公开(公告)号：US20150306763A1

公开(公告)日：2015-10-29

申请号：US14788719

申请日：2015-06-30

Applicant: QUALCOMM Technologies Inc.

Inventor： Philip MEIER ,  Paul BENDER

IPC: B25J9/00

CPC classification number: B25J9/0081 ,  B25J9/1674 ,  B25J9/1697 ,  B25J19/023 ,  G05B19/41815 ,  G05B19/42 ,  G05B2219/39393 ,  G05B2219/40003 ,  G05B2219/40033 ,  G05B2219/40298 ,  Y10S901/03 ,  Y10S901/08

Abstract: Apparatus and methods for implementing learning by robotic devices. Attention of the robot may be manipulated by use of a spot-light device illuminating a portion of the aircraft undergoing inspection in order to indicate to inspection robot target areas requiring more detailed inspection. The robot guidance may be aided by way of an additional signal transmitted by the agent to the robot indicating that the object has been illuminated and attention switch may be required. The robot may initiate a search for the signal reflected by the illuminated area requiring its attention. Responsive to detecting the illuminated object and receipt of the additional signal, the robot may develop an association between the two events and the inspection task thereby storing a robotic context. The context of one robot may be shared with other devices in lieu of training so as to enable other devices to perform the task.

Abstract translation: 机器人设备实现学习的装置和方法。 机器人的注意可以通过使用照亮被检查的飞行器的一部分的点光装置来操纵，以指示检查机器人需要更详细检查的目标区域。 可以通过由代理向机器人发送的附加信号来辅助机器人引导，指示物体已被照亮并且可能需要注意力开关。 机器人可以开始搜索需要注意的照明区域反射的信号。 响应于检测照明物体和接收附加信号，机器人可以在两个事件和检查任务之间形成关联，从而存储机器人上下文。 一个机器人的上下文可以与其他设备共享以代替训练，以便使其他设备能够执行任务。

公开(公告)号：US09172890B2

公开(公告)日：2015-10-27

申请号：US13932905

申请日：2013-07-01

Applicant: Qualcomm Technologies, Inc.

Inventor： Assaf Weissman ,  Pia Zobel

IPC: H04N5/235

CPC classification number: H04N5/2355

Abstract: A method, apparatus, and manufacture for generating an HDR image is provided. An original image is received from an HDR interlaced sensor that includes at least two fields captured with different exposures. The fields are separated from each other to provide separate images, and each of the separate images is upscaled. Next, blending is performed on each of the upscaled separate images to generate a high-dynamic range image, and ghost identification is performed on the high-dynamic range image. Subsequently, detail identification is performed on the high-dynamic range image. The detail identification includes identifying areas in the non-ghost areas of the high-dynamic range image that have details, and modifying the high-dynamic image by replacing each of the areas identified to have details with the corresponding area from the original image.

Abstract translation: 提供了一种用于生成HDR图像的方法，装置和制造。 从HDR隔行传感器接收原始图像，其包括用不同曝光捕获的至少两个场。 这些字段彼此分离以提供单独的图像，并且每个单独的图像被放大。 接下来，对每个放大的分离图像进行混合以产生高动态范围图像，并对高动态范围图像执行重影识别。 随后，在高动态范围图像上执行细节识别。 细节识别包括识别具有细节的高动态范围图像的非重影区域中的区域，以及通过将识别为具有与原始图像相对应的区域的细节的每个区域进行修改来修改高动态图像。

公开(公告)号：US20150301638A1

公开(公告)日：2015-10-22

申请号：US14788367

申请日：2015-06-30

Applicant: Qualcomm Technologies, Inc.

Inventor： Daniel D. Alexander ,  Timothy L. Blankenship ,  Yassar A. Ali ,  Andrew Chan ,  Feihua Zhang

IPC: G06F3/041

CPC classification number: G06F3/041 ,  G06F3/038

Abstract: System and method for substantially reducing an involvement of an applications processor in receiving data from a touchscreen display. In one aspect, the system includes a controller may be configured in an autonomous mode where it automatically measures the touchscreen display based configuration information received from the applications processor, determines notable events based on the measurement data, stores data and event identifiers related to the notable events in a memory, and sends a notification to the applications processor when event data is available In another aspect, the system includes a controller that filters user interactions events and transmits data related to only notable events to the applications processor. Because of the autonomous and event filtering operations of the touchscreen controller, there are substantially less communications between the controller and the applications processor. This improves the speed and efficiency of the applications processor.

Abstract translation: 用于大大减少应用处理器从触摸屏显示器接收数据的参与的系统和方法。 在一个方面，系统包括控制器可以被配置成自主模式，其中它自动测量从应用处理器接收的基于触摸屏显示的配置信息，基于测量数据确定显着的事件，存储与显着的相关的数据和事件标识符 在事件数据可用的情况下，向应用处理器发送通知。另一方面，该系统包括一个控制器，该控制器过滤用户交互事件，并向应用处理器发送与仅显着事件相关的数据。 由于触摸屏控制器的自主和事件滤波操作，控制器和应用处理器之间的通信量基本较少。 这提高了应用处理器的速度和效率。

公开(公告)号：US09165245B2

公开(公告)日：2015-10-20

申请号：US14275663

申请日：2014-05-12

Applicant: QUALCOMM TECHNOLOGIES INC.

