专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明授权

US09009156B1 System for automatic data clustering utilizing bio-inspired computing models 有权
标题翻译：使用生物启发计算模型的自动数据聚类系统
公开(公告)号：US09009156B1
公开(公告)日：2015-04-14
申请号：US12590574
申请日：2009-11-10
申请人： Qin Jiang , Yang Chen
发明人： Qin Jiang , Yang Chen
IPC分类号： G06F17/30
CPC分类号： G06F15/1735 , G06N3/0409 , G06N3/0418 , G06N3/0436
摘要： Described is a system for automatic data clustering which utilizes bio-inspired computing models. The system performs operations of mapping a set of input data into a feature space using a bio-inspired computing model. A number of clusters inside the set of input data is then determined by finding an optimal vigilance parameter using a bio-inspired computing model. Finally, the set of input data is clustered based on the determined number of clusters. The input data is mapped with a Freeman's KIII network, such that each data point is mapped into a KIII network response. Furthermore, the number of clusters is determined using the fuzzy adaptive resonance theory (ART), and the data is clustered using the fuzzy c-means method. Clustering quality measures are used to compute an objective function to evaluate the quality of clustering.
摘要翻译：描述了一种利用生物启发计算模型的自动数据聚类系统。系统执行使用生物启发的计算模型将一组输入数据映射到特征空间的操作。然后通过使用生物启发的计算模型找到最佳警戒参数来确定输入数据集合内的多个群集。最后，基于所确定的群集数量对该组输入数据进行聚类。输入数据用Freeman的KIII网络映射，使得每个数据点被映射到KIII网络响应。此外，使用模糊自适应共振理论（ART）确定簇的数量，并且使用模糊c-means方法对数据进行聚类。聚类质量测度用于计算目标函数，以评估聚类质量。

82. 发明授权

US09008366B1 Bio-inspired method of ground object cueing in airborne motion imagery 有权
标题翻译：空中运动图像中地面物体提示的生物灵感方法
公开(公告)号：US09008366B1
公开(公告)日：2015-04-14
申请号：US13938196
申请日：2013-07-09
申请人： HRL Laboratories, LLC
发明人： Kyungnam Kim , Changsoo S. Jeong , Deepak Khosla , Yang Chen , Shinko Y. Cheng , Alexander L. Honda , Lei Zhang
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/6202 , G06T7/246 , G06T2207/10016 , G06T2207/10032 , G06T2207/30196 , G06T2207/30232 , G06T2207/30241
摘要： Described is method for object cueing in motion imagery. Key points and features are extracted from motion imagery, and features between consecutive image frames of the motion imagery are compared to identify similar image frames. A candidate set of matching keypoints is generated by matching keypoints between the similar image frames. A ground plane homography model that fits the candidate set of matching keypoints is determined to generate a set of correct matching keypoints. Each image frame of a set of image frames within a selected time window is registered into a reference frame's coordinate system using the homography transformation. A difference image is obtained between the reference frame and each registered image frame, resulting in multiple difference images. The difference images are then accumulated to calculate a detection image which is used for detection of salient regions. Object cues for surveillance use are produced based on the detected salient regions.
摘要翻译：描述了运动图像中对象提示的方法。从运动图像中提取关键点和特征，并比较运动图像的连续图像帧之间的特征，以识别相似的图像帧。通过匹配相似图像帧之间的关键点来生成候选的匹配关键点集合。确定适合匹配关键点候选组的地平面单应性模型，以生成一组正确的匹配关键点。在所选择的时间窗口内的一组图像帧的每个图像帧使用单变图变换登记到参考系的坐标系中。在参考帧和每个注册的图像帧之间获得差分图像，导致多个差分图像。然后累积差分图像以计算用于检测突出区域的检测图像。基于检测到的突出区域产生用于监视使用的对象线索。

