Automated aerial animal detection when spatial resolution conditions are varied

Brown, Jasper; Qiao, Yongliang; Clark, Cameron; Lomax, Sabrina; Rafique, Khalid; Sukkarieh, Salah

doi:10.1016/j.compag.2022.106689

Cited by 22 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the simple method of livestock detection, advancements in Artificial Intelligence (AI) and Machine Learning (ML) have allowed researchers to detect livestock using a pre-trained Convolutional Neural Network (CNN)-based architecture. For instance, an adjusted version of R-CNN was employed to identify and count livestock on a grazing field [19]. In this method, a selective search algorithm was used to generate a region proposal and then applied a CNN to extract the features in the region, which were then later classified using a Support Vector Machine (SVM).…”

Section: Literature Reviewmentioning

confidence: 99%

Livestock Management on Grazing Field: A FANET Based Approach

et al. 2022

View full text Add to dashboard Cite

In recent times, designated grazing areas/fields or routes for livestock grazing are usually defined. Hence, their herding activities’ success relies on data extracted from aerial photographs. As such, a direct and cost-effective way of monitoring livestock for perimeter coverage and in other natural situations is required. This paper presents a coverage solution involving multiple unmanned aerial vehicles interacting. The presented approach is built on a graph, with geographic coordinates set such that several Unmanned Aerial Vehicles (UAVs) can successfully cover the area. The maximum flying time determines the number of UAVs employed for coverage. The proposed solution is thought to solve some practical problems encountered during the execution of the task with actual UAVs. It is suitable for long-term monitoring of animal behavior under various weather conditions and observing the relationship between livestock distribution and available resources on a grazing field. The simulation was carried out using MATLAB and aerial images from Google Earth.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Livestock Management on Grazing Field: A FANET Based Approach

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Due to increasing levels of industrialization and urbanization, dozens of major diseases and pests found on 2 billion hectares of land around the world all year round (Sun et al, 2019). The management of these diseases and pests requires a significant amount of manual input for agricultural plant protection operations, resulting in a sharp rise in labor costs (Yongliang et al, 2019;Brown et al, 2022). Therefore, intelligent plant protection information systems such as rice canopy pest monitoring systems (Li et al, 2022), field pest monitoring and forecasting systems (Liu et al, 2022), meteorological monitoring systems, and crop disease real-time monitoring and early warning systems have been widely used.…”

Section: Introductionmentioning

confidence: 99%

Efficient Windows malware identification and classification scheme for plant protection information systems

2023

View full text Add to dashboard Cite

Due to developments in science and technology, the field of plant protection and the information industry have become increasingly integrated, which has resulted in the creation of plant protection information systems. Plant protection information systems have modernized how pest levels are monitored and improved overall control capabilities. They also provide data to support crop pest monitoring and early warnings and promote the sustainable development of plant protection networks, visualization, and digitization. However, cybercriminals use technologies such as code reuse and automation to generate malware variants, resulting in continuous attacks on plant protection information terminals. Therefore, effective identification of rapidly growing malware and its variants has become critical. Recent studies have shown that malware and its variants can be effectively identified and classified using convolutional neural networks (CNNs) to analyze the similarity between malware binary images. However, the malware images generated by such schemes have the problem of image size imbalance, which affects the accuracy of malware classification. In order to solve the above problems, this paper proposes a malware identification and classification scheme based on bicubic interpolation to improve the security of a plant protection information terminal system. We used the bicubic interpolation algorithm to reconstruct the generated malware images to solve the problem of image size imbalance. We used the Cycle-GAN model for data augmentation to balance the number of samples among malware families and build an efficient malware classification model based on CNNs to improve the malware identification and classification performance of the system. Experimental results show that the system can significantly improve malware classification efficiency. The accuracy of RGB and gray images generated by the Microsoft Malware Classification Challenge Dataset (BIG2015) can reach 99.76% and 99.62%, respectively.

show abstract

“…To minimize costs when using satellite images of animals, the lowest spatial resolution data that enable accurate livestock detection should be selected. Therefore, Brown et al determined the association between object detector performance and spatial degradation for cattle, sheep, and dogs [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

An Integrated Goat Head Detection and Automatic Counting Method Based on Deep Learning

Liu

Chen

et al. 2022

Animals

View full text Add to dashboard Cite

Goat farming is one of the pillar industries for sustainable development of national economies in some countries and plays an active role in social and economic development. In order to realize the precision and intelligence of goat breeding, this paper describes an integrated goat detection and counting method based on deep learning. First, we constructed a new dataset of video images of goats for the object tracking task. Then, we took YOLOv5 as the baseline of the object detector and improved it using a series of advanced methods, including: using RandAugment to explore suitable data augmentation strategies in a real goat barn environment, using AF-FPN to improve the network’s ability to represent multi-scale objects, and using the Dynamic Head framework to unify the attention mechanism with the detector’s heads to improve its performance. The improved detector achieved 92.19% mAP, a significant improvement compared to the 84.26% mAP of the original YOLOv5. In addition, we also input the information obtained by the detector into DeepSORT for goat tracking and counting. The average overlap rate of our proposed method is 89.69%, which is significantly higher than the 82.78% of the original combination of YOLOv5 and DeepSORT. In order to avoid double counting as much as possible, goats were counted using the single-line counting based on the results of goat head tracking, which can support practical applications.

show abstract

Automated aerial animal detection when spatial resolution conditions are varied

Cited by 22 publications

References 28 publications

Livestock Management on Grazing Field: A FANET Based Approach

Livestock Management on Grazing Field: A FANET Based Approach

Efficient Windows malware identification and classification scheme for plant protection information systems

An Integrated Goat Head Detection and Automatic Counting Method Based on Deep Learning

Contact Info

Product

Resources

About