Inventor： Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran ,  Jeffrey Alexander Levin ,  Venkat Rangan ,  Erik Christopher Malone

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

CPC classification number: G06N3/049 ,  G06N3/063 ,  G06N3/08

Abstract: Apparatus and methods for partial evaluation of synaptic updates in neural networks. In one embodiment, a pre-synaptic unit is connected to a several post synaptic units via communication channels. Information related to a plurality of post-synaptic pulses generated by the post-synaptic units is stored by the network in response to a system event. Synaptic channel updates are performed by the network using the time intervals between a pre-synaptic pulse, which is being generated prior to the system event, and at least a portion of the plurality of the post synaptic pulses. The system event enables removal of the information related to the portion of the post-synaptic pulses from the storage device. A shared memory block within the storage device is used to store data related to post-synaptic pulses generated by different post-synaptic nodes. This configuration enables memory use optimization of post-synaptic units with different firing rates.

Abstract translation: 用于部分评估神经网络中突触更新的装置和方法。 在一个实施例中，突触前单元经由通信信道连接到几个后突触单元。 与由突触后单元产生的多个突触后脉冲相关的信息由网络响应于系统事件存储。 突触信道更新由网络使用在系统事件之前产生的预触觉脉冲与多个突触后脉冲的至少一部分之间的时间间隔来执行。 系统事件使得能够从存储设备去除与突触后部分脉冲相关的信息。 存储设备内的共享存储器块用于存储与由不同的突触后节点产生的突触后脉冲相关的数据。 这种配置使得具有不同发射速率的突触后单元的存储器使用优化成为可能。

公开(公告)号：US09148593B2

公开(公告)日：2015-09-29

申请号：US14472131

申请日：2014-08-28

Applicant: QUALCOMM Technologies, Inc.

Inventor： Dudi Vakrat ,  Noam Korem ,  Victor Pinto

IPC: G06K9/00 ,  H04N5/357 ,  G06T5/00 ,  H04N5/217 ,  H04N5/232 ,  H04N9/64

CPC classification number: H04N5/357 ,  G06T5/00 ,  G06T5/002 ,  H04N5/217 ,  H04N5/23229 ,  H04N9/646

Abstract: A noise reduction apparatus for digital cameras is presented that includes groups of one or more connected non-linear filter units. Each of the filter unit groups are driven by decimated input image data at a different level of decimation and the output of at least one of these filter unit groups serves as one of a plurality of inputs to another filter unit group driven at a different decimation level. Filtered image data from one or more filter unit groups is adaptively combined in response to one or more image metrics related to one or more local regional image characteristics.

Abstract translation: 提供了一种用于数字照相机的降噪装置，其包括一个或多个连接的非线性滤波器单元的组。 滤波器单元组中的每一个以抽取的不同抽取级别的抽取的输入图像数据驱动，并且这些滤波器单元组中的至少一个的输出用作到以不同抽取级别驱动的另一个滤波器单元组的多个输入之一 。 响应于与一个或多个局部区域图像特征相关的一个或多个图像度量自适应地组合来自一个或多个过滤器单元组的滤波图像数据。

公开(公告)号：US09110689B2

公开(公告)日：2015-08-18

申请号：US13680399

申请日：2012-11-19

Applicant: QUALCOMM TECHNOLOGIES, INC.

Inventor： Jean-Jacques Lecler

IPC: G06F9/00 ,  G06F17/50 ,  G06F9/445 ,  G06F9/38

CPC classification number: G06F9/445 ,  G06F9/3875 ,  G06F17/505 ,  G06F2217/84

Abstract: The optimal configuration of a number of optional pipeline stages within the data paths of systems-on-chip is determined by application of a solver. The solver includes variables such as: the placement of modules physically within the floorplan of the chip; the signal propagation time; the logic gate switching time; the arrival time, after a clock edge, of a signal at each module port; the arrival time at each pipeline stage; and the Boolean value of the state of activation of each optional pipeline stage. The optimal configuration ensures that a timing constraint is met, if possible, with the lowest possible cost of pipeline stages.

Abstract translation: 通过应用求解器确定片上系统的数据路径内的多个可选流水线级的最佳配置。 求解器包括以下变量：将模块物理放置在芯片的平面图中; 信号传播时间; 逻辑门切换时间; 每个模块端口的信号到达时间，时钟沿之后; 每个流水线阶段的到达时间; 以及每个可选流水线阶段的激活状态的布尔值。 最佳配置确保了在可能的情况下满足流水线阶段可能的最低成本的时序约束。

公开(公告)号：US09098658B2

公开(公告)日：2015-08-04

申请号：US13898540

申请日：2013-05-21

Applicant: QUALCOMM TECHNOLOGIES, INC.

