Contextual boost for object detection
    1.
    发明授权
    Contextual boost for object detection 有权
    对象检测的上下文提升

    公开(公告)号:US08538081B2

    公开(公告)日:2013-09-17

    申请号:US13371847

    申请日:2012-02-13

    IPC分类号: G06K9/00

    摘要: Aspects of the present invention includes systems and methods for generating detection models that consider contextual information of an image patch and for using detection models that consider contextual information. In embodiments, a multi-scale image context descriptor is generated to represent the contextual cues in multiple parameters, such as spatial, scaling, and color spaces. In embodiments, a classification context is defined using the contextual features and is used in a contextual boost classification scheme. In embodiments, the contextual boost propagates contextual cues to larger coverage through iterations to improve the detection accuracy.

    摘要翻译: 本发明的方面包括用于产生考虑图像补丁的上下文信息以及使用考虑上下文信息的检测模型的检测模型的系统和方法。 在实施例中,生成多尺度图像上下文描述符以表示诸如空间,缩放和颜色空间的多个参数中的上下文提示。 在实施例中,使用上下文特征来定义分类上下文,并且在上下文增强分类方案中使用。 在实施例中,上下文提升通过迭代将上下文提示传播到更大的覆盖范围,以提高检测精度。

    Ray image modeling for fast catadioptric light field rendering
    2.
    发明授权
    Ray image modeling for fast catadioptric light field rendering 有权
    用于快速反射折射光场渲染的射线图像建模

    公开(公告)号:US08432435B2

    公开(公告)日:2013-04-30

    申请号:US13207224

    申请日:2011-08-10

    IPC分类号: H04N7/12

    摘要: A catadioptric camera creates image light fields from a 3D scene by creating ray images defined as 2D arrays of ray-structure picture-elements (ray-xels). Each ray-xel captures light intensity, mirror-reflection location, and mirror-incident light ray direction. A 3D image is then rendered from the ray images by combining the corresponding ray-xels.

    摘要翻译: 反射折射照相机通过创建被定义为射线结构图像元素(ray-xels)的2D阵列的射线图像,从3D场景创建图像光场。 每个ray-xel捕获光强度,镜面反射位置和镜像入射光线方向。 然后通过组合相应的射线 - xels从射线图像渲染3D图像。

    Local Difference Pattern Based Local Background Modeling For Object Detection
    3.
    发明申请
    Local Difference Pattern Based Local Background Modeling For Object Detection 有权
    基于局部差异模式的本地背景建模对象检测

    公开(公告)号:US20120219224A1

    公开(公告)日:2012-08-30

    申请号:US13198382

    申请日:2011-08-04

    IPC分类号: G06K9/46

    摘要: Systems and methods for object detection that consider background information are presented. Embodiments of the present invention utilizing a feature called Local Difference Pattern (LDP), which is more discriminative for modeling local background image features. In embodiments, the LDP feature is used to train detection models. In embodiments, the LDP feature may be used in detection to differentiate different image background conditions and adaptively adjust classification to yield higher detection rates.

    摘要翻译: 介绍了考虑背景信息的物体检测系统和方法。 利用称为局部差异模式(LDP)的特征的本发明的实施例,其更为区分对本地背景图像特征的建模。 在实施例中,LDP特征用于训练检测模型。 在实施例中,LDP特征可以用于检测以区分不同的图像背景条件并且自适应地调整分类以产生更高的检测率。

    IMPORTANCE FILTERING FOR IMAGE RETARGETING
    4.
    发明申请
    IMPORTANCE FILTERING FOR IMAGE RETARGETING 有权
    图像重定向的重要过滤

    公开(公告)号:US20120121204A1

    公开(公告)日:2012-05-17

    申请号:US13099228

    申请日:2011-05-02

    IPC分类号: G06K9/40

    CPC分类号: G06T3/0012 G06K9/4671

    摘要: A content-aware image retargeting technique uses an “importance filtering” technique to preserve important information in the resizing of an image. The image saliency is first filtered, guided by the image itself to achieve a structure-consistent importance map. The pixel importance is then used as the key constraint in computing the gradient map of pixel shifts from the original resolution to the target resolution. Finally the shift gradient is integrated across the image by a weighted filtering process to construct a smooth pixel shift-map and render the target image. The weight is again controlled by the pixel importance. The two filtering processes enforce the maintaining of structural consistency while preserving the important contents in the target image. The simple nature of the present filter operations allow for real-time applications and easy extension to video retargeting, as the structural constraints from the original image naturally convey the temporal coherence between frames.