83. 发明授权

US08973594B2 Tent peg 有权
标题翻译：帐篷钉
公开(公告)号：US08973594B2
公开(公告)日：2015-03-10
申请号：US13261624
申请日：2011-09-20
申请人： Kirsty Burgess , Edward Joseph Khoury
发明人： Kirsty Burgess , Edward Joseph Khoury
IPC分类号： E04H15/62
CPC分类号： E04H15/62
摘要： Described is tent peg that provides easy storage and transport to reduce the likelihood of the tent peg being lost. The tent peg comprises a shaft having and a head comprising a body having an arm extending therefrom. The arm comprises a first aperture adjacent to the body and a second aperture located between the first aperture and a distal end of the arm. The first aperture is formed to receive a shaft of a first further tent peg in an opposite orientation. Additionally, the second aperture is formed to receive a shaft of a second further tent peg in the same orientation as the tent beg. Further, the shaft of the second further tent peg is receivable in a first aperture of the first further tent peg. Therefore, multiple tent pegs can be interconnected with each tent peg in the opposite orientation to the adjacent tent pegs.
摘要翻译：描述了提供容易的储存和运输以减少帐篷钉丢失的可能性的帐篷钉。帐篷钉包括具有头部的轴，头部包括具有从其延伸的臂的主体。臂包括邻近主体的第一孔和位于第一孔和臂的远端之间的第二孔。第一孔被形成为接收处于相反方向的第一另外的帐篷钉的轴。另外，第二孔被形成为以与帐篷乞求相同的方向接收第二另外的帐篷钉的轴。此外，第二另外的帐篷钉的轴可以接收在第一另外的帐篷钉的第一孔中。因此，多个帐篷钉可以与每个帐篷钉相互连接，与相邻的帐篷钉相反。

84. 发明授权

US08965115B1 Adaptive multi-modal detection and fusion in videos via classification-based-learning 有权
标题翻译：通过基于分类的学习，视频中的自适应多模态检测和融合
公开(公告)号：US08965115B1
公开(公告)日：2015-02-24
申请号：US14100886
申请日：2013-12-09
申请人： HRL Laboratories, LLC
发明人： Deepak Khosla , Alexander L. Honda , Yang Chen , Shinko Y. Cheng , Kyungnam Kim , Lei Zhang , Changsoo S. Jeong
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00664 , G06K9/3241 , G06K9/6264 , G06K9/629
摘要： Described is a system for object detection using classification-based learning. A fusion method is selected, then a video sequence is processed to generate detections for each frame, wherein a detection is a representation of an object candidate. The detections are fused to generate a set of fused detections for each frame. The classification module generates a classification score labeling each fused detection based on a predetermined classification threshold. Otherwise, a token indicating that the classification module has abstained from generating a classification score is generated. The scoring module produces a confidence score for each fused detection based on a set of learned parameters from the learning module and the set of fused detections. The set of fused detections are filtered by the accept-reject module based on one of the classification score or the confidence score. Finally, a set of final detections representing an object is output.
摘要翻译：描述了使用基于分类的学习的对象检测系统。选择融合方法，然后处理视频序列以产生每个帧的检测，其中检测是对象候选的表示。检测被融合以产生用于每个帧的一组融合检测。分类模块基于预定分类阈值生成标记每个融合检测的分类分数。否则，生成表示分类模块已经放弃生成分类分数的令牌。评分模块基于来自学习模块的一组学习参数和融合检测集合，为每个融合检测产生置信度分数。基于分类分数或置信度分数之一，接受拒绝模块对融合检测集合进行过滤。最后，输出一组表示对象的最终检测。

85. 发明授权

US08928815B1 System and method for outdoor scene change detection 有权
标题翻译：室外场景变化检测系统及方法
公开(公告)号：US08928815B1
公开(公告)日：2015-01-06
申请号：US14205362
申请日：2014-03-11
申请人： HRL Laboratories, LLC
发明人： Terrell N. Mundhenk , A. Arturo Flores
IPC分类号： H04N9/64 , H04N5/14 , H04N11/20
CPC分类号： H04N5/147 , G06T7/254 , G06T7/90
摘要： Described is a system for scene change detection. The system receives an input image (current frame) from a video stream. The input image is color conditioned to generate a color conditioned image. A sliding window is used to segment the input image into a plurality boxes. Descriptors are extracted from each box of the color conditioned image. Thereafter, differences in the descriptors are identified between a current frame and past frames. The differences are attenuated to generate a descriptor attenuation factor αi. Initial scores are generated for each box based on the descriptor attenuation factor αi. The initial scores are filtered to generate a set of conspicuity scores for each box, the set of conspicuity scores being reflective of the conspicuity of each box in the image. Finally, the conspicuity scores are presented to the user or provided to other systems for further processing.
摘要翻译：描述了用于场景变化检测的系统。系统从视频流接收输入图像（当前帧）。输入图像经过颜色调节以产生色彩图像。使用滑动窗口将输入图像分割成多个框。描述符是从色条图像的每个框中提取出来的。此后，在当前帧和过去帧之间识别描述符中的差异。差异被衰减以产生描述符衰减因子αi。基于描述符衰减因子αi为每个框生成初始分数。过滤初始分数以产生每个框的一组显着性分数，该显着性分数集反映了图像中每个框的显着性。最后，将显着性得分呈现给用户或提供给其他系统进行进一步处理。

