Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Körez, Atakan; Barışçı, Necaattin; Çetin, A. Enis; Ergün, Uçman

doi:10.3390/ijgi9060370

Cited by 20 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many ensemble methods [ 35 , 36 ], therefore, seek to promote diversity among their combined models. More recent studies have shown the effectiveness of ensemble methods in both classification [ 37 , 38 ] and object detection [ 39 , 40 ] problems. However, the process to ensemble object detectors is costly in time and memory both at training and inference, which limits its applicability.…”

Section: Introductionmentioning

confidence: 99%

Ensemble model for rail surface defects detection

Wang

Liu

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

The detection of rail surface defects is vital for high-speed rail maintenance and management. The CNN-based computer vision approach has been proved to be a strong detection tool widely used in various industrial scenarios. However, the CNN-based detection models are diverse from each other in performance, and most of them require sufficient training samples to achieve high detection performance. Selecting an appropriate model and tuning it with insufficient annotated rail defect images is time-consuming and tedious. To overcome this challenge, motivated by ensemble learning that uses multiple learning algorithms to obtain better predictive performance, we develop an ensemble framework for industrialized rail defect detection. We apply multiple backbone networks individually to obtain features, and mix them in a binary format to obtain better and more diverse sub-networks. Image augmentation and feature augmentation operations are randomly applied to further make the model more diverse. A shared feature pyramid network is adopted to reduce model parameters as well as computation cost. Experimental results substantiate that the approach outperforms single detecting architecture in our specified rail defect task. On the collected dataset with 8 defect classes, our algorithm achieves 7.4% higher mAP.5 compared with YOLOv5 and 2.8% higher mAP.5 compared with Faster R-CNN.

show abstract

Section: Introductionmentioning

confidence: 99%

Ensemble model for rail surface defects detection

Wang

Liu

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The most frequently used augmentation approach in remote sensing is also color and geometrical transformations [45], [49], [19], [16]. In [21], rescaling, slicing, and rotation augmentations were applied in order to increase the quantity and diversity of training samples in building semantic segmentation task.…”

Section: Related Workmentioning

confidence: 99%

“…The considered in our study transformations are described in Table 1. Since most of the works in remote sensing do not specify albumentations parameters for images augmentation [49], [19], we also set default parameters.…”

Section: Object-based Augmentationmentioning

confidence: 99%

Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation

Illarionova¹,

Nesteruk²,

Shadrin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Today deep convolutional neural networks (CNNs) push the limits for most computer vision problems, define trends, and set state-of-the-art results. In remote sensing tasks such as object detection and semantic segmentation, CNNs reach the SotA performance. However, for precise performance, CNNs require much high-quality training data. Rare objects and the variability of environmental conditions strongly affect prediction stability and accuracy. To overcome these data restrictions, it is common to consider various approaches including data augmentation techniques. This study focuses on the development and testing of object-based augmentation. The practical usefulness of the developed augmentation technique is shown in the remote sensing domain, being one of the most demanded in effective augmentation techniques. We propose a novel pipeline for georeferenced image augmentation that enables a significant increase in the number of training samples. The presented pipeline is called object-based augmentation (OBA) and exploits objects' segmentation masks to produce new realistic training scenes using target objects and various label-free backgrounds. We test the approach on the buildings segmentation dataset with six different CNN architectures and show that the proposed method benefits for all the tested models. We also show that further augmentation strategy optimization can improve the results. The proposed method leads to the meaningful improvement of U-Net model predictions from 0.78 to 0.83 F1-score.

show abstract

“…The training of SSD was done using ResNet-152 architecture [41] from Torchvision version 0.3.0 [42]. [35] and [43]. The full parameters and layers of the SSD model that we used are available in Appendix A.…”

Section: Preparing the Training And Validation Datamentioning

confidence: 99%

“…The f1-Score (Equation (3)) was used to assess the performance of species classification; therefore, it was only computed for sites 1 and 2, where species information was available. Due to the class imbalance [35] and [43]. The full parameters and layers of the SSD model that we used are available in Appendix A.…”

Section: Detecting With Single Modelsmentioning

confidence: 99%

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

et al. 2020

View full text Add to dashboard Cite

Traditional methods for individual tree-crown (ITC) detection (image classification, segmentation, template matching, etc.) applied to very high-resolution remote sensing imagery have been shown to struggle in disparate landscape types or image resolutions due to scale problems and information complexity. Deep learning promised to overcome these shortcomings due to its superior performance and versatility, proven with reported detection rates of ~90%. However, such models still find their limits in transferability across study areas, because of different tree conditions (e.g., isolated trees vs. compact forests) and/or resolutions of the input data. This study introduces a highly replicable deep learning ensemble design for ITC detection and species classification based on the established single shot detector (SSD) model. The ensemble model design is based on varying the input data for the SSD models, coupled with a voting strategy for the output predictions. Very high-resolution unmanned aerial vehicles (UAV), aerial remote sensing imagery and elevation data are used in different combinations to test the performance of the ensemble models in three study sites with highly contrasting spatial patterns. The results show that ensemble models perform better than any single SSD model, regardless of the local tree conditions or image resolution. The detection performance and the accuracy rates improved by 3–18% with only as few as two participant single models, regardless of the study site. However, when more than two models were included, the performance of the ensemble models only improved slightly and even dropped.

show abstract

Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Cited by 20 publications

References 38 publications

Ensemble model for rail surface defects detection

Ensemble model for rail surface defects detection

Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

Contact Info

Product

Resources

About