Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images

Guo, Wei; Li, Weihong; Gong, Weiguo; Cui, Jinkai

doi:10.3390/rs12050784

Cited by 14 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e process of the meta-testing stage is the same as that of meta-evaluation. Formulas (10) and (11) are used for meta-testing. e algorithm flow is shown in Figure 3.…”

Section: Meta-evaluation and Meta-testmentioning

confidence: 99%

See 1 more Smart Citation

A Joint Optimization Framework of the Embedding Model and Classifier for Meta-Learning

Liu

Chu

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

The aim of meta-learning is to train the machine to learn quickly and accurately. Improving the performance of the meta-learning model is important in solving the problem of small samples and in achieving general artificial intelligence. A meta-learning method based on feature embedding that exhibits good performance on the few-shot problem was previously proposed. In this method, the pretrained deep convolution neural network was used as the embedding model of sample features, and the output of one layer was used as the feature representation of samples. The main limitation of the method is the inability to fuse low-level texture features and high-level semantic features of the embedding model and joint optimization of the embedding model and classifier. Therefore, a multilayer adaptive joint training and optimization method of the embedding model was proposed in the current study. The main characteristics of the current method include using multilayer adaptive hierarchical loss to train the embedding model and using the quantum genetic algorithm to jointly optimize the embedding model and classifier. Validation was performed based on multiple public datasets for meta-learning model testing. The proposed method shows higher accuracy compared with multiple baseline methods.

show abstract

“…e process of the meta-testing stage is the same as that of meta-evaluation. Formulas (10) and (11) are used for meta-testing. e algorithm flow is shown in Figure 3.…”

Section: Meta-evaluation and Meta-testmentioning

confidence: 99%

“…e characteristics of different layers of the deep convolutional neural network comprise different information. e bottom layer comprises high amounts of low-level visual information, whereas the top layer comprises semantic information [11,12]. Low-level visual information and semantic information are important in visual recognition tasks.…”

Section: Introductionmentioning

confidence: 99%

A Joint Optimization Framework of the Embedding Model and Classifier for Meta-Learning

Liu

Chu

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Regarding Semantic Segmentation [84,147,148,149], there are some use cases, such as building footprint extraction [11,12,150,13,14,15,16,17,18], road extraction [151,152,153] and land use and land cover (LULC) analysis [154,155]. • SpaceNet [158,159]: dataset with satellite imagery of the following cities: Rio de Janeiro, Las Vegas, Paris, Khartoum, and Shanghai.…”

Section: Applications On Remote Sensing and Examples Of Available Datasetsmentioning

confidence: 99%

“…Particularly in the context of semantic Segmentation, neural networks have achieved outstanding results [11,12,13,14,15,16,17,18]. Unlike traditional pixel-wise classification, semantic Segmentation using CNNs can preserve the object boundaries producing sharp, fine-scale Segmentation.…”

Section: Introductionmentioning

confidence: 99%

A Review of Remote Sensing Applications on Very High-Resolution Imagery Using Deep Learning-Based Semantic Segmentation Techniques

Borba¹,

Bias²,

Silva³

et al. 2021

IJAERS

View full text Add to dashboard Cite

Semantic Segmentation is a technique in Computer Sciences(CS) to extract information from images. Recent advances in Artificial Intelligence, particularly in Deep Learning, Semantic Segmentation combined with techniques such as convolutional neural networks, have presented better results and exciting results. Due to its power and better results than classical approaches, there has been an increase in research articles in Remote Sensing that propose using deep learning-based semantic Segmentation to extract information from satellite or airborne imagery. In this paper, we surveyed the state-of-the-art of Semantic Segmentation in Remote Sensing from 2010 until 2020 by identifying the research topics and the number of publications and citations. Furthermore, we also pointed out the fundamental algorithms, the main convolutional neural network architectures, backbones, and the most used evaluation metrics. In addition, some datasets were highlighted, as well as some frameworks that can be used to train semantic segmentation deep neural networks. Finally, we have shown some applications of the showcased techniques and concluded the paper by pointing out some research opportunities of Remote Sensing Semantic Segmentation, concerning some bleeding-edge scientific papers published in 2020 in CS.

show abstract

“…We also used data augmentation to balance their sizes. k-means [15] is then used to cluster different numbers of anchor boxes to find the optimised number and size for better results. Finally, the model is retrained by zoom out-category data.…”

Section: Pest Animal Annotation Model Training and Detectionmentioning

confidence: 99%

Pest Animal's Detection and Habitat Identification in Low-resolution Airborne Thermal Imagery

Ulhaq¹,

Khan²

2020

Preprint

View full text Add to dashboard Cite

Invasive species are significant threats to global agriculture and food security being the major causes of crop loss. An operative biosecurity policy requires full automation of detection and habitat identification of the potential pests and pathogens. Unmanned Aerial Vehicles (UAVs) mounted thermal imaging cameras can observe and detect pest animals and their habitats, and estimate their population size around the clock. However, their effectiveness becomes limited due to manual detection of cryptic species in hours of captured flight videos, failure in habitat disclosure and the requirement of expensive high-resolution cameras. Therefore, the cost and efficiency trade-off often restricts the use of these systems. In this paper, we present an invasive animal species detection system that uses cost-effectiveness of consumer-level cameras while harnessing the power of transfer learning and an optimised small object detection algorithm. Our proposed optimised object detection algorithm named Optimised YOLO (OYOLO) enhances YOLO (You Only Look Once) by improving its training and structure for remote detection of elusive targets. Our system, trained on the massive data collected from New South Wales and Western Australia, can detect invasive species (rabbits, Kangaroos and pigs) in real-time with a higher probability of detection (85–100 %), compared to the manual detection. This work will enhance the visual analysis of pest species while performing well on low, medium and high-resolution thermal imagery, and equally accessible to all stakeholders and end-users in Australia via a public cloud.

show abstract

Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images

Cited by 14 publications

References 35 publications

A Joint Optimization Framework of the Embedding Model and Classifier for Meta-Learning

A Joint Optimization Framework of the Embedding Model and Classifier for Meta-Learning

A Review of Remote Sensing Applications on Very High-Resolution Imagery Using Deep Learning-Based Semantic Segmentation Techniques

Pest Animal's Detection and Habitat Identification in Low-resolution Airborne Thermal Imagery

Contact Info

Product

Resources

About