《计算机应用》唯一官方网站 ›› 2021, Vol. 41 ›› Issue (11): 3228-3233.DOI: 10.11772/j.issn.1001-9081.2021010073
所属专题: 人工智能
章悦1, 张亮1,2(), 谢非1,2, 杨嘉乐1, 张瑞1, 刘益剑1,2
收稿日期:
2021-01-14
修回日期:
2021-03-25
接受日期:
2021-04-06
发布日期:
2021-04-26
出版日期:
2021-11-10
通讯作者:
张亮
作者简介:
章悦(1995—),女,江苏南京人,硕士研究生,CCF 会员,主要研究方向:深度学习、计算机视觉、目标检测、实例分割
Yue ZHANG1, Liang ZHANG1,2(), Fei XIE1,2, Jiale YANG1, Rui ZHANG1, Yijian LIU1,2
Received:
2021-01-14
Revised:
2021-03-25
Accepted:
2021-04-06
Online:
2021-04-26
Published:
2021-11-10
Contact:
Liang ZHANG
About author:
ZHANG Yue, born in 1995, M. S. candidate. Her research interests include deep learning, computer vision, target detection, instance segmentation摘要:
在交通安全领域,道路抛洒物易引发交通事故,构成了交通安全隐患。针对传统抛洒物检测方式识别率低、对于多类抛洒物检测效果不佳等问题,提出了一种基于实例分割模型CenterMask优化的道路抛洒物检测算法。首先,使用空洞卷积优化的残差网络ResNet50作为主干神经网络来提取特征并进行多尺度处理;然后,通过距离交并比(DIoU)函数优化的全卷积单阶段(FCOS)目标检测器实现对抛洒物的检测和分类;最后,使用空间注意力引导掩膜作为掩膜分割分支来实现对于目标形态的分割,并采用迁移学习的方式实现模型的训练。实验结果表明,所提算法对于抛洒物目标的检测率为94.82%,相较常见实例分割算法Mask R-CNN,所提的道路抛洒物检测算法在边界框检测上的平均精度(AP)提高了8.10个百分点。
中图分类号:
章悦, 张亮, 谢非, 杨嘉乐, 张瑞, 刘益剑. 基于实例分割模型优化的道路抛洒物检测算法[J]. 计算机应用, 2021, 41(11): 3228-3233.
Yue ZHANG, Liang ZHANG, Fei XIE, Jiale YANG, Rui ZHANG, Yijian LIU. Road abandoned object detection algorithm based on optimized instance segmentation model[J]. Journal of Computer Applications, 2021, 41(11): 3228-3233.
算法 | AP | AP50 | AP75 | APs | APm | APl |
---|---|---|---|---|---|---|
CenterMask | 54.30 | 89.50 | 65.60 | 47.20 | 66.80 | 59.30 |
CenterMask+DIoU | 59.40 | 89.20 | 67.50 | 53.30 | 74.80 | 53.50 |
CenterMask+ Dilated CNN | 60.40 | 91.30 | 71.00 | 49.80 | 73.90 | 66.60 |
本文算法 | 61.70 | 89.40 | 71.50 | 50.40 | 76.50 | 71.50 |
表1 道路抛洒物检测优化算法结果对比 ( %)
Tab. 1 Result comparison of optimization algorithms for road abandoned object detection
算法 | AP | AP50 | AP75 | APs | APm | APl |
---|---|---|---|---|---|---|
CenterMask | 54.30 | 89.50 | 65.60 | 47.20 | 66.80 | 59.30 |
CenterMask+DIoU | 59.40 | 89.20 | 67.50 | 53.30 | 74.80 | 53.50 |
CenterMask+ Dilated CNN | 60.40 | 91.30 | 71.00 | 49.80 | 73.90 | 66.60 |
本文算法 | 61.70 | 89.40 | 71.50 | 50.40 | 76.50 | 71.50 |
算法 | AP/% | 单张图像 平均耗时/s | 检测率/% | |
---|---|---|---|---|
边界框检测 | 掩膜分割 | |||
CenterMask | 54.30 | 52.40 | 0.28 | 93.39 |
Mask R-CNN | 53.60 | 50.30 | 0.35 | 93.14 |
YOLACT | 42.80 | 41.60 | 0.11 | 92.56 |
本文算法 | 61.70 | 54.10 | 0.29 | 94.82 |
表2 不同算法测试性能对比
Tab. 2 Comparison of test performance of different algorithms
算法 | AP/% | 单张图像 平均耗时/s | 检测率/% | |
---|---|---|---|---|
边界框检测 | 掩膜分割 | |||
CenterMask | 54.30 | 52.40 | 0.28 | 93.39 |
Mask R-CNN | 53.60 | 50.30 | 0.35 | 93.14 |
YOLACT | 42.80 | 41.60 | 0.11 | 92.56 |
本文算法 | 61.70 | 54.10 | 0.29 | 94.82 |
1 | KHATOONABADI S H, BAJIC I V. Video object tracking in the compressed domain using spatio-temporal Markov random field [J]. IEEE Transactions on Image Processing, 2013, 22(1): 300-313. 10.1109/tip.2012.2214049 |
2 | ASVADI A, PEIXOTO P, NUNES U. Detection and tracking of moving objects using 2.5D motion grid [C]// Proceedings of the IEEE 18th International Conference on Intelligent Transportation Systems. Piscataway: IEEE, 2015: 788-793. 10.1109/itsc.2015.133 |