86. 发明授权

US08875718B2 Method for mult-layer eyelash painting 有权
标题翻译：多层睫毛涂抹方法
公开(公告)号：US08875718B2
公开(公告)日：2014-11-04
申请号：US13399945
申请日：2012-02-17
申请人： Daniel Phu Dinh
发明人： Daniel Phu Dinh
IPC分类号： A41G3/00 , A41G5/02 , A45D44/00
CPC分类号： A41G5/02 , A45D44/00
摘要： A method for multi-layered eyelash painting is described. The method is directed to fastening a user's eyelashes against the user's face and then painting one layer of eyelashes at a time in a multi-layered approach. The eyelash paint is applied to the user's eyelashes one layer at a time such that eyelash paint is applied to a first layer of eyelashes and, thereafter, eyelash paint is applied to a second layer of eyelashes, thereby providing a user with eyelashes having eyelash paint attached thereto.
摘要翻译：描述了一种多层睫毛涂装方法。该方法旨在将用户的睫毛紧紧贴靠在使用者的脸上，然后以多层次的方式一次涂一层睫毛。睫毛涂料一次一层地施用于使用者的睫毛，使得睫毛涂料施加到第一层睫毛上，然后将睫毛涂料施加到第二层睫毛上，从而为使用者提供具有睫毛涂料的睫毛附在其上。

87. 发明授权

US08837839B1 Method for recognition and pose estimation of multiple occurrences of multiple objects in visual images 有权
标题翻译：用于识别和姿态估计多个对象在视觉图像中的方法
公开(公告)号：US08837839B1
公开(公告)日：2014-09-16
申请号：US12938722
申请日：2010-11-03
申请人： David J. Huber , Deepak Khosla
发明人： David J. Huber , Deepak Khosla
IPC分类号： G06K9/62 , G06K9/36 , G06K9/64 , G06K9/32
CPC分类号： G06K9/6218 , G06K9/4671
摘要： Described is a system for multiple-object recognition in visual images. The system is configured to receive an input test image comprising at least one object. Keypoints representing the object are extracted using a local feature algorithm. The keypoints from the input test image are matched with keypoints from at least one training image stored in a training database, resulting in a set of matching keypoints. A clustering algorithm is applied to the set of matching keypoints to detect inliers among the set of matching keypoints. The inliers and neighboring keypoints in a vicinity of the inliers are removed from the input test image. An object label and an object boundary for the object are generated, and the object in the input test image is identified and segmented. Also described is a method and computer program product for multiple-object recognition in visual images.
摘要翻译：描述了一种在视觉图像中进行多目标识别的系统。该系统被配置为接收包括至少一个对象的输入测试图像。使用局部特征算法提取表示对象的关键点。来自输入测试图像的关键点与来自存储在训练数据库中的至少一个训练图像的关键点匹配，从而产生一组匹配的关键点。将聚类算法应用于匹配关键点集合，以检测匹配关键点集合之间的内联。从入口测试图像中删除内部值附近的内联和相邻关键点。生成对象标签和对象边界，并且识别和分割输入测试图像中的对象。还描述了一种用于视觉图像中的多目标识别的方法和计算机程序产品。

88. 发明授权

US08774517B1 System for identifying regions of interest in visual imagery 有权
标题翻译：用于识别视觉图像中的感兴趣区域的系统
公开(公告)号：US08774517B1
公开(公告)日：2014-07-08
申请号：US12982713
申请日：2010-12-30
申请人： Deepak Khosla , Rajan Bhattacharyya , Terrell N. Mundhenk , David J. Huber
发明人： Deepak Khosla , Rajan Bhattacharyya , Terrell N. Mundhenk , David J. Huber
IPC分类号： G06K9/00
CPC分类号： G06K9/00771 , G06K9/00993 , G06K9/4623 , G06K9/629
摘要： The present invention relates to a system for identifying regions of interest in visual imagery. The system is configured to receive a series of consecutive frames representing a scene as captured from N sensors. The frames include at least a current frame and a previous frame. A surprise map can be generated based on features found in the current frame and the previous frame. The surprise map having a plurality of values corresponding to spatial locations within the scene. Based on the values, a surprise in the scene can be identified if a value in the surprise map exceeds a predetermined threshold.
摘要翻译：本发明涉及用于识别视觉图像中的感兴趣区域的系统。该系统被配置为从N个传感器接收一系列表示场景的连续帧。帧至少包括当前帧和前一帧。可以基于当前帧和前一帧中发现的特征生成惊喜图。惊奇地图具有对应于场景内的空间位置的多个值。基于这些值，如果惊奇图中的值超过预定阈值，则可以识别场景中的惊喜。

