基于增强型Tiny-YOLOV3模型的野鸡识别方法

易诗; 沈练; 周思尧; 朱竞铭; 袁学松

doi:10.11975/j.issn.1002-6819.2020.13.017

基于增强型Tiny-YOLOV3模型的野鸡识别方法

1.
成都理工大学信息科学与技术学院<网络安全学院、牛津布鲁克斯学院>，成都 610059
2.
电子科技大学电子科学与工程学院，成都 610054

基金项目: 国家自然科学基金项目（61771096）；国家大学生创新创业项目（201910616129）

计量
- 文章访问数: 1009
- HTML全文浏览量: 0
- PDF下载量: 517
出版历程
- 收稿日期: 2020-02-03
- 修回日期: 2020-05-26
- 发布日期: 2020-06-30

Recognition method of pheasant using enhanced Tiny-YOLOV3 model

1.
College of Information Science and Technology , Chengdu University of Technology, Chengdu 610059, China
2.
College of Electronic Science and Engineering, University of Electronic Science and Technology, Chengdu 610054, China

摘要

摘要: 智慧农业病虫害检测技术发展迅猛，而对农作物具有危害的鸟类检测技术尚处于起步阶段，近年来由于生态改善，野鸡繁殖数量激增，其喜食小麦、玉米、红薯等农作物的种子与幼苗，对农业造成一定危害。该研究提出了一种适宜于嵌入式系统部署的人工智能野鸡识别方法。由于在野外环境下移动平台上部署，需采用轻量级网络，同时保证检测精度与实时性，因此，根据Tiny-YOLOV3轻量级目标检测网络基本结构，提出了一种针对野外复杂环境中出现野鸡的实时检测网络-增强型轻量级目标检测网络（Enhanced Tiny-YOLO，ET-YOLO），该网络特征提取部分加深Tiny-YOLOV3特征提取网络深度，增加检测尺度以提高原网络目标检测精度，网络检测层使用基于CenterNet结构的检测方式以进一步提高检测精度与检测速度。使用野外实地采集各种环境下出现的野鸡图像作为数据集，包括不同距离、角度、环境出现的野鸡共计6 000幅高清图像制作数据集。试验结果表明，ET-YOLO在视频中复杂环境下出现的野鸡平均检测精度达86.5%，平均检测速度62帧/s，相对改进前Tiny-YOLOV3平均检测精度提高15个百分点，平均检测速度相对改进前Tiny-YOLOV3提高2帧/s，相对YOLOV3、Faster-RCNN与SSD_MobileNetV2主流代表性目标检测算法，平均检测精度分别提高1.5、1.1与18个百分点，平均检测速度分别提高38、47与1帧/s。可高效实时地对复杂环境下出现的野鸡进行识别，并且检测模型大小为56 MB，适宜于在农业机器人，智能农机所搭载的嵌入式系统上部署。
- 农业 /
- 人工智能 /
- 嵌入式系统 /
- 野鸡识别 /
- ET-YOLO /
- CenterNet检测结构
Abstract: The increase of pheasants has posed a threaten to crops as the advancement of ecology. However, most conventional methods of bird repellent have inherent deficiencies in terms of efficiency and danger. An efficiency monitoring method for pheasant is necessary to combine with artificial intelligence, in order to provide early warning and expulsion of pheasants. Normally, pheasant activities are mostly in the early morning and dusk under complex environment with protective color or habit of hiding. This behavior has made monitoring methods much more challenge. In this paper, a novel recognition method for pheasant has been proposed on the deployment of embedded computing platform, combined with the enhanced Tiny-YOLOV3 target detection network, particularly on considering the behavior of pheasant and specific living conditions. A lightweight network is required to ensure the accuracy and real-time monitoring due to the deployment on a mobile platform in the field environment. A real-time monitoring network ET-YOLO has also been established for the emergence of pheasants in a complex field environment, according to the basic structure of the Tiny-YOLOV3 lightweight target detection network. The feature extraction can deepen the net depth of Tiny-YOLOV3, and thereby increase the detection scale to improve the detection accuracy of original net target. CenterNet structure was used in the net detection layer to further enhance the detection accuracy and speed. The dataset of pheasant monitoring was produced after augmentation using the field collection of images in various environments, including 6000 high resolution images of pheasant in different distances, angles and environments. The indicators of experimental evaluation were mainly tested in terms of accuracy, real-time performance, and model size. Specifically, the average detection accuracy, average detection speed, and detection model size of the pheasant were used for evaluation. The experimental results showed that the average detection accuracy of ET-YOLO in the complex field environment was 86.5%, and the average detection speed was 62 frames/s, 15% higher than that of initial Tiny-YOLOV3. The average detection accuracy was higher than that of YOLOV3, Faster-RCNN and SSD_MobileNetV2 by 1.5%, 1.1% and 18%, respectively. The average detection speed was 38 frames /s, 47 frames /s and 1 frame/s higher than that of YOLOV3, Faster-RCNN and SSD_MobileNetV2, respectively, when the detection model size of 56 MB. The proposed method can be suitable for the deployment on embedded computing platforms equipped with agricultural robots and intelligent machines in terms of recognition accuracy, real-time performance, and model size, particularly recognizing pheasants in complex environments.
- agriculture /
- artificial intelligence /
- embedded system /
- pheasant recognition /
- ET-YOLO /
- CenterNet detection structure

