CSD-YOLOv8s: Dense Sheep Small Target Detection Model Based on UAV Images

doi:10.12133/j.smartag.SA202401004

Abstract

Abstract:

[Objective] The monitoring of livestock grazing in natural pastures is a key aspect of the transformation and upgrading of large-scale breeding farms. In order to meet the demand for large-scale farms to achieve accurate real-time detection of a large number of sheep, a high-precision and easy-to-deploy small-target detection model: CSD-YOLOv8s was proposed to realize the real-time detection of small-targeted individual sheep under the high-altitude view of the unmanned aerial vehicle (UAV). [Methods] Firstly, a UAV was used to acquire video data of sheep in natural grassland pastures with different backgrounds and lighting conditions, and together with some public datasets downloaded formed the original image data. The sheep detection dataset was generated through data cleaning and labeling. Secondly, in order to solve the difficult problem of sheep detection caused by dense flocks and mutual occlusion, the SPPFCSPC module was constructed with cross-stage local connection based on the you only look once (YOLO)v8 model, which combined the original features with the output features of the fast spatial pyramid pooling network, fully retained the feature information at different stages of the model, and effectively solved the problem of small targets and serious occlusion of the sheep, and improved the detection performance of the model for small sheep targets. In the Neck part of the model, the convolutional block attention module (CBAM) convolutional attention module was introduced to enhance the feature information capture based on both spatial and channel aspects, suppressing the background information spatially and focusing on the sheep target in the channel, enhancing the network's anti-jamming ability from both channel and spatial dimensions, and improving the model's detection performance of multi-scale sheep under complex backgrounds and different illumination conditions. Finally, in order to improve the real-time and deploy ability of the model, the standard convolution of the Neck network was changed to a lightweight convolutional C2f_DS module with a changeable kernel, which was able to adaptively select the corresponding convolutional kernel for feature extraction according to the input features, and solved the problem of input scale change in the process of sheep detection in a more flexible way, and at the same time, the number of parameters of the model was reduced and the speed of the model was improved. [Results and Discussions] The improved CSD-YOLOv8s model exhibited excellent performance in the sheep detection task. Compared with YOLO, Faster R-CNN and other classical network models, the improved CSD-YOLOv8s model had higher detection accuracy and frames per second (FPS) of 87 f/s in the flock detection task with comparable detection speed and model size. Compared with the YOLOv8s model, Precision was improved from 93.0% to 95.2%, mAP was improved from 91.2% to 93.1%, and it had strong robustness to sheep targets with different degree of occlusion and different scales, which effectively solved the serious problems of missed and misdetection of sheep in the grassland pasture UAV-on-ground sheep detection task due to the small sheep targets, large background noise, and high degree of densification. misdetection serious problems. Validated by the PASCAL VOC 2007 open dataset, the CSD-YOLOv8s model proposed in this study improved the detection accuracy of 20 different objects, including transportation vehicles, animals, etc., especially in sheep detection, the detection accuracy was improved by 9.7%. [Conclusions] This study establishes a sheep dataset based on drone images and proposes a model called CSD-YOLOv8s for detecting grazing sheep in natural grasslands. The model addresses the serious issues of missed detections and false alarms in sheep detection under complex backgrounds and lighting conditions, enabling more accurate detection of grazing livestock in drone images. It achieves precise detection of targets with varying degrees of clustering and occlusion and possesses good real-time performance. This model provides an effective detection method for detecting sheep herds from the perspective of drones in natural pastures and offers technical support for large-scale livestock detection in breeding farms, with wide-ranging potential applications.

Key words: sheep detection, YOLOv8, small target, SPPFCSPC, attention mechanism, depthwise separable convolution

WENG Zhi, LIU Haixin, ZHENG Zhiqiang. CSD-YOLOv8s: Dense Sheep Small Target Detection Model Based on UAV Images[J]. Smart Agriculture, 2024, 6(4): 42-52.

