面向无人机小目标的RTDETR改进检测算法

doi:10.3778/j.issn.1002-8331.2404-0114

摘要/Abstract

摘要： 针对无人机目标检测中目标小且密集、背景复杂、硬件条件限制等挑战，提出一种改进的RTDETR检测器。在骨干网络，设计轻量级多尺度注意力特征提取模块（Rep-FasterNet EMA block），使用RepConv改进FasterNet block，同时引入多尺度注意力模块（EMA），增强空间特征提取能力并降低计算冗余。在Encoder部分，采用了DyASF特征融合结构替换CCFM，利用动态尺度序列特征融合（DySSFF）模块和三重特征编码器（TPE）模块，避免上下采样导致的小目标特征信息丢失，并丰富小目标检测详细信息，增强了网络尺度特征融合能力。对于损失函数，结合Focaler-IoU和Shape-IoU的优点，提出了Focaler-Shape-IoU替换原模型GIOU，注入边界框的形状和尺度信息，聚焦困难样本，增强边界框回归效果。实验结果表明，改进模型在Visdrone2019数据集上的mAP0.5和mAP0.5:0.95分别提升了1.6个百分点和0.7个百分点，同时权值文件大小有一定减少，验证了改进模型的有效性。

关键词: 无人机遥感, 小目标检测, RTDETR, 多尺度注意力

Abstract: An improved RTDETR detector is proposed to solve the challenges in UAV target detection, such as small and dense targets, complex background and limited hardware conditions. In the backbone network, lightweight multi-scale attention feature extraction module (Rep-FasterNet EMA block) is designed, and RepConv is used to improve the FasterNet block. Meanwhile, multi-scale attention module (EMA) is introduced to enhance the spatial feature extraction capability and reduce the computational redundancy. In the Encoder part, DyASF feature fusion structure is used to replace CCFM, and dynamic scale sequence feature fusion (DySSFF) module and triple feature encoder (TPE) module are used to avoid the loss of small target feature information caused by up and down sampling, enrich the detailed information of small target detection, and enhance the network scale feature fusion capability. Finally, for the loss function, combining the advantages of Focaler-IoU and shape-IoU, Focaler-Shape-IoU is proposed to replace the original model GIOU, inject the shape and scale information of the bounding box, focus the difficult samples, and enhance the bounding box regression effect. The experimental results show that the mAP0.5 and mAP0.5：0.95 of the improved model on the Visdrone2019 dataset are improved by 1.6 percentage points and 0.7 percentage points respectively, while the weight file size has been reduced to a certain extent, which verifies the effectiveness of the improved model.

Key words: UAV remote sensing, small target detection, real-time detection Transformer (RTDETR), multiscale attention

胡佳乐, 周敏, 申飞. 面向无人机小目标的RTDETR改进检测算法[J]. 计算机工程与应用, 2024, 60(20): 198-206.

HU Jiale, ZHOU Min, SHEN Fei. Improved Detection Algorithm of RTDETR for UAV Small Target[J]. Computer Engineering and Applications, 2024, 60(20): 198-206.

参考文献

[1] 赵鑫, 陈里里, 杨维川, 等. DY-YOLOv5: 基于多重注意力机制的航拍图像目标检测[J]. 计算机工程与应用, 2024, 60(7): 183-191.
ZHAO X, CHEN L L, YANG W C, et al. DY-YOLOv5: target detection for aerial image based on multiple attention[J]. Computer Engineering and Applications, 2024, 60(7): 183-191.
[2] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[3] LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.
02976, 2022.
[4] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[5] REIS D, KUPEC J, HONG J, et al. Real-time flying object detection with YOLOv8[J]. arXiv:2305.09972, 2023.
[6] REN S, HE K, 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.
[7] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
[8] KIRILLOV A, WU Y, HE K, et al. PointRend: image segmentation as rendering[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9799-9808.
[9] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of the European Conference on Computer Vision, 2020: 213-229.
[10] ZHU X, SU W, LU L, et al. Deformable DETR: deformable transformers for end-to-end object detection[J]. arXiv:2010.
04159, 2020.
[11] MENG D, CHEN X, FAN Z, et al. Conditional DETR for fast training convergence[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 3651-3660.
[12] WANG Y, ZHANG X, YANG T, et al. Anchor DETR: query design for transformer-based detector[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022: 2567-2575.
[13] LIU S, LI F, ZHANG H, et al. DAB-DETR: dynamic anchor boxes are better queries for DETR[J]. arXiv:2201.12329, 2022.
[14] LI F, ZHANG H, LIU S, et al. DN-DETR: accelerate DETR training by introducing query denoising[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 13619-13627.
[15] ZHANG H, LI F, LIU S, et al. DINO: DETR with improved denoising anchor boxes for end-to-end object detection[J]. arXiv:2203.03605, 2022.
[16] LUY W, XU S, ZHAO Y, et al. DETRs beat YOLOs on real-time object detection[J]. arXiv:2304.08069, 2023.
[17] YUAN X, CHENG G, YAN K, et al. Small object detection via coarse-to-fine proposal generation and imitation learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023: 6317-6327.
[18] DING X, ZHANG X, MA N, et al. RepVGG: making VGG-style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13733-13742.
[19] OUYANG D, HE S, ZHANG G, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, 2023: 1-5.
[20] ZHANG H, ZHANG S. Focaler-IoU: more focused intersection over union loss[J]. arXiv:2401.10525, 2024.
[21] ZHANG H, ZHANG S. Shape-IoU: more accurate metric considering bounding box shape and scale[J]. arXiv:2312.
17663, 2023.
[22] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1251-1258.
[23] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12021-12031.
[24] BOCK J, KRAJEWSKI R, MOERS T, et al. The inD dataset: a drone dataset of naturalistic road user trajectories at german intersections[C]//Proceedings of the 2020 IEEE Intelligent Vehicles Symposium, 2020: 1929-1934.
[25] SUN Q S, ZENG S G, LIU Y, et al. A new method of feature fusion and its application in image recognition[J]. Pattern Recognition, 2005, 38(12): 2437-2448.
[26] LIU W, LU H, FU H, et al. Learning to upsample by learning to sample[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023: 6027-6037.
[27] KANG M, TING C M, TING F, et al. ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J]. arXiv:2312.06458, 2023.
[28] 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.
[29] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 8574-8586.
[30] 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.
[31] 周孟然, 王澳. 基于DETR的轻量级遥感图像目标检测算法[J/OL]. 重庆工商大学学报 (自然科学版): 1-10[2024-03-29]. http://kns.cnki.net/kcms/detail/50.1155.N.20240328.
1703.004.html.
ZHOU M R, WANG A. Lightweight remote sensing image object detection algorithm based on DETR[J/OL]. Journal of Chongqing Technology and Business University (Natural Science Edition): 1-10[2024-03-29]. http://kns.cnki.net/kcms/detail/50.1155.N.20240328.1703.004.html.
[32] DU D, ZHU P, WEN L, et al. VisDrone-SOT2019: the vision meets drone single object tracking challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
[33] ZHENG Q, SAPONARA S, TIAN X, et al. A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT[J]. Cognitive Neurodynamics, 2023, 18(2): 659-671.
[34] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2921-2929.