基于自适应协同注意力机制的航拍密集小目标检测算法

doi:10.7527/S1000-6893.2022.27944

Abstract

Abstract:

In response to the problem of a large number of targets and a high proportion of small targets in a wide field of view in drone aerial target detection tasks， a drone aerial target detection algorithm ACAM-YOLO based on adaptive collaborative attention mechanism is proposed. In the backbone network and feature enhancement network parts， the Adaptive Co-Attention Module （ACAM） is embedded， which first segments the input features along the channel direction， Then， spatial attention features and channel attention features are separately mined， and finally adaptively weighted into collaborative attention weights to increase the effective utilization of spatial and channel information for input features； To improve detection accuracy while ensuring lightweight of the detection network， the backbone network， feature enhancement network， and detection head are optimized. Firstly， a lightweight backbone network is used to significantly reduce the number of parameters， and then a high-resolution feature enhancement network is used to retain more semantic features and detailed features. Finally， the positioning accuracy is improved by using a large and dense number of anchor boxes in the large-scale detection head. Verified using the public dataset VisDrone2019， compared with the baseline network version 6.0 YOLOv5 object detection algorithm， ACAM-YOLO’s mAP_0.5 increased by 11.0%， mAP_0.95 increased by 7.8%， and model parameters decreased by 65.5%. The experiment proved that the ACAM-YOLO object detection network has strong practicality for detecting dense small targets in aerial photography.

Key words: computer vision, small object detection, YOLOv5, attention mechanisms, drone

CLC Number:

V279

Zihao LI, Zhengping WANG, Yuntao HE. Aerial-photography dense small target detection algorithm based on adaptive cooperative attention mechanism[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(13): 327944-327944.

Figures/Tables 11

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Fig. 5

Table 2

Table 3

Table 4

Fig. 6

Fig. 7

References 22

1	江波，屈若锟，李彦冬，等. 基于深度学习的无人机航拍目标检测研究综述［J］. 航空学报， 2021， 42（4）：524519
	JIANG B， QU R K， LI Y D， et al. Object detection in UAV imagery based on deep learning： Review［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）：524519 （in Chinese）.
2	REN S， HE K， GIRSHICK，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.
3	LIU W， ANGUELOV D， ERHAN D， et al. SSD： Single shot MultiBox detector［C］∥European Conference on Computer Vision. Cham： Springer， 2016： 21-37.
4	LIN T Y， GOYAL P， GIRSHICK R， et al. Focal loss for dense object detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2020， 42（2）： 318-327.
5	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： Unified， real-time object detection［C］∥2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2016： 779-788.
6	REDMON J， FARHADI A. YOLO9000： Better， faster， stronger［C］∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 6517-6525.
7	REDMON J， FARHADI A. YOLOv3： An incremental improvement［DB/OL］. ArXiv preprint： 1804.02767， 2018.
8	BOCHKOVSKIY A， WANG C Y， LIAO H. YOLOv4： Optimal speed and accuracy of object detection［DB/OL］. arXiv preprint： 2004.10934， 2020
9	张艳，张明路，吕晓玲，等. 深度学习小目标检测算法研究综述［J］. 计算机工程与应用， 2022， 58（15）： 1-17.
	ZHANG Y， ZHANG M L， LYU X L， et al. Review of research on small target detection based on deep learning［J］. Computer Engineering and Applications， 2022， 58（15）： 1-17 （in Chinese）.
10	李科岑，王晓强，林浩，等. 深度学习中的单阶段小目标检测方法综述［J］. 计算机科学与探索， 2022， 16（1）：41-58.
	LI K C， WANG X Q， LIN H， et al. Survey of one-stage small object detection methods in deep learning［J］. Journal of Frontiers of Computer Science & Technology， 2022， 16（1）：41-58 （in Chinese）.
11	曹家乐，李亚利，孙汉卿，等. 基于深度学习的视觉目标检测技术综述［J］. 中国图象图形学报， 2022， 27（6）：1697-1722.
	CAO J L， LI Y L， SUN H Q， et al. A survey on deep learning based visual object detection［J］. Journal of Image and Graphics， 2022， 27（6）：1697-1722 （in Chinese）.
12	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018： 7132-7141.
13	WOO S， PARK J， LEE J Y， et al. CBAM： Convolutional block attention module［DB/OL］. ArXiv preprint： 1807.06521， 2018.
14	HOU Q B， ZHOU D Q， FENG J S. Coordinate attention for efficient mobile network design［C］∥ 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 13708-13717.
15	LIN T Y， DOLLÁR P， GIRSHICK R， et al. Feature pyramid networks for object detection［C］∥ 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 936-944.
16	LIU S， QI L， QIN H F， et al. Path aggregation network for instance segmentation［C］∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018： 8759-8768.
17	TAN M X， PANG R M， LE Q V. EfficientDet： Scalable and efficient object detection［C］∥ 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2020： 10778-10787.
18	CHEN Y K， ZHANG P Z， LI Z， et al. Stitcher： Feedback-driven data provider for object detection［DB/OL］. arXiv preprint： 2004.12432， 2020.
19	YUN S， HAN D， CHUN S， et al. CutMix： Regularization strategy to train strong classifiers with localizable features［C］∥ 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Piscataway： IEEE Press， 2020： 6022-6031.
20	KISANTAL M， WOJNA Z， MURAWSKI J， et al. Augmentation for small object detection［C］∥ 9th International Conference on Advances in Computing and Information Technology （ACITY 2019）， 2019.
21	DU D W， ZHU P F， WEN L Y， et al. VisDrone-DET2019： The vision meets drone object detection in image challenge results［C］∥ 2019 IEEE/CVF International Conference on Computer Vision Workshop （ICCVW）. Piscataway： IEEE Press， 2020： 213-226.
22	冒国韬，邓天民，于楠晶. 基于多尺度分割注意力的无人机航拍图像目标检测算法［J］.航空学报， 2023， 44（5）： 326738.
	MAO G T， DENG T M， YU N J. Object detection in UAV images based on multi-scale split attetion［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（5）： 326738 （in Chinese）.