89. 发明授权

US08762305B1 Method and system for dynamic task selection suitable for mapping external inputs and internal goals toward actions that solve problems or elicit rewards 有权
标题翻译：用于动态任务选择的方法和系统，适用于将外部输入和内部目标映射到解决问题或引发奖励的动作
公开(公告)号：US08762305B1
公开(公告)日：2014-06-24
申请号：US13287953
申请日：2011-11-02
申请人： Suhas E. Chelian , Narayan Srinivasa
发明人： Suhas E. Chelian , Narayan Srinivasa
IPC分类号： G06F15/18 , G06F17/00 , G06N5/02 , G06N3/00 , G06N99/00
CPC分类号： G06N3/008 , G06N3/08 , G06N99/005 , Y10S706/903
摘要： The present invention relates to a system for mapping external inputs and internal goals toward actions that solve problems or elicit external rewards. The present invention allows an instructor to test and train an agent to perform dynamic task selection (executive control) by using a schema that computes the agent's emotional and motivational states from reward/punishment inputs and sensory inputs (visual, auditory, kinematic, tactile, olfactory, somatosensory, and motor inputs). Specifically, the invention transforms the sensory inputs into unimodal and bimodal spatio-temporal schemas that are combined with the reward/punishment inputs and with the emotional and motivation states to create an external/internal schema (EXIN schema), that provides a compressed representation assessing the agent's emotions, motivations, and rewards. The invention uses the EXIN schema to create a motor schema to be executed by the agent to dynamically perform the task selected by the instructor.
摘要翻译：本发明涉及一种用于将外部输入和内部目标映射到解决问题或引发外部奖励的动作的系统。本发明允许教师通过使用从奖励/惩罚输入和感觉输入（视觉，听觉，运动学，触觉学习和计算机学习）来计算代理人的情绪和动机状态的模式来测试和训练代理来执行动态任务选择（执行控制）嗅觉，体感和运动输入）。具体来说，本发明将感官输入转换成单峰和双峰时空模式，其与奖励/惩罚输入以及情绪和动机状态结合以创建外部/内部模式（EXIN模式），其提供压缩表示评估代理人的情绪，动机和奖励。本发明使用EXIN模式来创建要由代理执行的运动模式以动态地执行教师所选择的任务。

90. 发明授权

US08734276B2 Transforming dart 有权
标题翻译：变形飞镖
公开(公告)号：US08734276B2
公开(公告)日：2014-05-27
申请号：US13626877
申请日：2012-09-25
申请人： JAKKS Pacific, Inc.
发明人： Dominic Laurienzo , Rip Lopusnak , Brandon Giraldez , Dennis Lee Chi Wai , Eli Halpert
IPC分类号： A63B65/02
CPC分类号： A63H27/005 , A63H33/18
摘要： A transforming dart mechanism is described. The transforming dart mechanism includes an inner collar and an outer collar. A dart body is positioned through the inner collar, while fins are pivotally attached with the outer collar. A deployable canopy is affixed with the fins. Thus, in operation, a user can position the fins and deployable canopy against the dart body in a collapsed state. When in the collapsed state, a user can shoot the toy dart horn a to dart gun and upon contacting a target, the fins and deployable canopy expand into an expanded state.
摘要翻译：描述了转换飞镖机制。变形飞镖机构包括内部轴环和外部轴环。飞镖体通过内部轴环定位，而翼片与外部轴环枢转地连接。一个可展开的篷盖贴上翅片。因此，在操作中，使用者可以在折叠状态下将翅片和可展开的冠盖定位在飞镖体上。当处于倒塌状态时，用户可以拍摄玩具飞镖角a到飞镖枪，并且在接触目标时，鳍片和可展开的冠层扩展到扩展状态。

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