稀疏样本条件下的舰船舷号检测与识别  

Ship hull number detection and recognition under sparse samples

作　　者：洪汉玉[1,2] 陈冰川 马雷 张必银[3] Hong Hanyu;Chen Bingchuan;Ma Lei;Zhang Biyin(School of Electrical and Information Engineering,Wuhan Institute of Technology,Wuhan 430205,China;Hebei Proviacial Key Laboratory of Optical Information and Pattern Recognition,Wuhan Institute of Technology,Wuhan 430205,China;China Shipbuilding Industry Corporation No.709 Research Institute,Wuhan 430074,China)

机构地区：[1]武汉工程大学电气信息学院,武汉430205 [2]武汉工程大学光学信息与模式识别湖北省重点实验室,武汉430205 [3]中国船舶重工集团公司第七〇九研究所,武汉430074

出　　处：《中国图象图形学报》2023年第4期984-1003,共20页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62171329,62201406);武汉市知识创新专项(2022010801010351)。

摘　　要：目的舰船舷号检测识别是海面态势感知的关键技术,精准的舷号检测识别对海洋权益保护具有重要意义。但目前没有公开数据提供支持。为此,本文先构建了一个真实场景下的稀疏舰船舷号数据集(sparse ship hull number dataset in real scene,SSHN-RS),包含3004幅舰船图像,共计11328个舷号字符,覆盖了多国、各类、水平、倾斜、背景简单、背景复杂、光线不佳和被遮挡的舰船舷号样本,是一个具有挑战性的数据集。基于SSHN-RS,开展舰船舷号检测识别研究,其主要难点在于:1)样本稀疏,模型容易过拟合;2)舷号字符分布密集,网络难以充分提取各字符特征;3)部分字符存在嵌套区域和相似区域,网络会识别出大量冗余结果。针对上述难点,提出了一种基于多视角渐进式上下文解耦的舰船舷号检测识别算法。方法首先,引入一个固定中心和最大化面积的随机透视变换技术,在不增加样本数量的前提下扩充舷号姿态,实现了数据增广,提升了模型的泛化能力;其次,提出了一个渐进式上下文解耦技术,先通过依次擦除舷号各字符生成一系列新样本,再利用特征提取网络提取和融合各样本的多尺度特征,不仅减少字符上下文信息对特征学习的干扰,而且再次增广了数据;最后,在测试阶段,提出了一个掩码间扰动抑制技术,先根据预测结果采用与渐进式上下文解耦技术类似的方法生成新样本并重新进行预测,再引入一个1维非极大值抑制技术去除预测结果中错误的冗余字符,输出最佳检测识别结果,进一步优化网络性能。结果在SSHN-RS上采用主流实例分割算法进行定性和定量评估。在定量评估上,本文算法舷号的检测精确率、召回率、F值和识别率分别可达0.9854,0.9576,0.9713,0.9018,均优于其他算法。相比指标排名第2的算法,分别提高了4.51%,3.45%,3.97%,8.83%;在定性评估上,本文算法更适合舰船舷号检测识别�Objective Ship hull number detection and recognition can be as the key technologies for marine awareness.It is essential for the preservation of maritime rights and interests.However,it is required to data-driven researches in support of ship hull number detection and recognition.Therefore,we develop a sparse ship hull number dataset in real scene(SSHN-RS),which contains 3004 images with a total of 11328 hull numbers.The challenging SSHN-RS dataset is fea⁃tured of ship hull numbers of various countries,hull numbers of various types,horizontal hull numbers,inclined hull num⁃bers,hull numbers with complex background,hull numbers with simple background,poorly illuminated hull numbers and partially occluded hull numbers.We carry out SSHN-RS-related research on ship hull number detection and recognition.The main challenges are required to be resolved on three aspects as following:1)the hull number samples are sparse,which causes over-fitting of the network,2)the features of hull number are densely distributed,which is challenged to learn some of the hull number characteristics fully,and 3)some hull number have its nested areas and a high degree of similarity,which is costly for large number of redundant results.Method To resolve these problems mentioned above,we demonstrate a ship hull number detection and recognition algorithm in terms of multi-view progressive context decoupling.First,a random perspective transformation technology with fixed center and maximized area is illustrated.To realize data augmentation and improve the generalization ability of the model,the hull number spatial attitude is extended without increasing the number of samples.Second,a progressive context decoupling technology is proposed.A series of new samples are first generated by sequentially erasing each character of the hull number,and the feature extraction network is then used to extract and fuse the multi-scale features of each sample.It can reduce the influence of feature-contextual infor⁃mation on feature learning and rich the da

关 键 词：稀疏样本 公开数据集 舰船舷号检测与识别 实例分割 数据增广 渐进式上下文解耦 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]