video data and outputs a series of synchronized video images with telemetry data. Thus, telemetry information is associated with each video image. The telemetry data may be acquired at a different rate than the video data. As a result, telemetry data may be interpolated or extrapolated to correspond to each video image. The present system operates in real-time, thus data acquired from aerial vehicles can be displayed on a map.
摘要翻译： 解析遥测数据和对应的编码视频数据的系统，其中遥测和视频数据随后基于诸如时间戳的时间信息来同步。 遥测数据和视频数据最初是不同步的，并且每个数据由单独的设备获取。 获取装置可位于飞行器内或附着于飞行器上。 该系统接收遥测数据和编码视频数据，并输出一系列具有遥测数据的同步视频图像。 因此，遥测信息与每个视频图像相关联。 可以以与视频数据不同的速率获取遥测数据。 结果，遥测数据可以被内插或外插以对应于每个视频图像。 本系统实时运行，因此从飞行器获取的数据可以显示在地图上。
-
公开(公告)号：US07961216B2
公开(公告)日：2011-06-14
申请号：US11196494
申请日：2005-08-03
IPC分类号： H04N7/12
摘要： An apparatus and method for preparing a composite image from a video data stream and for identifying changed features in two composite images. Frames from the video data stream are transformed to a projected 2D image, aligned with adjacent frames and overlapping areas are averaged to provide a higher apparent resolution. The composite image can be stored in real-time. As a second composite image is prepared of the same location at a later time, portions of the second image can be compared to corresponding portions of the stored image after the intensities of the images are equalized. Image areas whose absolute difference exceeds a threshold are again intensity equalized. Areas that are again above threshold can be flagged for further scrutiny, either by a human or by a machine that performs object recognition. In this way, composite video images of a scene can be prepared and compared in real-time.
摘要翻译： 一种用于从视频数据流准备合成图像并识别两个合成图像中的改变的特征的装置和方法。 来自视频数据流的帧被转换为与相邻帧对准的投影2D图像，并且重叠区域被平均以提供更高的视在分辨率。 合成图像可以实时存储。 由于第二合成图像在稍后的时间被制备为相同的位置，所以在图像的强度被均衡之后，第二图像的部分可以与存储的图像的相应部分进行比较。 其绝对差异超过阈值的图像区域再次强度相等。 再次高于阈值的区域可以由人或由执行对象识别的机器进行进一步检查。 以这种方式，可以准备并比较场景的复合视频图像。
-
公开(公告)号：US20130322697A1
公开(公告)日：2013-12-05
申请号：US13485369
申请日：2012-05-31
IPC分类号： G06K9/00
CPC分类号： G06T7/246 , G06T2207/10024 , G06T2207/20101 , G06T2207/20104 , G06T2207/30236
摘要： A method and system for estimating the average speed of a moving object based on an attribute of the moving object present within the captured image data is disclosed. A plurality of images of the moving object are recorded using an image sensor that senses the ambient light or other electromagnetic radiation reflected or emitted by the moving object. Each image is captured at a different capture time. The image sensor is preferably located at a fixed or substantially fixed location when imaging the moving object. An area of interest of the moving object is located within the image data of the first image. An attribute of the moving object is then calculated for the first image. For at least a second image, the same attribute is calculated for the same area of interest of the moving object. The attribute calculations for the first and at least second images are then used to determine the average speed of the moving object. The attribute may be the cross-sectional area of the area of interest of the moving object.
摘要翻译： 公开了一种基于拍摄图像数据中存在的移动物体的属性来估计移动物体的平均速度的方法和系统。 使用感测由移动物体反射或发射的环境光或其他电磁辐射的图像传感器记录运动物体的多个图像。 每个图像在不同的拍摄时间被捕获。 当对移动物体进行成像时，图像传感器优选地位于固定或基本上固定的位置。 移动物体的感兴趣区域位于第一图像的图像数据内。 然后针对第一图像计算移动对象的属性。 对于至少第二个图像，为运动对象的相同感兴趣区域计算相同的属性。 然后，使用第一和至少第二图像的属性计算来确定移动物体的平均速度。 该属性可以是移动物体的感兴趣区域的横截面积。
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.015 秒)
