改进的GDT-YOLOV3目标检测算法

唐悦; 吴戈; 朴燕

doi:doi:10.37188/yjyxs20203508.0852

液晶与显示, 2020, 35 (8): 852, 网络出版: 2020-08-18

改进的GDT-YOLOV3目标检测算法

Improved algorithm of GDT-YOLOV3 image target detection

论文大纲

唐悦吴戈朴燕

作者单位

长春理工大学电子信息工程学院, 吉林长春 130022

目标检测卷积神经网络密集连接网络 target detection convolutional neural network YOLOV3 YOLOV3 densenet K-means K-means

摘要

为了解决视频图像中目标检测准确率低、速度慢等问题, 本文提出了一种基于YOLOV3改进的目标检测方法。通过引入GIOU Loss, 可解决原IOU无法直接优化的非重叠部分问题, 在借鉴了密集连接网络的思想之后, 将YOLOV3中的3个残差块更换为3个密集块, 并结合Max Pooling加强密集连接块之间的特征传递, 重新替换IOU和原网络的连接结构, 检测设计出新的网络结构后, 减少了参数量, 增强了特征的复用与融合, 最终实现了优于原方法的效果。实验结果表明: 改进的GDT-YOLOV3算法与原有的算法相比, 无论是在简单还是复杂交通场景中都有较优秀的检测效果, 本文所提出的算法平均检出准确率高达92.77% , 速度达到25.3 f/s, 基本满足了实时性。此外在检测精度上, 改进的GDT-YOLOV3算法要优于SSD512、YOLOV2与YOLOV3算法。

Abstract

In order to solve the problems of low accuracy and slow speed of target detection in video images, an improved YOLOV3-based object detection method is proposed. By introducing GIOU Loss, the non-overlapping part problem that the original IOU cannot directly optimize can be solved. After drawing on the idea of densely connected networks, the three residual blocks in YOLOV3 are replaced with three dense blocks, and the denseness is combined with Max Pooling to strengthen the denseness. After transferring the features between the connected blocks, and replacing the IOU and the original network to detect the connection structure, a new network structure is designed. The number of parameters is reduced, the feature reuse and fusion are enhanced, and the effect is better than the original method. The experimental results show that comparing with the original algorithm, the improved GDT-YOLOV3 algorithm has excellent results in both simple and complex traffic scenarios. The average detection accuracy of the algorithm proposed in this paper is up to 92.77%, and the speed has reached 25.3 f/s, which basically meets the real-time performance. In addition, in terms of detection accuracy, the improved GDT-YOLOV3 performs better than SSD512, YOLOV2, and YOLOV3.

参考文献

[1] 刘博艺, 程杰仁, 唐湘滟, 等．复杂动态环境下运动车辆的识别方法[J]．计算机科学与探索, 2017, 11(1): 134-143．

LIU B Y, CHENG J R, TANG X Y, et al. Moving vehicles recognition in complex dynamic environment [J]. Journal of Frontiers of Computer Science & Technology, 2017, 11(1): 134-143. (in Chinese)

[2] LI H, FU K, YAN M L, et al. Vehicle detection in remote sensing images using denoizing-based convolutional neural networks [J]. Remote Sensing Letters, 2017, 8(3): 262-270.

[3] 吴言枫, 王延杰, 孙海江, 等. 复杂动背景下的“低小慢”目标检测技术[J]. 中国光学, 2019, 12(4): 853-865.

WU Y F, WANG Y J, SUN H J, et al. LSS-target detection in complex sky backgrounds [J]. Chinese Optics, 2019, 12(4): 853-865. (in Chinese)

[4] 高文, 朱明, 贺柏根, 等. 目标跟踪技术综述 [J]. 中国光学, 2014, 7(3): 365-375.

GAO W, ZHU M, HE B G,et al. Overview of target tracking technology [J]. Chinese Optics, 2014, 7(3): 365-375.

[5] 赵永强, 饶元, 董世鹏, 等.深度学习目标检测方法综述 [J]. 中国图象图形学报, 2020, 25(4):629-654. (in Chinese)

ZHAO Y Q, RAO Y, DONG S P, et al. Survey on deep learning object detection [J]. Journal of Image and Graphics, 2020, 25(4):629-654. (in Chinese)

[6] 姜文涛,张驰,张晟翀,等. 多尺度特征图融合的目标检测[J]. 中国图象图形学报, 2019, 24(11):1918-1931.

JIANG W T, ZHANG C, ZHANG S C, et al. Multiscale feature map fusion algorithm for target detection [J]. Journal of Image and Graphics, 2019, 24(11):1918-1931. (in Chinese)

[7] 杨丹,戴芳. 运动目标检测的ViBe算法改进 [J]. 中国图象图形学报, 2018, 23(12):1813-1828.

YANG D, DAI F. Improved ViBe algorithm for detection of moving objects [J]. Journal of Image and Graphics, 2018, 23(12):1813-1828. (in Chinese)

[8] 董潇潇, 何小海, 吴晓红, 等．基于注意力掩模融合的目标检测算法[J]．液晶与显示, 2019, 34(8): 825-833．

DONG X X, HE X H, WU X H, et al. Object detection algorithm based on attention mask fusion [J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(8): 825-833. (in Chinese)

[9] 葛雯, 史正伟．改进YOLOV3算法在行人识别中的应用[J]．计算机工程与应用, 2019, 55(20): 128-133．

GE W, SHI Z W. Application of improved YoLOV3 algorithm in pedestrian identification [J]. Computer Engineering and Applications, 2019, 55(20): 128-133. (in Chinese)

[10] 梁华, 宋玉龙, 钱锋, 等．基于深度学习的航空对地小目标检测[J]．液晶与显示, 2018, 33(9): 793-800．

LIANG H, SONG Y L, QIAN F, et al. Detection of small target in aerial photography based on deep learning [J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(9): 793-800. (in Chinese)

[11] 李云鹏, 侯凌燕, 王超．基于YOLOv3的自动驾驶中运动目标检测[J]．计算机工程与设计, 2019, 40(4): 1139-1144．

LI Y P, HOU L Y, WANG C. Moving objects detection in automatic driving based on YOLOv3 [J]. Computer Engineering and Design, 2019, 40(4): 1139-1144. (in Chinese)

[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.

[13] REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6517-6525.

[14] DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks [C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona: ACM, 2016: 379-387.

[15] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks [C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2261-2269.

[16] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.

唐悦, 吴戈, 朴燕. 改进的GDT-YOLOV3目标检测算法[J]. 液晶与显示, 2020, 35(8): 852. TANG Yue, WU Ge, PIAO Yan. Improved algorithm of GDT-YOLOV3 image target detection[J]. Chinese Journal of Liquid Crystals and Displays, 2020, 35(8): 852.

改进的GDT-YOLOV3目标检测算法

关于本站 Cookie 的使用提示

全站搜索

改进的GDT-YOLOV3目标检测算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索