Inventor： Daniel Michel ,  Xavier Van Ruymbeke ,  Pascal Godet ,  Xavier Leloup

IPC: G06F17/50

CPC classification number: G06F17/5031 ,  G06F17/505 ,  G06F2217/84

Abstract: A method and NoC design tool is disclosed that automatically maps the paths listed in a timing report and the unit size in an area report to the topology of a NoC and displays the paths and unit sizes in a GUI. The tool can also automatically add pipeline stages, separated by the maximum delay allowed in the timing budget, in order to achieve timing closure in an automated way.

Abstract translation: 公开了一种方法和NoC设计工具，其将定时报告中列出的路径和区域报告中的单位大小自动映射到NoC的拓扑，并在GUI中显示路径和单位大小。 该工具还可以自动添加流水线阶段，由时间预算允许的最大延迟分隔，以便以自动方式实现时序收敛。

公开(公告)号：US09092738B2

公开(公告)日：2015-07-28

申请号：US14198446

申请日：2014-03-05

Applicant: QUALCOMM TECHNOLOGIES INC.

Inventor： Eugene M. Izhikevich ,  Botond Szatmary ,  Csaba Petre ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

IPC: G06N3/10 ,  G06N3/08 ,  G05B13/02

CPC classification number: G06N3/08 ,  G05B13/027 ,  G06N3/049 ,  G06N3/10

Abstract: A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The software and hardware engines are optimized to take into account short-term and long-term synaptic plasticity in the form of LTD, LTP, and STDP.

Abstract translation: 公开了一种简单的格式，并被称为基本网络描述（END）。 该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。 这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。 软件和硬件引擎经过优化考虑了LTD，LTP和STDP形式的短期和长期突触可塑性。

公开(公告)号：US09082198B2

公开(公告)日：2015-07-14

申请号：US13656442

申请日：2012-10-19

Applicant: Qualcomm Technologies, Inc.

Inventor： Ayelet Mashiah

IPC: H04N5/225 ,  G06T7/20 ,  G06T7/00 ,  G06T13/80

CPC classification number: G06T7/204 ,  G06T7/12 ,  G06T7/149 ,  G06T7/215 ,  G06T7/248 ,  G06T13/80 ,  G06T2207/10016 ,  G06T2207/20116

Abstract: Embodiments are directed towards automatically creating a cinemagraph on at least an imaging device, where the cinemagraph can be created without additional user interaction beyond capturing an initial sequence of images, and indicating that a cinemagraph is to be created from the sequence. Automatic creation of the cinemagraph includes selecting an anchor frame within the sequence and aligning the other frames to the anchor frame. Detection and segmentation of moving objects within the sequence, with respect to the anchor frame are performed. A mask is generated and refined. Segmentation of masks are then unified, and combined with a background from the anchor frame to generate an animated sequence.

Abstract translation: 实施例涉及在至少一个成像设备上自动创建电影节目，其中可以创建电影节目，而不需要额外的用户交互，而不是捕获图像的初始序列，并且指示要从序列中创建电影节目。 影片的自动创建包括选择序列内的锚帧，并将其他帧与锚帧对齐。 执行序列内相对于锚帧的移动对象的检测和分割。 生成和修饰面具。 然后将掩码的分割统一起来，并与来自锚帧的背景组合以生成动画序列。

公开(公告)号：US20150054991A1

公开(公告)日：2015-02-26

申请号：US14472131

申请日：2014-08-28

Applicant: QUALCOMM Technologies, Inc.

Inventor： Dudi Vakrat ,  Noam Korem ,  Victor Pinto

IPC: H04N5/357 ,  H04N9/64 ,  G06T5/00

CPC classification number: H04N5/357 ,  G06T5/00 ,  G06T5/002 ,  H04N5/217 ,  H04N5/23229 ,  H04N9/646

Abstract: A noise reduction apparatus for digital cameras is presented that includes groups of one or more connected non-linear filter units. Each of the filter unit groups are driven by decimated input image data at a different level of decimation and the output of at least one of these filter unit groups serves as one of a plurality of inputs to another filter unit group driven at a different decimation level. Filtered image data from one or more filter unit groups is adaptively combined in response to one or more image metrics related to one or more local regional image characteristics.

Abstract translation: 提供了一种用于数字照相机的降噪装置，其包括一个或多个连接的非线性滤波器单元的组。 滤波器单元组中的每一个以抽取的不同抽取级别的抽取的输入图像数据驱动，并且这些滤波器单元组中的至少一个的输出用作到以不同抽取级别驱动的另一个滤波器单元组的多个输入之一 。 响应于与一个或多个局部区域图像特征相关的一个或多个图像度量自适应地组合来自一个或多个过滤器单元组的滤波图像数据。