改进RetinaNet的遮挡目标检测算法研究

doi:10.3778/j.issn.1002-8331.2107-0277

摘要/Abstract

摘要： 针对目标检测任务中目标实例密集、重叠等因素导致的检测精度不高的问题，提出一种改进回归损失函数与动态非极大值抑制的目标检测框架。采用结合排斥因子Rep的GIoU-Loss进行目标位置回归，在增加回归参数间相关性的同时降低候选边框向邻近真值偏移概率。Rep-GIoU-Loss不仅有效提升目标位置回归精度，对目标遮挡情形也具有较好的鲁棒性。此外，增加稠密度预测分支预测目标被遮挡程度，并将遮挡程度预测值作为NMS方法的动态阈值，以减少漏检、虚检目标实例。实验结果表明，改进方法检测精度在PASCAL VOC2007测试数据集上提高了1.3个百分点，自制数据集可提高2.8个百分点，验证了该方法的有效性。

关键词: 目标检测, 遮挡, GIoU, RetinaNet, 非极大值抑制

Abstract: Aiming at the problem of low detection accuracy caused by the dense and overlapping instances, a detection framework with the improved regression loss function and dynamic non-maximum suppression（NMS） is proposed in this paper. Rep-GIoU-Loss derived from the combination of GIoU-Loss and the rejection factor Rep is used for location regression of object, which increases the correlation among regression parameters and reduces the probability of candidate bounding box offset to adjacent truth boxes. As a result, Rep-GIoU-Loss not only improves the regression accuracy of object location effectively, but also enjoys good robustness to the occlusion problem. In addition, a density prediction branch for predicting occlusion degree is added. The computed value from the density prediction branch is utilized as the dynamic threshold of the NMS, which reduces the missed and false detection instances. The detection accuracy of the proposed approach is improved by 1.3 percentage points on Pascal VOC and 2.8 percentage points on the self-made dataset. The experimental results show the effectiveness of the proposed method.

Key words: object detection, occlusion, GIoU, RetinaNet, non-maximum suppression（NMS）

阳珊, 王建, 胡莉, 刘波, 赵皓. 改进RetinaNet的遮挡目标检测算法研究[J]. 计算机工程与应用, 2022, 58(11): 209-214.

YANG Shan, WANG Jian, HU Li, LIU Bo, ZHAO Hao. Research on Occluded Object Detection by Improved RetinaNet[J]. Computer Engineering and Applications, 2022, 58(11): 209-214.

参考文献

[1] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[2] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[3] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[4] TIAN Z，SHEN C，CHEN H，et al.FCOS：a simple and strong anchor-free object detector[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，44（4）：1922-1933.
[5] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[6] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[7] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，2016.
[8] LI Z，ZHOU F.FSSD：feature fusion single shot multibox detector[J].arXiv：1712.00960，2017.
[9] YU J，JIANG Y，WANG Z，et al.Unitbox：an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia，2016：516-520.
[10] REZATOFIGHI H，TSOI N，GWAK J Y，et al.Generalized intersection over union：a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：658-666.
[11] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[12] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2020，42（2）：318-327.
[13] WANG X，XIAO T，JIANG Y，et al.Repulsion loss：detecting pedestrians in a crowd[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7774-7783.
[14] LIU S，HUANG D，WANG Y.Adaptive NMS：refining pedestrian detection in a crowd[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：6459-6468.
[15] 汪能.基于SSD模型优化的小目标和遮挡目标检测算法研究[D].武汉：华中师范大学，2020.
WANG N.Small target and occluded target detection algorithm based on SSD model optimization[D].Wuhan：Central China Normal University，2020.
[16] 程婧怡，段先华，朱伟.改进YOLOv3的金属表面缺陷检测研究[J].计算机工程与应用，2021，57（19）：252-258.
CHENG J Y，DUANG X H，ZHU W.Research on metal surface defect detection by improved YOLOv3[J].Computer Engineering and Applications，2021，57（19）：252-258.
[17] TAN M，PANG R，LE Q V.Efficientdet：scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.
[18] BODLA N，SINGH B，CHELLAPPA R，et al.Soft-NMS—improving object detection with one line of code[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5561-5569.