论文标题
端到端可训练的一阶段停车插槽检测整合了全球和本地信息
End-to-End Trainable One-Stage Parking Slot Detection Integrating Global and Local Information
论文作者
论文摘要
本文提出了一种可用于查看监视器（AVM）图像的端到端可训练的一阶段停车位检测方法。拟议的方法同时通过使用卷积神经网络（CNN）获取全球信息（停车位的入口，类型和占用）以及本地信息（位置和交界处的位置和方向），并将其集成以检测停车位及其属性。该方法将AVM图像划分为网格，并执行基于CNN的特征提取。对于网格的每个单元格，通过将卷积过滤器应用于提取的特征图来获得停车位的全局和本地信息。最终的检测结果是通过通过非最大抑制（NMS）整合停车位的全球和本地信息而产生的。由于所提出的方法使用没有区域建议阶段的完全卷积网络获得了停车位的大多数信息，因此它是可端到端的一阶段探测器。在实验中，使用公共数据集对该方法进行了定量评估，并通过显示99.77％的召回和精度，类型分类精度为100％，而占用分类精度为99.31％，同时每秒处理60帧。
This paper proposes an end-to-end trainable one-stage parking slot detection method for around view monitor (AVM) images. The proposed method simultaneously acquires global information (entrance, type, and occupancy of parking slot) and local information (location and orientation of junction) by using a convolutional neural network (CNN), and integrates them to detect parking slots with their properties. This method divides an AVM image into a grid and performs a CNN-based feature extraction. For each cell of the grid, the global and local information of the parking slot is obtained by applying convolution filters to the extracted feature map. Final detection results are produced by integrating the global and local information of the parking slot through non-maximum suppression (NMS). Since the proposed method obtains most of the information of the parking slot using a fully convolutional network without a region proposal stage, it is an end-to-end trainable one-stage detector. In experiments, this method was quantitatively evaluated using the public dataset and outperforms previous methods by showing both recall and precision of 99.77%, type classification accuracy of 100%, and occupancy classification accuracy of 99.31% while processing 60 frames per second.
