Improved YOLOv8s Model for Small Object Detection from Perspective of Drones

doi:10.3778/j.issn.1002-8331.2312-0043

Abstract

Abstract: Facing with the problems of small and densely distributed image targets, uneven class distribution, and model size limitation of hardware conditions, object detection from the perspective of drones has less precise results. A new improved model based on YOLOv8s with multiple attention mechanisms is proposed. To solve the problem of shared attention weight parameters in receptive field features and enhance feature extraction ability, receptive field attention convolution and CBAM (concentration based attention module) attention mechanism are introduced into the backbone, adding attention weight in channel and spatial dimensions. By introducing large separable kernel attention into feature pyramid pooling layers, information fusion between different levels of features is increased. The feature layers with rich semantic information of small targets are added to improve the neck structure. The inner-IoU loss function is used to improve the MPDIoU (minimum point distance based IoU) function and the inner-MPDIoU instead of the original loss function is used to enhance the learning ability for difficult samples. The experimental results show that the improved YOLOv8s model has improved mAP, P, and R by 16.1%, 9.3%, and 14.9% respectively on the VisDrone dataset, surpassing YOLOv8m in performance and can be effectively applied to unmanned aerial vehicle visual detection tasks.

Key words: unmanned aerial vehicle (UAV), small object detection, YOLOv8s, receptive field attention, large separable kernel attention

摘要： 从无人机视角进行目标检测，面临图像目标小、分布密集、类别不均衡等难点，且由于无人机的硬件条件限制了模型的规模，导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型，在骨干网络中引入感受野注意力卷积和CBAM（concentration-based attention module）注意力机制改进卷积模块，解决注意力权重参数在感受野特征中共享问题的同时，在通道和空间维度加上注意力权重，增强特征提取能力；通过引入大型可分离卷积注意力思想，改造空间金字塔池化层，增加不同层级特征间的信息交融；优化颈部结构，增加具有丰富小目标语义信息的特征层；使用inner-IoU损失函数的思想改进MPDIoU（minimum point distance based IoU）函数，以inner-MPDIoU代替原损失函数，提升对困难样本的学习能力。实验结果表明，改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%，性能超过YOLOv8m，可以有效应用于无人机平台上的目标检测任务。

关键词: 无人机, 小目标检测, YOLOv8s, 感受野注意力, 大型可分离卷积

PAN Wei, WEI Chao, QIAN Chunyu, YANG Zhe. Improved YOLOv8s Model for Small Object Detection from Perspective of Drones[J]. Computer Engineering and Applications, 2024, 60(9): 142-150.

潘玮, 韦超, 钱春雨, 杨哲. 面向无人机视角下小目标检测的YOLOv8s改进模型[J]. 计算机工程与应用, 2024, 60(9): 142-150.

References

[1] SAEED Z, YOUSAF M H, AHMED R, et al. On-board small-scale object detection for unmanned aerial vehicles (UAVs)[J]. Drones, 2023, 7(5): 310.
[2] BISIO I, HALEEM H, GARIBOTTO C, et al. Performance evaluation and analysis of drone-based vehicle detection techniques from deep learning perspective[J]. IEEE Internet of Things Journal, 2021, 9(13): 10920-10935.
[3] HOSHINO W, SEO J, YAMAZAKI Y. A study for detecting disaster victims using multi-copter drone with a thermographic camera and image object recognition by SSD[C]//2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), 2021: 162-167.
[4] SORBELLI F B, PALAZZETTI L, PINOTTI C M. YOLO-based detection of halyomorpha halys in orchards using RGB cameras and drones[J]. Computers and Electronics in Agriculture, 2023, 213: 108228.
[5] SINGHA S, AYDIN B. Automated drone detection using YOLOv4[J]. Drones, 2021, 5(3): 95.
[6] LI Y, YUAN H, WANG Y, et al. GGT-YOLO: a novel object detection algorithm for drone-based maritime cruising[J]. Drones, 2022, 6(11): 335.
[7] PIRASTEH S, RASHIDI P, RASTIVEIS H, et al. Developing an algorithm for buildings extraction and determining changes from airborne LiDAR, and comparing with R-CNN method from drone images[J]. Remote Sensing, 2019, 11(11): 1272.
[8] SEO D M, WOO H J, KIM M S, et al. Identification of asbestos slates in buildings based on faster region-based convolutional neural network (Faster R-CNN) and drone-based aerial imagery[J]. Drones, 2022, 6(8): 194.
[9] 陈卫彪, 贾小军, 朱响斌, 等. 基于DSM-YOLO v5的无人机航拍图像目标检测[J]. 计算机工程与应用, 2023, 59(18): 226-233.
CHEN W B, JIA X J, ZHU X B, et al. Target detection for UAV image based on DSM-YOLO v5[J]. Computer Engineering and Applications, 2023, 59(18): 226-233.
[10] 陈范凯, 李士心. 改进Yolov5的无人机目标检测算法[J]. 计算机工程与应用, 2023, 59(18): 218-225.
CHEN F K, LI S X. UAV target detection algorithm with improved Yolov5[J]. Computer Engineering and Applications, 2023, 59(18): 218-225.
[11] 刘涛, 丁雪妍, 张冰冰, 等. 改进YOLOv5的遥感图像检测方法[J]. 计算机工程与应用, 2023, 59(10): 253-261.
LIU T, DING X Y, ZHANG B B, et al. Improved YOLOv5 for remote sensing image detection[J]. Computer Engineering and Applications, 2023, 59(10): 253-261.
[12] LI Y, FAN Q, HUANG H, et al. A modified YOLOv8 detection network for UAV aerial image recognition[J]. Drones, 2023, 7(5): 304.
[13] LOU H, DUAN X, GUO J, et al. DC-YOLOv8: small-size object detection algorithm based on camera sensor[J]. Electronics, 2023, 12(10): 2323.
[14] GUO J, LOU H, CHEN H, et al. A new detection algorithm for alien intrusion on highway[J]. Scientific Reports, 2023, 13(1): 10667.
[15] WANG F, WANG H, QIN Z, et al. UAV target detection algorithm based on improved YOLOv8[J]. IEEE Access, 2023, 11: 116534-116544.
[16] WANG G, CHEN Y, AN P, et al. UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios[J]. Sensors, 2023, 23(16): 7190.
[17] ZHANG X, LIU C, YANG D, et al. RFAConv: innovating spatital attention and standard convolutional operation[J]. arXiv:2304.03198, 2023.
[18] WOO S, PARK J, LEE J Y, et al. Cbam: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[19] LAU K W, PO L M, REHMAN Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN[J]. Expert Systems with Applications, 2024, 236: 121352.
[20] ZHANG H, XU C, ZHANG S. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv:2311.02877, 2023.
[21] MA S L, XU Y. MPDIoU: a loss for efficient and accurate bounding box regression[J]. arXiv:2307.07662, 2023.
[22] DU D, ZHU P, WEN L, et al. VisDrone-DET2019: the vision meets drone object detection in image challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
[23] 张智, 易华挥, 郑锦. 聚焦小目标的航拍图像目标检测算法[J]. 电子学报, 2023, 51(4): 944-955.
ZHANG Z, YI H H, ZHENG J. Focusing on small objects detector in aerial images[J]. Acta Electonica Sinica, 2023, 51(4): 944-955.
[24] HSIEH M R, LIN Y L, HSU W H. Drone-based object counting by spatially regularized regional proposal network[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 4145-4153.