3 | 汪贵平,马力旺,郭璐,等.高速公路抛洒物事件图像检测算法[J].长安大学学报(自然科学版),2017,37(5):81-88. 10.18057/icass2018.p.123 |
WANG G P, MA L W, GUO L, et al. Image detection algorithm for incident of discarded things in highway [J]. Journal of Chang’an University (Natural Science Edition), 2017, 37(5): 81-88. 10.18057/icass2018.p.123 | |
4 | 李清瑶,邹皓,赵群,等.基于帧间差分自适应法的车辆抛洒物检测[J].长春理工大学学报(自然科学版),2018,41(4):108-113. |
LI Q Y, ZOU H, ZHAO Q, et al. Vehicles throwing detection based on inter-frame difference adaptive method [J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2018, 41(4): 108-113. | |
5 | 金瑶,张锐,尹东.城市道路视频中小像素目标检测[J].光电工程,2019,46(9):74-81. 10.32657/10356/144136 |
JIN Y, ZHANG R, YIN D. Object detection for small pixel in urban roads videos [J]. Opto-Electronic Engineering, 2019, 46(9): 74-81. 10.32657/10356/144136 | |
6 | 程文冬,马勇,魏庆媛.驾驶人手机通话行为中基于图像特征决策融合的手势识别方法[J].交通运输工程学报,2019,19(4):171-181. 10.3969/j.issn.1671-1637.2019.04.016 |
CHENG W D, MA Y, WEI Q Y. Hand gesture recognition method in driver’s phone-call behavior based on decision fusion of image features [J]. Journal of Traffic and Transportation Engineering, 2019, 19(4): 171-181. 10.3969/j.issn.1671-1637.2019.04.016 | |
7 | 陆德彪,郭子明,蔡伯根,等.基于深度数据的车辆目标检测与跟踪方法[J].交通运输系统工程与信息,2018,18(3):55-62. 10.16097/j.cnki.1009-6744.2018.03.009 |
LU D B, GUO Z M, CAI B G, et al. A vehicle detection and tracking method based on range data [J]. Journal of Transportation System Engineering and Information Technology, 2018, 18(3): 55-62. 10.16097/j.cnki.1009-6744.2018.03.009 | |
8 | 孙首群,刘康亚,刘硕妍,等.铁路客运站复杂环境中的运动目标检测[J].交通运输工程学报,2013,13(3):113-120. 10.3969/j.issn.1671-1637.2013.03.016 |
SUN S Q, LIU K Y, LIU S Y, et al. Moving target detection in complex environment of railway station [J]. Journal of Traffic and Transportation Engineering, 2013, 13(3): 113-120. 10.3969/j.issn.1671-1637.2013.03.016 | |
9 | 周雨阳,龚艺,姚琳,等.无人机广域视频的机动车交通参数计算及分析[J].交通运输系统工程与信息,2015,15(6):67-73. 10.3969/j.issn.1009-6744.2015.06.011 |
ZHOU Y Y, GONG Y, YAO L, et al. Calculation and analysis of the traffic parameters of vehicles based on the wide-area drone video [J]. Journal of Transportation System Engineering and Information Technology, 2015, 15(6): 67-73. 10.3969/j.issn.1009-6744.2015.06.011 | |
10 | 郑文博,王坤峰,王飞跃.基于贝叶斯生成对抗网络的背景消减算法[J].自动化学报,2018,44(5):878-890. |
ZHENG W B, WANG K F, WANG F Y. Background subtraction algorithm with Bayesian generative adversarial networks [J]. Acta Automatica Sinica, 2018, 44(5): 878-890. | |
11 | 卢胜男,李小和.结合双向光流约束的特征点匹配车辆跟踪方法[J].交通运输系统工程与信息,2017,17(4):76-82. 10.16097/j.cnki.1009-6744.2017.04.012 |
LU S N, LI X H. Vehicle tracking method using feature point matching combined with bidirectional optical flow [J]. Journal of Transportation System Engineering and Information Technology, 2017, 17(4): 76-82. 10.16097/j.cnki.1009-6744.2017.04.012 | |
12 | 蔡彪,沈宽,付金磊,等.基于Mask R-CNN的铸件X射线DR图像缺陷检测研究[J].仪器仪表学报,2020,41(3):61-69. |
CAI B, SHEN K, FU J L, et al. Research on defect detection of X-ray DR images of casting based on Mask R-CNN [J]. Chinese Journal of Scientific Instrument, 2020, 41(3): 61-69. | |
