面向航拍图像中工程车辆检测与识别的改进胶囊网络  

Improved capsule network method for engineering vehicles detection and recognition in aerial images

作　　者：钟映春[1] 郑海阳 张文祥 王波 罗志勇 Zhong Yingchun;Zheng Haiyang;Zhang Wenxiang;Wang Bo;Luo Zhiyong(Schol of Automation,Guangdong Uniersity of Technology,Guangzhou510006,China;Department of Electro-Mechanical Enginering,Guangdong Machinery Technician College,Guangzhou510450,China;Guanghou Ufly Technology Co.,Lud.,Guangzhou510630,China)

机构地区：[1]广东工业大学自动化学院,广州510006 [2]广东省机械技师学院机电工程系,广州510450 [3]广州市优飞信息科技有限公司,广州510630

出　　处：《中国图象图形学报》2022年第8期2380-2390,共11页Journal of Image and Graphics

基　　金：广东省自然科学基金项目(2018A0303130137);国家自然科学基金项目(61975248);广州市科技计划项目(202007040004)。

摘　　要：目的 利用无人机(unmanned aerial vehicle, UAV)巡检识别航拍图像中的工程车辆对于减少电力安全事故的发生具有重要意义。采用人工提取特征的经典模式识别方法或YOLOv5(you only look once v5)等深度学习算法识别无人机电力巡检航拍图像中的工程车辆,存在识别准确率低、模型参数规模大等问题。针对上述问题,提出一种改进的胶囊网络识别航拍图像中的工程车辆。方法 采用多层密集连接型方法改进原始胶囊网络结构,以提取图像中工程车辆更多的特征;改进了胶囊网络的动态路由方法,以提高胶囊网络的抗干扰能力;探索了网络层数和动态路由算法中关键参数对识别准确率的影响,以找到识别准确率最高时的参数。结果 实验结果表明:1)在所采用的算法模型中,本文方法的平均识别率(mean average precision, mAP)达到94.56%,明显高于其他方法。2)网络层数对识别准确率有很大影响,但二者之间并非单调线性关系。在本文的应用场景中,5层胶囊网络的识别准确率最高;此外,动态路由算法改进与否并不会影响识别准确率跟随网络层数的变化趋势。3)胶囊网络层数增加会降低识别效率,但是并不会明显增加参数规模,且参数规模与mAP无明显关联。结论 本文方法在获得较高识别准确率的同时具有参数规模较小的特点,为无人机在机载端识别目标物奠定了基础。Objective Electrical power lines construction, plays an important role in the urban development, especially the high-voltage power lines. Engineering vehicles are composed of excavators and wheeled cranes contexts, which are used in construction sites. If the engineering vehicle is working on site surrounding the high-voltage power line, its bucket or boom would probably enter the high-voltage breakdown range when they are lifted, which is very easy to result in accidents such as short circuit breakdowns. So, it is necessary to find out the adequate engineering vehicles working scenario near high-voltage power line. The multiple rotors unmanned aerial vehicle(UAV) is widely used to acquire amounts of aerial images for power lines inspection. The engineering vehicle information should be recognized from these aerial images manually in common. The classical pattern recognition methods and some deep learning models like you only look once version 5(YOLOv5) has been challenged to some issues of recognizing the engineering vehicle in acquired aerial image, such as inefficiency and inaccuracy. The classical pattern recognition method needs to manually extract the features. Some deep learning models usually have large parameter scale and complex network structure, and are not accurate enough while the training set is small. In order to solve these problems, our research demonstrated an improved capsule network model to recognize engineering vehicles from aerial images. Capsule network improvement is mainly on the two aspects as mentioned below: one is to improve the network structure of the capsule network model, and the other one is to improve the dynamic routing algorithm of the capsule network. Method First, we built up an image dataset, which includes 1 890 aerial images in total. The dataset is then separated into training set and testing set at a ratio of 4 ∶1. Next, we improved the network structure of capsule network through a multi-layer densely connected method to extract more features of the engineering veh

关 键 词：无人机航拍图像 工程车辆识别 胶囊网络 动态路由算法 密集连接型网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]