HTML全文

参考文献(30)

[1]	卢振宇，孙连新，黄志银，等. 野鸡对春玉米的危害及综防策略研究[J]. 农业科技通讯，2017(7)：65-67.Lu Zhenyu, Sun Lianxin, Huang Zhiyin, et al. Study on the harm of pheasant to spring corn and its integrated control strategy[J]. Agricultural Science and Technology Communication, 2017(7): 65-67. (in Chinese with English abstract)
[2]	国家森防总站. 2004年全国林业有害生物发生趋势预测[EB/OL]. 2004-02-19 [2019-05-23]. http: //gssfz. nease. net/4. html.
[3]	李燕，万津瑜，徐环李，等. 果园鸟害防治[J]. 北方园艺，2012(3)：134-135.Li Yan, Wan Jinyu, Xu Huanli, et al. Bird pest control in orchard[J]. Northern Horticulture, 2012(3): 134-135. (in Chinese with English abstract)
[4]	He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[5]	Girshick R. Fast R-CNN [C]//IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440-1448.
[6]	Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[7]	Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[8]	Redmon J, Farhadi A. Yolov3: An incremental improvement [EB/OL]. (2018-04-08) [2018-09-07]. org/abs/1804. 02767.
[9]	熊俊涛，刘振，汤林越，等. 自然环境下绿色柑橘视觉检测技术研究[J]. 农业机械学报，2018，49(4)：45-52.Xiong Juntao, Liu Zheng, Tang Linyue, et al. Research on visual inspection technology of green citrus in natural environment[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(4): 45-52. (in Chinese with English abstract)
[10]	赵德安，刘晓洋，孙月平，等. 基于机器视觉的水下河蟹识别方法[J]. 农业机械学报，2019，50(3)：151-158.Zhao Dean, Liu Xiaoyang, Sun Yueping, et al. Detection of under water crabs based on machine vision[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(3): 151-158. (in Chinese with English abstract)
[11]	吕石磊，卢思华，李震，等. 基于改进YOLOv3-LITE轻量级神经网络的柑橘识别方法[J]. 农业工程学报，2019，35(17)：205-215.Lü Shilei, Lu Sihua, Li Zhen, et al. Orange recognition method using improved YOLOv3-LITE lightweight neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(17): 205-215. (in Chinese with English abstract).
[12]	燕红文，刘振宇，崔清亮，等. 基于改进 Tiny-YOLO 模型的群养生猪脸部姿态检测[J]. 农业工程学报，2019，35(18)：169-180.Yan Hongwen, Liu Zhenyu, Cui Qingliang, et al. Detection of facial gestures of group pigs based on improved Tiny-YOLO[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(18): 169-180. (in Chinese with English abstract)
[13]	易诗，李欣荣，吴志娟，等. 基于红外热成像与改进YOLOV3的夜间野兔监测方法[J]. 农业工程学报，2019，35(19)：215-222.Yi Shi, Li Xinrong, Wu Zhijuan, et al. Night hare detection method based on infrared thermal imaging and improved YOLOV3[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(19): 215-222. (in Chinese with English abstract)
[14]	Duan Kaiwen, Bai Song, Ling Xixie, et al. CenterNet: Keypoint triplets for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition. United States: IEEE, 2019: 3668-3685.
[15]	Neubeck A, Van Gool L. Efficient non-maximum suppression[C]//18th International Conference on Pattern Recognition (ICPR). Springer: Berlin, German, 2006, 3: 850-855.
[16]	刘军，后士浩，张凯，等. 基于增强 Tiny YOLOV3 算法的车辆实时检测与跟踪[J]. 农业工程学报，2019，35(8)：118-126.Liu Jun, Hou Shihao, Zhang Kai, et al. Real-time vehicle detection and tracking based on enhanced Tiny YOLOV3 algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(8): 118-126. (in Chinese with English abstract).
[17]	Zhou Xingyi, Wang Dequan, Kr?henbühl P, et al. Objects as Points [C]//IEEE Conference on Computer Vision and Pattern Recognition. United States: IEEE, 2019: 2678-2689.
[18]	李善军，胡定一，高淑敏，等. 基于改进 SSD 的柑橘实时分类检测[J]. 农业工程学报，2019，35(24)：307-314.Li Shanjun, Hu Dingyi, Gao Shumin, et al. Real-time classification and detection of citrus based on improved single short multibox detecter[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(24): 307-314. (in Chinese with English abstract)
[19]	Loshchilov I, Hutter F. SGDR: stochastic gradient descent with warm restarts[J]. arXiv: 2016, 1608. 03983.
[20]	Mehta S, Rastegari M, Shapiro L, et al. Espnetv2: A light-weight, power efficient, and general purpose convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. United States: IEEE, 2019: 9190-9200.
[21]	Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[22]	Lu J, Lee W S, Gan H, et al. Immature citrus fruit detection based on local binary pattern feature and hierarchical contour analysis[J]. Biosystems Engineering, 2018, 171: 78-90.
[23]	Zhao C, Lee W S, He D. Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove[J]. Computers and Electronics in Agriculture, 2016, 124: 243-253.
[24]	Liu S, Yang C, Hu Y, et al. A method for segmentation and recognition of mature citrus and branches-leaves based on regional features[C]//Chinese Conference on Image and Graphics Technologies. Singapore: Springer, 2018: 292-301.
[25]	Lin Tsung Yi, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA: IEEE, 2017: 2117-2125.
[26]	Liang Zhen, Shao Jie, Zhang Dongyang, et al. Small object detection using deep feature pyramid networks[C]//Pacific Rim Conference on Multimedia, Hefei, China: Springer, 2018: 554-564.
[27]	Microsoft. PASCAL-VOC2012 [DB/OL]. (2012-02-20) [2019-08-02]. http://host.robots.ox.ac.uk/pascal/VOC/voc2012.
[28]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[29]	Kirillov A, Girshick R, He Kaiming, et al. Panoptic feature pyramid networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, California: IEEE, 2019: 6399-6408.
[30]	Liu Jun, Li Pengfei. A mask R-CNN model with improved region proposal network for medical ultrasound image[C]//Proceedings of the International Conference on Intelligent Computing, Wuhan: Springer, 2018: 26-33.

