| 基于改进卷积神经网络的动态障碍物检测方法 |
| |
| 引用本文： | 孙凯,何明祥,张红,蒋纪威.基于改进卷积神经网络的动态障碍物检测方法[J].计算机应用与软件,2019,36(2):235-239,263. |
| |
| 作者姓名： | 孙凯 何明祥 张红 蒋纪威 |
| |
| 作者单位： | 山东科技大学计算机科学与工程学院 山东青岛266590;山东科技大学计算机科学与工程学院 山东青岛266590;山东科技大学计算机科学与工程学院 山东青岛266590;山东科技大学计算机科学与工程学院 山东青岛266590 |
| |
| 基金项目： | 山东省社会科学基金规划项目 |
| |
| 摘 要： | 针对传统卷积神经网络在感兴趣目标较小的情况下对动态障碍物检测会出现结果不准确的问题,提出一种基于改进卷积神经网络的运动障碍物检测方法。该方法在层层抽取细节特征的基础上融入全局特征,利用全局特征修正细节特征的提取,利用Softmax层进行分类来获取图像的整体信息。实验结果表明,与传统卷积神经网络相比,改进卷积神经网络具有较低的时间复杂度,以及较高的识别率。
|
| 关 键 词： | 深度学习 卷积神经网络 障碍物检测 感兴趣区域 |
DYNAMIC OBSTACLE DETECTION BASED ON IMPROVED CONVOLUTION NEURAL NETWORK |
| |
| Sun Kai,He Mingxiang,Zhang Hong,Jiang Jiwei.DYNAMIC OBSTACLE DETECTION BASED ON IMPROVED CONVOLUTION NEURAL NETWORK[J].Computer Applications and Software,2019,36(2):235-239,263. |
| |
| Authors: | Sun Kai He Mingxiang Zhang Hong Jiang Jiwei |
| |
| Affiliation: | (College of Computer Science and Engineering,Shandong University of Science and Technology, Qingdao 266590,Shandong,China) |
| |
| Abstract: | Traditional convolution neural network can produce inaccurate results in dynamic obstacle detection when the target of interest is small. To solve this problem, we proposed moving obstacle detection method based on improved convolution neural network. The method integrated global features into detail feature extraction layer by layer. We used the global features to modify the extraction of detail features, and used the Softmax layer to classify to obtain the overall information of the image. The experimental results show that the improved convolution neural network has lower time complexity and higher recognition rate than the traditional convolution neural network. |
| |
| Keywords: | Deep learning Convolutional neural network Obstacle detection Region of interest |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
