会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 3. 发明授权
    • Stereo image processing device and method
    • 立体图像处理装置及方法
    • US08548226B2
    • 2013-10-01
    • US12711787
    • 2010-02-24
    • Morihiko SakanoMirai HiguchiTakuya NakaTakeshi ShimaShoji Muramatsu
    • Morihiko SakanoMirai HiguchiTakuya NakaTakeshi ShimaShoji Muramatsu
    • G06K9/00G06K9/44
    • G06T7/593G06T2207/10012
    • In stereo matching based on standard area matching, in order to suppress a decrease in matching accuracy, it is effective to adaptively change a matching area in accordance with the local properties of an image. However, this requires high calculation costs. Thus, the present invention provides a stereo image processing apparatus including an image pickup unit 101 configured to take a plurality of image data using a plurality of cameras, an image memory 102 configured to store the plurality of image data taken by the image pickup unit 101, a calculated disparity storage unit 105 configured to store disparity data determined based on the plurality of image data, a matching area control unit 103 configured to set a matching area for each pixel based on the plurality of data read from the image memory 102 and the disparity data read from the calculated disparity storage unit 105, and a disparity calculating unit 104 configured to perform matching on the image data based on the plurality of image data read from the image memory 102 and the matching area for each pixel set by the matching area control unit 103 to calculate disparity data.
    • 在基于标准区域匹配的立体匹配中,为了抑制匹配精度的降低,根据图像的局部特性自适应地改变匹配区域是有效的。 然而,这需要很高的计算成本。 因此,本发明提供了一种立体图像处理装置,其包括被配置为使用多个摄像机拍摄多个图像数据的图像拾取单元101,被配置为存储由图像拾取单元101拍摄的多个图像数据的图像存储器102 被配置为存储基于多个图像数据确定的视差数据的计算出的视差存储单元105,匹配区域控制单元103,被配置为基于从图像存储器102读取的多个数据来设置每个像素的匹配区域, 从计算出的视差存储单元105读取的视差数据和视差计算单元104,被配置为基于从图像存储器102读取的多个图像数据和由匹配区域设置的每个像素的匹配区域对图像数据进行匹配 控制单元103来计算视差数据。
    • 9. 发明授权
    • Neural network apparatus and learning method thereof
    • 神经网络装置及其学习方法
    • US5857178A
    • 1999-01-05
    • US872929
    • 1997-06-11
    • Tomohisa KimuraTakeshi Shima
    • Tomohisa KimuraTakeshi Shima
    • G06F15/18G06N3/063G06N3/08
    • G06N3/063G06N3/084
    • A neural network apparatus includes a neural network including at least two neuron layers each having a plurality of neurons and at least one synapse layer having a plurality of synapses each arranged between the neuron layers, each synapse storing a weight value between the neurons and multiplying the weight value with an output value from each of the neurons in the previous-stage neuron layer to output a product to the next-stage neuron layer, a section for causing an error signal between an output from the neural network and a desired output to back-propagate from an output-side neuron layer to an input-side neuron layer of the neural network, a learning control section for updating the weight value in the synapse on the basis of the error signal and the output value from the previous-stage neuron, and a selecting section for selecting a synapse whose weight value is to be updated by the learning control section when the learning control section is to update the weight values of a predetermined number of synapses in a predetermined order.
    • 神经网络装置包括包括至少两个神经元层的神经网络,每个神经元层具有多个神经元,并且至少一个具有多个突触的突触层,每个突起均布置在神经元层之间,每个突触存储神经元之间的权重值, 具有来自前一阶段神经元层中的每个神经元的输出值的权重值,以将产品输出到下一级神经元层,用于在神经网络的输出和期望的输出之间产生误差信号的部分 - 从输出侧神经元层向神经网络的输入侧神经元层传播,学习控制部分,用于基于误差信号和来自前一级神经元的输出值更新突触中的权重值 ,以及选择部,用于当学习控制部要更新ap的权重值时,通过学习控制部选择要更新其权重值的突触 以预定顺序重新确定突触数。