施引文献(39)

期刊类型引用(12)

1.	刘思幸，李爽，缪宏，柴岩，陈福康，王健，董佩璇. 基于YOLOv3不同场景辣椒采摘机器人识别定位研究. 农机化研究. 2024(02): 38-43 . 百度学术
2.	胡珂，沈家晓，凌在盈，张登荣，王嘉芃. 高分辨率遥感影像城市建筑垃圾自动识别的多种标注形式对比研究. 自动化应用. 2024(05): 47-51+54 . 百度学术
3.	张勇，翟今成，王俪晓，宋丙国，陈雷. 基于PP-YOLO的农业病虫害识别算法. 中国果菜. 2024(05): 80-87 . 百度学术
4.	纪宝锋，周孟创，朱芷芫，陈嘉辉，朱君，李斌. 畜禽个体识别技术研究进展. 中国猪业. 2024(03): 47-58 . 百度学术
5.	孙志坚，王健，时佳，白晓平. 基于YOLOv 4的机收甜菜破损检测方法研究. 农机化研究. 2023(05): 6-12 . 百度学术
6.	郭建军，何国煌，徐龙琴，刘同来，冯大春，刘双印. 基于改进YOLO v4的肉鸽行为检测模型研究. 农业机械学报. 2023(04): 347-355 . 百度学术
7.	赵春江，梁雪文，于合龙，王海峰，樊世杰，李斌. 基于改进YOLO v7的笼养鸡/蛋自动识别与计数方法. 农业机械学报. 2023(07): 300-312 . 百度学术
8.	王巧华，顾伟，蔡沛忠，张洪洲. 基于改进YOLO v4的群体棉种双面破损检测方法. 农业机械学报. 2022(01): 389-397 . 百度学术
9.	张展榜，罗志聪，周志斌，李鹏博，孙奇燕. 自然环境下基于增强YOLOv3的百香果目标检测. 安徽农业科学. 2022(06): 186-192+197 . 百度学术
10.	刘双印，范文婷，邓皓，何国煌，陈耀聪，周冰，李锦慧，冯大春，吴惠粦，李景彬，尹航. 采用改进RetinaNet的笼养肉鸽繁育期个体检测模型. 农业工程学报. 2022(13): 184-193 . 本站查看
11.	侯加林，房立发，吴彦强，李玉华，席芮. 基于深度学习的生姜种芽快速识别及其朝向判定. 农业工程学报. 2021(01): 213-222 . 本站查看
12.	陈锋军，朱学岩，周文静，郑一力，顾梦梦，赵燕东. 利用无人机航拍视频结合YOLOv3模型和SORT算法统计云杉数量. 农业工程学报. 2021(20): 81-89 . 本站查看