Ship detection based on enhanced YOLOv3 under complex environments
NIE Xin1,2, LIU Wen1,2, WU Wei3
1. School of Navigation, Wuhan University of Technology, Wuhan Hubei 430063, China; 2. Hubei Key Laboratory of Inland Navigation Technology(Wuhan University of Technology), Wuhan Hubei 430063, China; 3. School of Information Engineering, Wuhan University of Technology, Wuhan Hubei 430070, China
Abstract:In order to improve the intelligence level of waterway traffic safety supervision, and further improve the positioning precision and detection accuracy in the ship detection algorithms based on deep learning, based on the traditional YOLOv3, an enhanced YOLOv3 algorithm for ship detection was proposed. First, the prediction box uncertain regression was introduced in the network prediction layer in order to predict the uncertainty information of bounding box. Second, the negative logarithm likelihood function and improved binary cross entropy function were used to redesign the loss function. Then, the K-means clustering algorithm was used to redesign the scales of prior anchor boxes according to the shape of ship, and prior anchor boxes were evenly distributed to the corresponding prediction scales. During training phase, the data augmentation strategy was used to expand the number of training samples. Finally, the Non-Maximum Suppression (NMS) algorithm with Gaussian soft threshold function was used to post-process the prediction boxes. The comparison experiments of various improved methods and different object detection algorithms were conducted on real maritime video surveillance dataset. Experimental results show that, compared to the traditional YOLOv3 algorithm, the YOLOv3 algorithm with prediction box uncertainty information has the number of False Positives (FP) reduced by 35.42%, and the number of True Positives (TP) increased by 1.83%, thus improving the accuracy. The mean Average Precision (mAP) of the enhanced YOLOv3 algorithm on ship images reaches 87.74%, which is improved by 24.12% and 23.53% respectively compared to those of the traditional YOLOv3 algorithm and Faster R-CNN algorithm. The proposed algorithm has the number of images detected per second reaches 30.70, meeting the requirement of real-time detection. Experimental results indicate that the proposed algorithm can achieve high-precision, robust and real-time detection of ships under adverse weather and conditions such as fog weather and low-light condition as well as the complex navigation backgrounds.
聂鑫, 刘文, 吴巍. 复杂场景下基于增强YOLOv3的船舶目标检测[J]. 计算机应用, 2020, 40(9): 2561-2570.
NIE Xin, LIU Wen, WU Wei. Ship detection based on enhanced YOLOv3 under complex environments. Journal of Computer Applications, 2020, 40(9): 2561-2570.
[1] PRASAD D K, PRASATH C K, RAJAND D, et al. Object detection in a maritime environment:performance evaluation of background subtraction methods[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(5):1787-1802. [2] GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:580-587. [3] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2015:1440-1448. [4] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2015:91-99. [5] LIU W,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9905. Cham:Springer, 2016:21-37. [6] REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:779-788. [7] REDMON J,FARHADI A. YOLO9000:better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:6517-6525. [8] REDMON J,FARHADI A. YOLOv3:an incremental improvement[EB/OL].[2019-12-15]. https://arxiv.org/pdf/1804.02767.pdf. [9] 王新立, 江福才, 宁方鑫, 等. 基于改进卷积神经网络的船舶目标检测[J]. 中国航海,2018,41(2):41-45,51.(WANG X L, JIANG F C,NING F X,et al. Ship detection with improved convolutional neural network[J]. Navigation of China,2018,41(2):41-45,51.) [10] 陈从平, 吴喆, 吴杞, 等. 动态背景下航道船舶目标检测方法[J]. 三峡大学学报(自然科学版),2019,41(1):97-102. (CHEN C P,WU Z,WU Q,et al. Detection method of ship target in waterway under dynamic background[J]. Journal of China Three Gorges University (Natural Sciences),2019,41(1):97-102.) [11] 王言鹏, 杨飏, 姚远. 用于内河船舶目标检测的单次多框检测器算法[J]. 哈尔滨工程大学学报,2019,40(7):1258-1262. (WANG Y P,YANG Y,YAO Y. Single shot multibox detector for ships detection in inland waterway[J]. Journal of Harbin Engineering University,2019,40(7):1258-1262.) [12] 赵蓬辉, 孟春宁, 常胜江. 基于改进VGG网络的单阶段船舶检测算法[J]. 光电子·激光,2019,30(7):719-730.(ZHAO P H, MENG C N,CHANG S J. Single stage ship detection algorithm based on improved VGG network[J]. Journal of Optoelectronics·Laser,2019,30(7):719-730.) [13] 于洋, 李世杰, 陈亮, 等. 基于改进YOLO v2的船舶目标检测方法[J]. 计算机科学,2019,46(8):332-336.(YU Y,LI S J, CHEN L,et al. Ship target detection based on improved YOLO v2[J]. Computer Science,2019,46(8):332-336.) [14] 刘博, 王胜正, 赵建森, 等. 基于Darknet网络和YOLOv3算法的船舶跟踪识别[J]. 计算机应用,2019,39(6):1663-1668.(LIU B,WANG S Z,ZHAO J S,et al. Ship tracking and recognition based on Darknet network and YOLOv3 algorithm[J]. Journal of Computer Applications,2019,39(6):1663-1668.) [15] KIM K,HONG S,CHOI B,et al. Probabilistic ship detection and classification using deep learning[J]. Applied Sciences,2018,8(6):No. 936. [16] CHOI J, CHUN D, KIM H, et al. Gaussian YOLOv3:an accurate and fast object detector using localization uncertainty for autonomous driving[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE, 2019:502-511. [17] LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:2999-3007. [18] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019:658-666. [19] SHAO Z,WU W,WANG Z,et al. SeaShips:a large-scale precisely annotated dataset for ship detection[J]. IEEE Transactions on Multimedia,2018,20(10):2593-2604. [20] NIE X,YANG M,LIU R W. Deep neural network-based robust ship detection under different weather conditions[C]//Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference. Piscataway:IEEE,2019:47-52. [21] SHU X,PORIKLI F,AHUJA N. Robust orthonormal subspace learning:efficient recovery of corrupted low-rank matrices[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:3874-3881. [22] KANG Z,PENG C,CHENG Q. Robust PCA via nonconvex rank approximation[C]//Proceedings of the 2015 IEEE International Conference on Data Mining. Piscataway:IEEE,2015:211-220.