    摘要翻译: 内容感知图像重定向技术使用“重要性过滤”技术在图像大小调整中保留重要信息。 图像显着性首先被过滤,由图像本身引导,以实现结构一致的重要性图。 然后将像素重要性用作计算从原始分辨率到目标分辨率的像素偏移的梯度图的关键约束。 最后,通过加权滤波过程在图像上整合偏移梯度,以构建平滑像素移位图并渲染目标图像。 重量再次受到像素重要性的控制。 两个过滤过程强制维持结构一致性,同时保留目标图像中的重要内容。 由于来自原始图像的结构约束自然地传达帧之间的时间一致性,本过滤器操作的简单性质允许实时应用并且容易地扩展到视频重定向。

    Multi-scale, perspective context, and cascade features for object detection
    5.
    发明授权
    Multi-scale, perspective context, and cascade features for object detection 有权
    多尺度,透视上下文和用于对象检测的级联特征

    公开(公告)号:US08897575B2

    公开(公告)日:2014-11-25

    申请号:US13350375

    申请日:2012-01-13

    摘要: Systems and methods for object detection are presented herein. Embodiments of the present invention utilizing a cascade feature, one or more features at different scales, one or more multi-scale features in combination with a perspective feature, or combinations thereof to detect an object of interest in an input image. In embodiments, the various features are used to train classifiers. In embodiments, the trained classifiers are used in detecting an object of interest in one or more input images.

    摘要翻译: 本文介绍了对象检测的系统和方法。 本发明的实施例利用级联特征,不同尺度的一个或多个特征,与透视特征组合的一个或多个多尺度特征或其组合来检测输入图像中的感兴趣对象。 在实施例中,各种特征用于训练分类器。 在实施例中,训练分类器用于检测一个或多个输入图像中的感兴趣对象。

    Importance filtering for image retargeting
    6.
    发明授权
    Importance filtering for image retargeting 有权
    图像重新定位的重要性过滤

    公开(公告)号:US08494302B2

    公开(公告)日:2013-07-23

    申请号:US13099228

    申请日:2011-05-02

    IPC分类号: G06K9/40 G06K15/02

    CPC分类号: G06T3/0012 G06K9/4671

    摘要: A content-aware image retargeting technique uses an “importance filtering” technique to preserve important information in the resizing of an image. The image saliency is first filtered, guided by the image itself to achieve a structure-consistent importance map. The pixel importance is then used as the key constraint in computing the gradient map of pixel shifts from the original resolution to the target resolution. Finally the shift gradient is integrated across the image by a weighted filtering process to construct a smooth pixel shift-map and render the target image. The weight is again controlled by the pixel importance. The two filtering processes enforce the maintaining of structural consistency while preserving the important contents in the target image. The simple nature of the present filter operations allow for real-time applications and easy extension to video retargeting, as the structural constraints from the original image naturally convey the temporal coherence between frames.

    摘要翻译: 内容感知图像重定向技术使用“重要性过滤”技术在图像大小调整中保留重要信息。 图像显着性首先被过滤,由图像本身引导,以实现结构一致的重要性图。 然后将像素重要性用作计算从原始分辨率到目标分辨率的像素偏移的梯度图的关键约束。 最后,通过加权滤波过程在图像上整合偏移梯度,以构建平滑像素移位图并渲染目标图像。 重量再次受到像素重要性的控制。 两个过滤过程强制维持结构一致性,同时保留目标图像中的重要内容。 由于来自原始图像的结构约束自然地传达帧之间的时间一致性,本过滤器操作的简单性质允许实时应用并且容易地扩展到视频重定向。

    Adaptive threshold for object detection
    7.
    发明授权
    Adaptive threshold for object detection 有权
    物体检测的自适应阈值

    公开(公告)号:US08948522B2

    公开(公告)日:2015-02-03

    申请号:US13198412

    申请日:2011-08-04

    IPC分类号: G06K9/62 G06K9/46

    摘要: Systems and methods for developing and using adaptive threshold values for different input images for object detection are disclosed. In embodiments, detector response histogram-based systems and methods train models for predicting optimal threshold values for different images. In embodiments, when training the model, an optimal threshold value for an image is defined as the value that maximizes the reduction of false positive image patches while preserving as many true positive image patches as possible. Once trained, the model may be used to set different threshold values for different images by inputting a detector response histogram for the image patches of an image into the model to determine a threshold value for detection.

