A study of duck detection using deep neural network based on RetinaNet model in smart farming
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In a duck cage, ducks are placed in various states. In particular, if a duck is overturned and falls or dies, it will adversely affect the growing environment. In order to prevent the foregoing, it was necessary to continuously manage the cage for duck growth. This study proposes a method using an object detection algorithm to improve the foregoing. Object detection refers to the work to perform classification and localization of all objects present in the image when an input image is given. To use an object detection algorithm in a duck cage, data to be used for learning should be made and the data should be augmented to secure enough data to learn from. In addition, the time required for object detection and the accuracy of object detection are important. The study collected, processed, and augmented image data for a total of two years in 2021 and 2022 from the duck cage. Based on the objects that must be detected, the data collected as such were divided at a ratio of 9 : 1, and learning and verification were performed. The final results were visually confirmed using images different from the images used for learning. The proposed method is expected to be used for minimizing human resources in the growing process in duck cages and making the duck cages into smart farms.
Abstract
In a duck cage, ducks are placed in various states. In particular, if a duck is overturned and falls or dies, it will adversely affect the growing environment. In order to prevent the foregoing, it was necessary to continuously manage the cage for duck growth. This study proposes a method using an object detection algorithm to improve the foregoing. Object detection refers to the work to perform classification and localization of all objects present in the image when an input image is given. To use an object detection algorithm in a duck cage, data to be used for learning should be made and the data should be augmented to secure enough data to learn from. In addition, the time required for object detection and the accuracy of object detection are important. The study collected, processed, and augmented image data for a total of two years in 2021 and 2022 from the duck cage. Based on the objects that must be detected, the data collected as such were divided at a ratio of 9 : 1, and learning and verification were performed. The final results were visually confirmed using images different from the images used for learning. The proposed method is expected to be used for minimizing human resources in the growing process in duck cages and making the duck cages into smart farms.
참고문헌 (24)
- Zaidi SSA, "A survey of modern deep learning based object detection models", Digit Signal Process, 126, pp.103514~ (2022)[DOI]
- Lin TY, "Focal loss for dense object detection", Proceedings of the IEEE International Conference on Computer Vision, pp.2980~2988 (2017)
- Gikunda PK, "Intelligent Computing-Proceedings of the Computing Conference", pp.763~775 (2019), Springer
- Dhanya VG, "Deep learning based computer vision approaches for smart agricultural applications", Artif Intell Agric, 6, pp.211~229 (2022)[DOI]
- Sa I, "Deepfruits : a fruit detection system using deep neural networks", Sensors, 16, pp.1222~ (2016)[DOI]
- Ren S, "Faster R-CNN: towards real-time object detection with region proposal networks", Advances in neural information processing systems 28: 29th Annual conference on neural information processing systems 2015;, pp.91~99 (2015)
- Bargoti S, "Deep fruit detection in orchards", 2017 IEEE International Conference on Robotics and Automation (ICRA), pp.3626~3633 (2017)
- Sørensen RA, "Thistle detection using convolutional neural networks", EFITA WCCA 2017 Conference (2017)
- Zhu Y, "DenseNet for dense flow", 2017 IEEE International Conference on Image Processing (ICIP), pp.790~794 (2017)
- Albuquerque CKG, "Water spray detection for smart irrigation systems with mask R-CNN and UAV footage", 2020 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), pp.236~240 (2020)
- He K, "Mask R-CNN", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.2961~2969 (2017)
- Osorio K, "A deep learning approach for weed detection in lettuce crops using multispectral images", AgriEngineering, 2, pp.471~488 (2020)[DOI]
- Noble WS, "What is a support vector machine?", Nat Biotechnol, 24, pp.1565~1567 (2006)[DOI]
- "Yolov3: an incremental improvement" (2018)[URL]
- Riekert M, "Automatically detecting pig position and posture by 2D camera imaging and deep learning", Comput Electron Agric, 174, pp.105391~ (2020)[DOI]
- Tedesco-Oliveira D, "Convolutional neural networks in predicting cotton yield from images of commercial fields", Comput Electron Agric, 171, pp.105307~ (2020)[DOI]
- Liu W, "SSD: single shot multibox detector", European Conference on Computer Vision, pp.21~37 (2016), Springer
- Zhou Z, "Real-time kiwifruit detection in orchard using deep learning on AndroidTM smartphones for yield estimation", Comput Electron Agric, 179, pp.105856~ (2020)[DOI]
- Tang J, "Mapping center pivot irrigation systems in the southern Amazon from Sentinel-2 images", Water, 13, pp.298~ (2021)[DOI]
- Shojaeipour A, "Automated muzzle detection and biometric identification via few-shot deep transfer learning of mixed breed cattle", Agronomy, 11, pp.2365~ (2021)[DOI]
- He K, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016)
- Syed-Ab-Rahman SF, "Citrus disease detection and classification using end-to-end anchor-based deep learning model", Appl Intell, 52, pp.927~938 (2022)[DOI]
- He K, "Rethinking ImageNet pre-training", Proceedings of the IEEE, 2019, 4918~4927
- Lin TY, "Feature pyramid networks for object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2117~2125 (2017)