模型	Parameter/M	GFLOPs/G	检测头特征尺寸
YOLOv5	46.2	108.1	20/40/80
YOLOv5_rec	17.4	128.7	40/80/160

检测网络	特征输入	耦合特征提取	Parameter/M	FLOPs/G
YOLOv5l_rec			15.9	128.7
YOLOv5l_rec+ACAM	沿通道方向切分	深度可分离卷积	15.9	130.8
YOLOv5l_rec+ACAM	沿通道方向切分	正常卷积	16.0	144.7
YOLOv5l_rec+ACAM	全通道输入	深度可分离卷积	16.9	141.3
YOLOv5l_rec+ACAM	全通道输入	正常卷积	25.2	254.3

方法	mAP_0.5/%	mAP_0.95/%	Parameter/M	FLOPs/G
Baseline（YOLOv5）	38.5	21.8	46.1	108.1
YOLOv5+ACAM	39.1	22.2	46.2	110.9
YOLOv5_rec	48.5	29.2	15.9	128.7
YOLOv5_rec+SE	48.1	28.8	16.0	128.8
YOLOv5_rec+CBAM	48.0	28.7	16.0	128.9
YOLOv5_rec+CA	48.0	28.6	16.0	129.0
YOLOv5_rec+ACAM （ACAM-YOLO）	49.5	29.6	15.9	130.8