    摘要翻译: 公开了用于开发和使用用于对象检测的不同输入图像的自适应阈值的系统和方法。 在实施例中,基于检测器响应直方图的系统和方法训练用于预测不同图像的最佳阈值的模型。 在实施例中,当训练模型时,图像的最佳阈值被定义为最大化假阳性图像斑块的减少的值,同时保留尽可能多的真正的正图像斑块。 一旦被训练,该模型可以用于通过将图像的图像块的检测器响应直方图输入到模型中来确定用于检测的阈值来为不同的图像设置不同的阈值。

    Local difference pattern based local background modeling for object detection
    8.
    发明授权
    Local difference pattern based local background modeling for object detection 有权
    基于局部差异模式的本地背景建模对象检测

    公开(公告)号:US08565482B2

    公开(公告)日:2013-10-22

    申请号:US13198382

    申请日:2011-08-04

    IPC分类号: G06K9/46 G06K9/62

    摘要: Systems and methods for object detection that consider background information are presented. Embodiments of the present invention utilizing a feature called Local Difference Pattern (LDP), which is more discriminative for modeling local background image features. In embodiments, the LDP feature is used to train detection models. In embodiments, the LDP feature may be used in detection to differentiate different image background conditions and adaptively adjust classification to yield higher detection rates.

    摘要翻译: 介绍了考虑背景信息的物体检测系统和方法。 利用称为局部差异模式(LDP)的特征的本发明的实施例,其更为区分对本地背景图像特征的建模。 在实施例中,LDP特征用于训练检测模型。 在实施例中,LDP特征可以用于检测以区分不同的图像背景条件并且自适应地调整分类以产生更高的检测率。

    Contextual Boost for Object Detection
    9.
    发明申请
    Contextual Boost for Object Detection 有权
    对象检测的上下文提升

    公开(公告)号:US20120219211A1

    公开(公告)日:2012-08-30

    申请号:US13371847

    申请日:2012-02-13

    IPC分类号: G06K9/62 G06K9/46

    摘要: Aspects of the present invention includes systems and methods for generating detection models that consider contextual information of an image patch and for using detection models that consider contextual information. In embodiments, a multi-scale image context descriptor is generated to represent the contextual cues in multiple parameters, such as spatial, scaling, and color spaces. In embodiments, a classification context is defined using the contextual features and is used in a contextual boost classification scheme. In embodiments, the contextual boost propagates contextual cues to larger coverage through iterations to improve the detection accuracy.

    摘要翻译: 本发明的方面包括用于产生考虑图像补丁的上下文信息以及使用考虑上下文信息的检测模型的检测模型的系统和方法。 在实施例中,生成多尺度图像上下文描述符以表示诸如空间,缩放和颜色空间的多个参数中的上下文提示。 在实施例中,使用上下文特征来定义分类上下文,并且在上下文增强分类方案中使用。 在实施例中,上下文提升通过迭代将上下文提示传播到更大的覆盖范围,以提高检测精度。

    Catadioptric projectors
    10.
    发明授权
    Catadioptric projectors 有权
    反射折射投影机

    公开(公告)号:US08201951B2

    公开(公告)日:2012-06-19

    申请号:US12488190

    申请日:2009-06-19

    IPC分类号: G03B21/14

    CPC分类号: H04N17/04 H04N9/3191

    摘要: Herein is presented a catadioptric projector by combining a commodity digital projector with additional optical units. By using specially shaped reflectors and/or refractors, a catadioptric projector can offer an unprecedented level of flexibility in aspect ratio, size, and field of view. Also presented, are methods to reduce projection artifacts in catadioptric projectors, such as distortions, scattering, and defocusing. By analysis of projection defocus of reflector and thin refractor based catadioptric projectors, it is shown that defocus blur can be interpreted as spatially-varying Gaussian blurs on an input image. Kernels are measured directly from a light transport matrix, T, and de-convolution is applied to optimize an input image. Practical uses of catadioptric projectors in panoramic and omni-directional projections are also demonstrated.

    摘要翻译: 这里通过将商品数字投影仪与附加光学单元组合而呈现出反折射投影仪。 通过使用特殊形状的反射器和/或折射器,反折射投影仪可以在宽高比,尺寸和视野方面提供前所未有的灵活性。 还提出了减少反射折射投影仪投影假象的方法,如扭曲,散射和散焦。 通过分析反射器和基于薄折射仪的反折射投影仪的投影散焦,可以看出散焦模糊可以解释为输入图像上的空间变化高斯模糊。 内核直接从光传输矩阵T测量,并且应用去卷积以优化输入图像。 反射折射投影仪在全景和全方位投影中的实际应用也得到了展示。