论文标题
SPFCN：选择并修剪全卷积网络，用于实时停车位检测
SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection
论文作者
论文摘要
对于配备自动停车系统的车辆，停车位检测的准确性和速度至关重要。但是，高准确性是以低速或昂贵的计算设备的价格获得的，这对许多汽车制造商来说都是敏感的。在本文中，我们提出了使用CNN（卷积神经网络）的检测器，以更快的速度和较小的模型大小，同时保持准确性。为了实现最佳平衡，我们制定了一种策略，以选择最佳的接受场并在每个训练时期自动修剪冗余通道。所提出的模型能够共同检测停车位的角落和线路特征，同时平均实时进行有效地运行。该模型在2.3 GHz CPU核心上的帧速率约为30 fps，产生了停车位插槽角定位误差为1.51 $ \ pm $ 2.14 cm（std。err。），插槽检测准确性为98 \％，通常满足速度和准确性在机板移动终端的需求。
For vehicles equipped with the automatic parking system, the accuracy and speed of the parking slot detection are crucial. But the high accuracy is obtained at the price of low speed or expensive computation equipment, which are sensitive for many car manufacturers. In this paper, we proposed a detector using CNN(convolutional neural networks) for faster speed and smaller model size while keeps accuracy. To achieve the optimal balance, we developed a strategy to select the best receptive fields and prune the redundant channels automatically after each training epoch. The proposed model is capable of jointly detecting corners and line features of parking slots while running efficiently in real time on average processors. The model has a frame rate of about 30 FPS on a 2.3 GHz CPU core, yielding parking slot corner localization error of 1.51$\pm$2.14 cm (std. err.) and slot detection accuracy of 98\%, generally satisfying the requirements in both speed and accuracy on on-board mobile terminals.