Figures/Tables 16

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Table 2

Table 3

Fig. 9

Table 4

Table 5

Table 6

Table 7

References 20

1	AQUILANI C, CONFESSORE A, BOZZI R, et al. Review: Precision livestock farming technologies in pasture-based livestock systems[J]. Animal, 2022, 16(1): ID 100429.
2	赵建敏, 李雪冬, 李宝山. 基于无人机图像的羊群密集计数算法研究[J]. 激光与光电子学进展, 2021, 58(22): ID 2210013.
	ZHAO J M, LI X D, LI B S. Algorithm of sheep dense counting based on unmanned aerial vehicle images[J]. Laser & optoelectronics progress, 2021, 58(22): ID 2210013.
3	LI X H, HUANG H L, SAVKIN A, et al. Robotic herding of farm animals using a network of barking aerial drones[J]. Drones, 2022, 6(2): ID 29.
4	HERLIN A, BRUNBERG E, HULTGREN J, et al. Animal welfare implications of digital tools for monitoring and management of cattle and sheep on pasture[J]. Animals: an open access journal from MDPI, 2021, 11(3): ID 829.
5	CORCORAN E, DENMAN S, HAMILTON G. Evaluating new technology for biodiversity monitoring: Are drone surveys biased?[J]. Ecology and evolution, 2021, 11(11): 6649-6656.
6	郭秀明, 诸叶平, 李世娟, 等. 农业复杂环境下尺度自适应小目标识别算法——以蜜蜂为研究对象[J]. 智慧农业(中英文), 2022, 4(1): 140-149.
	GUO X M, ZHU Y P, LI S J, et al. Scale adaptive small objects detection method in complex agricultural environment: Taking bees as research object[J]. Smart agriculture, 2022, 4(1): 140-149.
7	MAKTAB DAR OGHAZ M, RAZAAK M, REMAGNINO P. Enhanced single shot small object detector for aerial imagery using super-resolution, feature fusion and deconvolution[J]. Sensors, 2022, 22(12): ID 4339.
8	ZHAO H K, MAO R, LI M, et al. SheepInst: A high-performance instance segmentation of sheep images based on deep learning[J]. Animals: An open access journal from MDPI, 2023, 13(8): ID 1338.
9	SARWAR F, GRIFFIN A, PERIASAMY P, et al. Detecting and counting sheep with a convolutional neural network[C]// 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). Piscataway, New Jersey, USA: IEEE, 2018: 1-6.
10	WANG Y H, MA L L, WANG Q, et al. A lightweight and high-accuracy deep learning method for grassland grazing livestock detection using UAV imagery[J]. Remote sensing, 2023, 15(6): ID 1593.
11	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]// European Conference on Computer Vision. Cham, German: Springer, 2018: 3-19.
12	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, New Jersey, USA: IEEE, 2018: 7132-7141.
13	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, New Jersey, USA: IEEE, 2021: 13708-13717.
14	WANG Q L, WU B G, ZHU P F, et al. ECA-net: Efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2020: 11531-11539.
15	Depthwise separable convolutions for machine learning[EB/OL]. Eli Bendersky. (2018-04-04)[2023-12-28].
16	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[M]// LEIBE B, MATAS J, SEBE N, et al, eds. Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
17	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]// 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway, New Jersey, USA: IEEE, 2017: 2999-3007.
18	REN S Q, HE K M, 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.
19	ZHANG Q L, YANG Y B. SA-net: Shuffle attention for deep convolutional neural networks[C]// ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, New Jersey, USA: IEEE, 2021: 2235-2239.
20	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]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2023: 7464-7475.

数据集类型	图像数量/张	无人机采集数据/张	公开数据/张
训练集	2 214	1 584	630
验证集	738	528	210
测试集	738	528	210
总计	3 690	2 640	1 050

硬件配置	参数
CPU	Intel（R） Core（TM） i9-9900K CPU@3.6 GHz
GPU	NVIDIA Quadro P6000
内存容量	32 G
操作系统	Windows 10
开发工具	PyCharm2020.1.1
CUDA版本	10.2
深度学习框架	PyTorch 1.10.0

模型名称	P/%	mAP/%	FLOPs/G	FPS/（f/s）	Params/M
YOLOv8s	93.0	91.2	28.6	105	11.13
YOLOv8s+SPPFCSPC	94.6	92.6	33.6	93	17.49
YOLOv8s+CBAM	94.1	92.1	28.7	88	11.17
YOLOv8s+C2f_DS	92.8	91.2	24.7	107	10.31
YOLOv8s+SPPFCSPC+CBAM	95.2	93.1	33.9	82	17.61
YOLOv8s+SPPFCSPC+C2f_DS	94.5	92.4	29.9	95	16.73
YOLOv8s+CBAM+C2f_DS	94.2	92..0	24.8	90	10.36
CSD-YOLOv8s（本研究）	95.2	93.1	29.9	87	16.68

Attention mechanism	P/%	mAP/%	FLOPs/G	FPS/（f/s）
——	93.0	91.2	28.6	105
SE	93.7	91.5	28.7	96
SimAM	93.2	91.2	28.6	100
CA	93.2	91.4	28.7	96
Shuffle	92.8	91.1	28.6	116
ECA	93.3	91.2	28.7	101
CBAM	94.1	92.1	28.7	88

Module	P/%	mAP/%	FLOPs/G	FPS/（f/s）	Params/M
SPPF	93.0	91.2	28.6	105	11.13
ASPP	93.3	91.0	35.0	84	19.38
SimSPPF	93.0	91.2	28.6	106	11.14
SPPCSPC	94.6	92.6	33.6	90	17.56
SPPFCSPC	94.6	92.6	33.6	93	17.56