复杂背景下遥感图像密集目标检测

doi:10.3778/j.issn.1002-8331.2112-0417

摘要/Abstract

摘要： 遥感图像中的目标排列密集，常见的检测算法难以较好地区分密集目标，同时目标所处背景复杂，导致在模型生成的特征图中，存在高响应的背景噪声，容易带来错误的检测结果。针对上述问题，在CenterNet算法基础上，提出一种改进权重分配的目标检测算法。在计算热力图损失的过程中，设计一种改进权重分配策略，加大目标边缘区域回传的损失，促进网络对密集目标边缘的学习，减少算法将密集目标认定为单个目标的概率；在CenterNet网络结构中，添加语义分割模块，让网络模型学习每一个目标的分割图，通过分割图抑制特征图中高响应的背景噪声。在DOTA数据集上进行实验，改进算法均值平均精度（mAP）达到68.56%，优于其他方法，和原CenterNet算法相比，mAP提升了6.53个百分点。实验结果表明，改进的CenterNet算法能更好地适应复杂背景下的密集目标检测。

关键词: 目标检测, 复杂背景, 密集目标, 语义分割, 改进权重分配策略

Abstract: The objects in remote sensing images are densely packed, and common detection algorithms face challenges in differentiating them. At the same time, the background of the target is complex, resulting in high-response background noise in the feature map generated by the model, which can lead to dissatisfied detection results. An object detection algorithm based on the CenterNet network with optimized weight distribution is proposed to resolve the aforementioned issues. To begin with, an optimized weight distribution strategy is designed to enlarge the loss returned from the target edge region during the calculation process of heatmap loss, encouraging the network to pay close attention to the edge of the dense target and lowering the probability of the algorithm recognizing the dense target as a single target. Second, a semantic segmentation module is incorporated into the CenterNet network structure, training the network model to learn the segmentation map of each target and applying the segmentation map predicted by the model to suppress the high-response background noise in the feature map. Experiments are carried out on the DOTA dataset, and the proposed method outperforms the previous algorithm with mean average accuracy（mAP） of 68.56%. Compared with the original CenterNet algorithm, mAP has improved by 6.53 percentage points. Experimental results show that the improved CenterNet algorithm can better adapt to the detection of dense targets distributed in complex backgrounds.

Key words: object detection, complex background, densely packed objects, semantic segmentation, optimized weight distribution strategy

李阿标, 郭浩, 戚畅, 安居白. 复杂背景下遥感图像密集目标检测[J]. 计算机工程与应用, 2023, 59(8): 247-253.

LI Abiao, GUO Hao, QI Chang, AN Jubai. Dense Object Detection in Remote Sensing Images Under Complex Background[J]. Computer Engineering and Applications, 2023, 59(8): 247-253.

参考文献

[1] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[2] 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.
[3] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[4] ZHOU X，WANG D，KR?HENBüHL P.Objects as points[J].arXiv：1904.07850，2019.
[5] MA J，SHAO W，YE H，et al.Arbitrary-oriented scene text detection via rotation proposals[J].IEEE Transactions on Multimedia，2018，20（11）：3111-3122.
[6] JIANG Y，ZHU X，WANG X，et al.R2CNN：rotational region CNN for orientation robust scene text detection[J].arXiv：1706.09579，2017.
[7] LIU L，PAN Z X，LEI B.Learning a rotation invariant detector with rotatable bounding box[J].arXiv：1711.09405，2017.
[8] YANG X，YANG J，YAN J，et al.SCRDet：towards more robust detection for small，cluttered and rotated objects[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：8232-8241.
[9] GUO Z，LIU C，ZHANG X，et al.Beyond bounding-box：convex-hull feature adaptation for oriented and densely packed object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：8792-8801.
[10] PAN X，REN Y，SHENG K，et al.Dynamic refinement network for oriented and densely packed object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：11207-11216.
[11] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[12] 蒋光峰，胡鹏程，叶桦，等.基于旋转中心点估计的遥感目标精确检测算法[J].计算机应用研究，2021，38（9）：2866-2870.
JIANG G F，HU P C，YE H，et al.Remote sensing target accurate detection algorithm based on rotation center point estimation[J].Application Research of Computers，2021，38（9）：2866-2870.
[13] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[14] WANG Q，BRECKON T P.Crowd counting via segmentation guided attention networks and curriculum loss[J].arXiv：1911.07990，2019.
[15] LIN M，CHEN Q，YAN S.Network in network[J].arXiv：1312.4400，2013.
[16] XIA G S，BAI X，DING J，et al.DOTA：a large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：3974-3983.
[17] DING J，XUE N，LONG Y，et al.Learning RoI transformer for detecting oriented objects in aerial images[J].arXiv：1812.00155，2018.
[18] LIN Y，FENG P，GUAN J，et al.IENet：interacting embranchment one stage anchor free detector for orientation aerial object detection[J].arXiv：1912.00969，2019.