论文标题
通过规范相关分析对单眼图像进行对象检测
Object Detection on Single Monocular Images through Canonical Correlation Analysis
论文作者
论文摘要
不使用额外的3-D数据（例如点云或深度图像）提供3-D信息，我们从单眼图像中检索了3-D对象信息。从单眼图像中恢复了高质量的预测深度图像，并将其馈送到具有相应单眼图像的2-D对象提案网络中。大多数使用两流入数数据的深度学习框架总是通过串联或添加来融合单独的数据，这些数据始终可以观看功能映射的每个部分都可以同等地对整个任务做出贡献。但是，当数据嘈杂并且信息太多时，这些方法不再有效地产生预测或分类。在本报告中，我们提出了一个二维CCA（规范相关分析）框架，以融合单眼图像，并为基本的计算机视觉任务（例如图像分类和对象检测）提供相应的预测深度图像。首先，我们使用一维CCA和Alexnet实施了不同的结构，以测试图像分类任务的性能。然后，我们用2D-CCA应用了这些结构之一进行对象检测。在这些实验中，我们发现我们提出的框架在将预测的深度图像作为输入中时的行为更好，该模型是从地面真实深度训练的模型。
Without using extra 3-D data like points cloud or depth images for providing 3-D information, we retrieve the 3-D object information from single monocular images. The high-quality predicted depth images are recovered from single monocular images, and it is fed into the 2-D object proposal network with corresponding monocular images. Most existing deep learning frameworks with two-streams input data always fuse separate data by concatenating or adding, which views every part of a feature map can contribute equally to the whole task. However, when data are noisy, and too much information is redundant, these methods no longer produce predictions or classifications efficiently. In this report, we propose a two-dimensional CCA(canonical correlation analysis) framework to fuse monocular images and corresponding predicted depth images for basic computer vision tasks like image classification and object detection. Firstly, we implemented different structures with one-dimensional CCA and Alexnet to test the performance on the image classification task. And then, we applied one of these structures with 2D-CCA for object detection. During these experiments, we found that our proposed framework behaves better when taking predicted depth images as inputs with the model trained from ground truth depth.
