自监督学习HOG预测辅助任务下的车位检测方法  

Parking space detection method based on self-supervised learning HOG prediction auxiliary task

作　　者：刘磊 伍鹏[1] 谢凯[1,2] 程贝芝 盛冠群 LIU Lei;WU Peng;XIE Kai;CHENG Beizhi;SHENG Guanqun(School of Electronic Information,Yangtze University,Jingzhou Hubei 434023,China;Western Research Institute,Yangtze University,Karamay Xinjiang 834000,China;College of Computer and Information Technology,China Three Gorges University,Yichang Hubei 443002,China)

机构地区：[1]长江大学电子信息学院,湖北荆州434023 [2]长江大学西部研究院,新疆克拉玛依834000 [3]三峡大学计算机与信息学院,湖北宜昌443002

出　　处：《计算机应用》2023年第12期3933-3940,共8页journal of Computer Applications

基　　金：国家自然科学基金资助项目(42204111)。

摘　　要：针对智能车位管理系统中,光照变化、车位遮挡等因素导致车位预测的精度下降、有效性变差的问题,提出一种自监督学习方向梯度直方图(HOG)预测辅助任务下的车位检测方法。首先,设计预测图像遮挡部分HOG特征的自监督学习辅助任务,利用MobileViTBlock(light-weight,general-purpose,and Mobile-friendly Vision Transformer Block)综合图像全局信息,使模型更充分地学习图像的视觉表征,并提高模型的特征提取能力;其次,改进SE(Squeeze-and-Excitation)注意力机制,使模型在更低的计算开销上达到甚至高于原始SE注意力机制的效果;最后,将辅助任务训练的特征提取部分应用于下游的分类任务进行车位状态预测,在PKLot和CNRPark的混合数据集上进行实验。实验结果表明,所提模型在测试集上的准确率达到了97.49%,相较于RepVGG,遮挡预测准确率提高了5.46个百分点,与其他的车位检测算法相比进步较大。In the intelligent parking space management system,a decrease in accuracy and effectiveness of parking space prediction can be caused by factors such as illumination changes and parking space occlusion.To overcome this problem,a parking space detection method based on self-supervised learning HOG(Histogram of Oriented Gradient)prediction auxiliary task was proposed.Firstly,a self-supervised learning auxiliary task to predict the HOG feature in occluded part of image was designed,the visual representation of the image was learned more fully and the feature extraction ability of the model was improved by using the MobileViTBlock(light-weight,general-purpose,and Mobile-friendly Vision Transformer Block)to synthesize the global information of the image.Then,an improvement was made to the SE(Squeeze-and-Excitation)attention mechanism,thereby enabling the model to achieve or even exceed the effect of the original SE attention mechanism at a lower computational cost.Finally,the feature extraction part trained by the auxiliary task was applied to the downstream classification task for parking space status prediction.Experiments were carried out on the mixed dataset of PKLot and CNRPark.The experimental results show that the proposed model has the accuracy reached 97.49%on the test set;compared to RepVGG,the accuracy of occlusion prediction improves by 5.46 percentage points,which represents a great improvement compared with other parking space detection algorithms.

关 键 词：智能停车系统 自监督学习 方向梯度直方图 辅助任务 车位状态预测 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]