13 | TIAN Z, SHEN C H, CHEN H, et al. FCOS: fully convolutional one-stage object detection [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 9626-9635. 10.1109/iccv.2019.00972 |
14 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
15 | YAMASHITA T, FURUKAWA H, FUJIYOSHI H. Multiple skip connections of dilated convolution network for semantic segmentation [C]// Proceedings of the 2018 25th IEEE International Conference on Image Processing. Piscataway: IEEE, 2018: 1593-1597. 10.1109/icip.2018.8451033 |
16 | ZHU X Z, CHENG D Z, ZHANG Z, et al. An empirical study of spatial attention mechanisms in deep networks [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 6687-6696. 10.1109/iccv.2019.00679 |
17 | REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. 10.1109/tpami.2016.2577031 |
18 | 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. 10.1109/cvpr.2016.91 |
19 | MASCI J, GIUSTI A, CIRESAN D, et al. A fast learning algorithm for image segmentation with max-pooling convolutional networks [C]// Proceedings of the 2013 IEEE International Conference on Image Processing. Piscataway: IEEE, 2013: 2713-2717. 10.1109/icip.2013.6738559 |
20 | LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944. 10.1109/cvpr.2017.106 |
21 | LIU Z C, WANG S. Broken corn detection based on an adjusted YOLO with focal loss [J]. IEEE Access, 2019, 7: 68281-68289. 10.1109/access.2019.2916842 |
22 | 丁松涛,曲仕茹.基于深度学习的交通目标感兴趣区域检测[J].中国公路学报,2018,31(9):167-174. 10.3969/j.issn.1001-7372.2018.09.019 |
DING S T, QU S R. Traffic object detection based on deep learning with region of interest selection [J]. China Journal of Highway and Transport, 2018, 31(9): 167-174. 10.3969/j.issn.1001-7372.2018.09.019 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 赵志强, 马培红, 黑新宏. 基于双重注意力机制的人群计数方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2886-2892. |
[3] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[4] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[5] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[6] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[7] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. |
[8] | 顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625. |
[9] | 石乾宏, 杨燕, 江永全, 欧阳小草, 范武波, 陈强, 姜涛, 李媛. 面向空气质量预测的多粒度突变拟合网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2643-2650. |
[10] | 吴筝, 程志友, 汪真天, 汪传建, 王胜, 许辉. 基于深度学习的患者麻醉复苏过程中的头部运动幅度分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2258-2263. |
[11] | 李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072. |
[12] | 张郅, 李欣, 叶乃夫, 胡凯茜. 基于暗知识保护的模型窃取防御技术DKP[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2080-2086. |
[13] | 赵亦群, 张志禹, 董雪. 基于密集残差物理信息神经网络的各向异性旅行时计算方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2310-2318. |
[14] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[15] | 孙逊, 冯睿锋, 陈彦如. 基于深度与实例分割融合的单目3D目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2208-2215. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||