方法	主干网络	AP_0.5/%										平均mAP_0.5/%
方法	主干网络	Pedestrian	Person	Bicycle	Car	Van	Trunk	Tri	Awn-tri	Bus	Motor	平均mAP_0.5/%
Faster R-CNN	ResNet-50	21.4	15.6	6.7	51.7	29.5	19.0	13.1	7.7	31.4	20.7	21.7
Faster R-CNN	ResNet-101	20.9	14.8	7.3	51.0	29.7	19.5	14.0	8.8	30.5	21.2	21.8
RetinaNet	ResNet-50	13.0	7.9	1.4	45.5	19.9	11.5	6.3	4.2	17.8	11.8	13.9
YOLOv4	CSPDarknet	24.8	12.6	8.6	64.3	22.4	22.7	11.4	7.6	44.3	21.7	30.7
CDNet	ResNeXt-101	35.6	19.2	13.8	55.8	42.1	38.2	33.0	25.4	49.5	29.3	34.2
YOLOv3-LITE	Darknet-53	34.5	23.4	7.9	70.8	31.3	21.9	15.3	6.2	40.9	32.7	28.5
MSC-CenterNet	Hourglass-104	33.7	15.2	12.1	55.2	40.5	34.1	29.2	21.6	42.2	27.5	31.1
DMNet	ResNet-50	28.5	20.4	15.9	56.8	37.9	30.1	22.6	14.0	41.7	29.2	30.3
HR-Cascade++	HRNet-W40	32.6	17.3	11.1	54.7	42.4	35.3	32.7	24.1	46.5	28.2	32.5
DBAI-Net	ResNeXt-101	36.7	12.8	14.7	47.4	38.0	41.4	23.4	16.9	31.9	16.6	28.0
Cascade R-CNN	ResNet-50	22.2	14.8	7.6	54.6	31.5	21.6	14.8	8.6	34.9	21.4	23.2
CenterNet	Hourglass-104	22.6	20.6	14.6	59.7	24.0	21.3	20.1	17.4	37.9	23.7	26.2
MSA-YOLO	CSPDarknet	33.4	17.3	11.2	76.8	41.5	41.4	14.8	18.4	60.9	31.0	34.7
ACAM-YOLO	CSPDarknet	57.6	45.9	25.7	88.5	51.9	45.5	38.1	19.9	69.1	56.3	49.5

[1]	Zhiqiang FENG, Zhijun XIE, Zhengwei BAO, Kewei CHEN. Real⁃time dense small object detection algorithm for UAV based on improved YOLOv5 [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(7): 327106-327106.
[2]	Guotao MAO, Tianmin DENG, Nanjing YU. Object detection in UAV images based on multi-scale split attention [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 326738-326738.
[3]	Ping WANG, Hui FU, Guili XU. Camera pose estimation and corresponding points matching based on rotation search [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(2): 326695-326695.
[4]	ZHONG Mengfan, PEI Jihong. Image stitching enhancement method with symmetrical constraint of local feature points [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(S1): 726948-726948.
[5]	LYU Shuaishuai, YANG Yu, WANG Binwen, YIN Chenfei. A crack identification method of aircraft structure based on improved FaceNet [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 525463-525463.
[6]	LI Hongguang, YU Ruonan, DING Wenrui. Research development of small object traching based on deep learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(7): 24691-024691.
[7]	JIANG Bo, QU Ruokun, LI Yandong, LI Chenglong. Object detection in UAV imagery based on deep learning: Review [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524519-524519.
[8]	CHEN Yanbo, HUANG Jinlong, WANG Zhijun, JIANG Bin, CHENG Yuehua, YANG Hao. Influences of drone swarm failure based on directed graph [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(S2): 724287-724287.
[9]	WANG Xiaoguang, ZHANG Weiguo, LIU Yang. Suicide drones' attack strategy on the condition of escort free-flight decoys influence [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2015, 36(9): 3137-3146.
[10]	LU Yuping, YANG Chaoxing, LIU Yangyang. A Survey of Modeling and Control Technologies for Aerial Refueling System [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2014, 35(9): 2375-2389.
[11]	CHEN Maowei, SUN Mao. Experimental Measurement and Force Analysis of a Fast Takeoff in Dronefly [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2014, 35(12): 3222-3231.
[12]	SHEN Hao, LI Shuxiao, SHEN Yiping, ZHU Chengfei, CHANG Hongxing. Fast Interframe Registration Method in Aerial Videos [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2013, 34(6): 1405-1413.
[13]	Jiang Hongxiang;Xu Jinfa;Gao Zheng. Vision-based Movement State Estimation Algorithm for Unmanned Helicopter Landing [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2010, 31(4): 744-753.
[14]	Cheng Xu;Hao Qun;Song Yong;Hu Yao;Zhang Kai. A Horizon Detection Algorithm Based on Between-class Variance Analysis [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2010, 31(10): 2056-2061.
[15]	CHEN Zhen;GAO Man-tun;Yang Sheng-yun;SHEN Yun-wen. Calculation of 3D Motion and Structure from Optical Flow in Image Sequence [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2004, 25(1): 55-58.

Aerial-photography dense small target detection algorithm based on adaptive cooperative attention mechanism

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 22

Related Articles 15

Recommended Articles

Metrics

Comments