Abstract
Object detection is one of the most important tasks involved in intelligent agriculture systems, especially in pest detection. This paper focuses on a most devastated agricultural disaster: grasshopper plagues. Grasshopper detection and monitoring is of paramount importance in preventing grasshopper
plagues. This paper proposes a probabilistic faster R-CNN algorithm with stochastic region proposing, where a probabilistic region proposal network, an image classification network, and an object detection network are integrated to detect and locate grasshoppers. More specifically, in the proposed framework,
the probabilistic region proposal network considers attributes (e.g. size, shape) of region proposals and the image classification network identifies the existence of grasshoppers while the object detection network scores recognition confidence for a region proposal. By integrating these three networks, the
uncertainty can be passed from end to end, and the final confidence is obtained for each region proposal can be explicitly quantified. To enhance algorithm robustness, a stochastic region proposing algorithm is developed to screen region proposals rather than using a predetermined threshold. The proposed
algorithm is validated by recently collected grasshopper datasets. The experimental results demonstrate that the proposed algorithm not only outperforms competing algorithms in terms of average precision (0.91), average missed rate (0.36), and maximum F1-score (0.9263), but also reduces the false positive rate of recognising the existence of grasshoppers in an open field.
plagues. This paper proposes a probabilistic faster R-CNN algorithm with stochastic region proposing, where a probabilistic region proposal network, an image classification network, and an object detection network are integrated to detect and locate grasshoppers. More specifically, in the proposed framework,
the probabilistic region proposal network considers attributes (e.g. size, shape) of region proposals and the image classification network identifies the existence of grasshoppers while the object detection network scores recognition confidence for a region proposal. By integrating these three networks, the
uncertainty can be passed from end to end, and the final confidence is obtained for each region proposal can be explicitly quantified. To enhance algorithm robustness, a stochastic region proposing algorithm is developed to screen region proposals rather than using a predetermined threshold. The proposed
algorithm is validated by recently collected grasshopper datasets. The experimental results demonstrate that the proposed algorithm not only outperforms competing algorithms in terms of average precision (0.91), average missed rate (0.36), and maximum F1-score (0.9263), but also reduces the false positive rate of recognising the existence of grasshoppers in an open field.
Original language | English |
---|---|
Pages (from-to) | 290-301 |
Number of pages | 12 |
Journal | Neurocomputing |
Volume | 459 |
Early online date | 30 Jun 2021 |
DOIs | |
Publication status | Published - 7 Oct 2021 |
Bibliographical note
Funding Information:This work was supported by the U.K. Science and Technology Facilities Council (STFC) Enabling Wide Area Persistent Remote Sensing for Agriculture Applications by Developing and Coordinating Multiple Heterogeneous Platforms programme and Integrating Advanced Earth Observation and Environmental Information for Sustainable Management of Crop Pests and Diseases programme under grant number ST/N006852/1 and ST/N006712/1.
Keywords
- Object detection
- Image recognition
- Gaussian mixture models
- Region proposal network