Benchmark datasets for detection and identification of insects from camera trap images with deep learning
收藏NIAID Data Ecosystem2026-03-14 收录
下载链接:
https://zenodo.org/record/7395751
下载链接
链接失效反馈官方服务:
资源简介:
Insect benchmark datasets for training, validation and test (train1201.zip, val1201.zip and test1201.zip) with time-lapse images as described in paper:
Bjerge K, Alison J, Dyrmann M, Frigaard C.E., Mann H. M. R., Høye T.T., Accurate detection and identification of insects from camera trap images with deep learning, bioRxiv:10.1101/2022.10.25.513484v1
Labels in YOLO format: ultralytics/yolov5: label format
The annotated training and validation datasets contains insects of nine different species as listed below:
0 Coccinellidae septempunctata
1 Apis mellifera
2 Bombus lapidarius
3 Bombus terrestris
4 Eupeodes corolla
5 Episyrphus balteatus
6 Aglais urticae
7 Vespula vulgaris
8 Eristalis tenax
The test dataset contains additional classes of insects.
9 Non-Bombus Anthophila
10 Bombus spp.
11 Syrphidae
12 Fly spp.
13 Unclear insect
14 Mixed animals:
——————————
Rhopalocera
Non-Anthophila Hymenoptera
Non-Syrphidae Diptera
Non-Conccinalidae Coleoptera
Concinellidae
Other animals
There are two naming conventions for image (.jpg) and label (.txt) files.
Background images without insects are named:
“X_Seq-YYYYMMDDHHMMSS-snapshot”.
E.g.:
Background image: 12_13-20190704172200-snapshot.jpg
Empty label file: 12_13-20190704172200-snapshot.txt
Images annotated with insects are named:
“SZ_IP-MonthDate_C_Seq-YYYYMMDDHHMMSS”.
E.g.:
Image file: S1_146-Aug23_1_156-20190822133230.jpg
Label file: S1_146-Aug23_1_156-20190822133230.txt
Abbreviations:
YYYYMMDDHHMMSS – Capture timestamp with year, month, date, hour, minutes, and second
Seq – Sequence number created by the motion program to separate images
C – Identification of two cameras with Id=0 or Id=1 in system identified by SZ_IP
MonthDate – Folder name for where the original image were stored in the system
SZ_IP – Identification of five camera systems: S1_123, S2_146, S3_194, S4_199, S5_187 (Two cameras in each system)
X – An index number related to a specific camera and folder ensuring unique file names of background images from different camera systems.
The important information in a filename is system (SZ_IP), camera Id (C) and timestamp (YYYYMMDDHHMMSS).
The three best YOLOv5 models (YOLOv5models.zip) from the paper are available in pytorch format.
All models are tested with YOLOv5 release v7.0 (22-11-2022): ultralytics/yolov5: YOLOv5 in PyTorch
insect1201-bestF1-640v5m.pt: Model no. 6 in Table 2 (F1=0.912)
insect1201-bestF1-1280v5m6.pt: Model no. 8 in Table 2 (F1=0.925)
insect1201-bestF1-1280v5m6.pt: Model no. 10 in Table 2 (F1=0.932)
insects-1201val.yaml: YAML file with label names to train YOLOv5
trainInsects-1201m.sh: Linux bash shell script with parameters to train YOLOv5m6
valInsectsF1-1201.sh: Linux bash shell script with parameters to validated models
用于训练、验证与测试的昆虫基准数据集(train1201.zip、val1201.zip及test1201.zip),采用延时摄影图像,相关细节见下述论文:
Bjerge K、Alison J、Dyrmann M、Frigaard C.E.、Mann H. M. R.、Høye T.T.:《基于深度学习的相机陷阱图像昆虫精准检测与识别》,bioRxiv:10.1101/2022.10.25.513484v1
标签采用YOLO(You Only Look Once)格式,参照ultralytics/yolov5的标签规范。
经标注的训练与验证数据集包含9类昆虫,具体如下:
0 七星瓢虫(Coccinellidae septempunctata)
1 西方蜜蜂(Apis mellifera)
2 石熊蜂(Bombus lapidarius)
3 大地熊蜂(Bombus terrestris)
4 长翅食蚜蝇(Eupeodes corolla)
5 条斑食蚜蝇(Episyrphus balteatus)
6 荨麻蛱蝶(Aglais urticae)
7 普通黄胡蜂(Vespula vulgaris)
8 长尾管蚜蝇(Eristalis tenax)
测试数据集包含额外的昆虫类别:
9 非熊蜂类采花膜翅目昆虫(Non-Bombus Anthophila)
10 熊蜂属物种(Bombus spp.)
11 食蚜蝇科(Syrphidae)
12 蝇类物种(Fly spp.)
13 难以识别的昆虫(Unclear insect)
14 混合动物:
——————————
蝶类(Rhopalocera)
非采花蜂类膜翅目(Non-Anthophila Hymenoptera)
非食蚜蝇科双翅目(Non-Syrphidae Diptera)
非Conccinalidae鞘翅目(Non-Conccinalidae Coleoptera)
Concinellidae科
其他动物
图像文件(.jpg)与标签文件(.txt)存在两种命名规范:
无昆虫的背景图像命名格式为:"X_Seq-YYYYMMDDHHMMSS-snapshot"。示例:背景图像:12_13-20190704172200-snapshot.jpg;空标签文件:12_13-20190704172200-snapshot.txt
含昆虫标注的图像命名格式为:"SZ_IP-MonthDate_C_Seq-YYYYMMDDHHMMSS"。示例:图像文件:S1_146-Aug23_1_156-20190822133230.jpg;标签文件:S1_146-Aug23_1_156-20190822133230.txt
缩写说明:
YYYYMMDDHHMMSS:拍摄时间戳,格式为年、月、日、时、分、秒
Seq:运动程序生成的序列编号,用于区分不同图像
C:系统内两台相机的标识,ID为0或1,由SZ_IP标识所属系统
MonthDate:系统中存储原始图像的文件夹名称
SZ_IP:5套相机系统的标识,分别为S1_123、S2_146、S3_194、S4_199、S5_187(每套系统含2台相机)
X:与特定相机及文件夹相关的索引编号,用于确保不同相机系统生成的背景图像文件名唯一
文件名中核心信息为:所属相机系统(SZ_IP)、相机ID(C)以及拍摄时间戳(YYYYMMDDHHMMSS)。
本论文中表现最优的3款YOLOv5模型(YOLOv5models.zip)已以PyTorch格式提供。
所有模型均基于YOLOv5 v7.0版本(2022年11月22日发布)进行测试,相关代码参照ultralytics/yolov5:PyTorch实现的YOLOv5。
insect1201-bestF1-640v5m.pt:对应论文表2中的第6号模型(F1值=0.912)
insect1201-bestF1-1280v5m6.pt:对应论文表2中的第8号模型(F1值=0.925)
insect1201-bestF1-1280v5m6.pt:对应论文表2中的第10号模型(F1值=0.932)
insects-1201val.yaml:用于YOLOv5训练的标签名称配置YAML文件
trainInsects-1201m.sh:用于训练YOLOv5m6的Linux Bash脚本
valInsectsF1-1201.sh:用于模型验证的Linux Bash脚本
创建时间:
2022-12-05



