Neural network algorithms for motion stereo
Neural network algorithms for motion stereo
复制标题
运动立体神经网络算法
DOI：
10.1109/ijcnn.1989.118707
复制
发表时间：
1989
期刊：
影响因子：
--
通讯作者：
R. Chellappa
中科院分区：
文献类型：
--
作者：
Y. Zhou;R. Chellappa
运动立体声从图像帧序列推断深度信息。给出了运动立体声的批处理和递归神经网络算法。用离散神经网络表示视差场。批处理算法首先通过将所有图像的信息嵌入到网络的偏置输入中来集成这些信息。然后通过神经元评估进行匹配。与传统的批处理方法需要多次匹配不同，该算法只执行一次匹配过程。该方法使用递推最小二乘算法来更新网络的偏差输入。视差值由匹配后的神经元状态唯一确定。由于神经网络可以并行运行，偏置输入更新方案可以在线执行，因此采用这种算法的实时视觉系统非常有吸引力。文中还提出了一种定位遮挡像素的检测算法。给出了利用自然图像序列进行实验的结果。
Motion stereo infers depth information from a sequence of image frames. Both batch and recursive neural network algorithms for motion stereo are presented. A discrete neural network is used for representing the disparity field. The batch algorithm first integrates information from all images by embedding them into the bias inputs of the network. Matching is then carried out by neuron evaluation. This algorithm implements the matching procedure only once, unlike conventional batch methods requiring matching many times. The method uses a recursive least square algorithm to update the bias inputs of the network. The disparity values are uniquely determined by the neuron states after matching. Since the neural network can be run in parallel and the bias input updating scheme can be executed on line, a real-time vision system employing such an algorithm is very attractive. A detection algorithm for locating occluding pixels is also included. Experimental results using natural image sequences are given.<<ETX>>