A Convolutional Neural Network for Automatic Analysis of Aerial Imagery
A Convolutional Neural Network for Automatic Analysis of Aerial Imagery
复制标题
用于航空图像自动分析的卷积神经网络
DOI：
10.1109/dicta.2014.7008084
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
A. Hodgson
中科院分区：
文献类型：
--
作者：
F. Maire;Luis Mejías Alvarez;A. Hodgson
本文介绍了一种新的方法来自动检测海洋物种的航空图像使用机器学习的方法。我们提出的系统的核心是卷积神经网络。我们比较这个可训练的分类器的基础上的颜色特征，熵和形状分析手工制作的分类器。实验表明，卷积神经网络优于手工制作的解决方案。我们还介绍了一个负的训练示例选择方法的情况下，原始训练集包括一个集合的标记图像，其中感兴趣的对象（正面的例子）已被标记的边界框。我们表明，从背景中挑选随机矩形并不一定是生成有用的反面例子的最佳方法。
This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.