Critical class oriented active learning for hyperspectral image classification

Wei, Di; Crawford, Melba M.

doi:10.1109/igarss.2011.6050083

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, AL minimises the need to hand-label target poplar samples without sacrificing classification performance. As highlighted in [59], when the class accuracy is high, the active learner avoids querying irrelevant samples.…”

Section: Effect Of Transfer Direction: Case Of the Poplar Classmentioning

confidence: 99%

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

Hamrouni

Paillassa

Chéret

et al. 2021

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

show abstract

Section: Effect Of Transfer Direction: Case Of the Poplar Classmentioning

confidence: 99%

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

Hamrouni

Paillassa

Chéret

et al. 2021

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

show abstract

“…ised the need to label target poplar samples without sacrificing the classification performance. As reported in (Di, Crawford, 2011), when the class accuracy is high, the active learner avoids querying irrelevant samples.…”

Section: Sentinel-2-based Classification: High Capacity To Identify Pmentioning

confidence: 99%

Synergistic Use of Sentinel-1 and Sentinel-2 Time Series for Poplar Plantations Monitoring at Large Scale

Hamrouni

Paillassa

Chéret

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The current context of availability of Earth Observation satellite data at high spatial and temporal resolutions makes it possible to map large areas. Although supervised classification is the most widely adopted approach, its performance is highly dependent on the availability and the quality of training data. However, gathering samples from field surveys or through photo interpretation is often expensive and time-consuming especially when the area to be classified is large. In this paper we propose the use of an active learning-based technique to address this issue by reducing the labelling effort required for supervised classification while increasing the generalisation capabilities of the classifier across space. Experiments were conducted to identify poplar plantations in three different sites in France using Sentinel-2 time series. In order to characterise the age of the identified poplar stands, temporal means of Sentinel-1 backscatter coefficients were computed. The results are promising and show the good capacities of the active learning-based approach to achieve similar performance (Poplar F-score &geq; 90%) to traditional passive learning (i.e. with random selection of samples) with up to 50% fewer training samples. Sentinel-1 annual means have demonstrated their potential to differentiate two stand ages with an overall accuracy of 83% regardless of the cultivar considered.

show abstract

“…Clusters are used to annotate the healthy and unhealthy (spoiled) samples for classification [21], [44], [45]. Consequently, the changed pixels have been labeled as spoiled while the unchanged ones as healthy.…”

Section: Figure 5: Principal Component Analysismentioning

confidence: 99%

Prediction of Microbial Spoilage and Shelf-Life of Bakery Products Through Hyperspectral Imaging

et al. 2020

View full text Add to dashboard Cite

The shelf life of bakery products highly depends on the environment and it may get spoiled earlier than its expiry which results in food-borne diseases and may affect human health or may get wasted beforehand. The traditional spoilage detection methods are time-consuming and destructive in nature due to the time taken to get microbiological results. To the best of the author's knowledge, this work presents a novel method to automatically predict the microbial spoilage and detect its spatial location in baked items using Hyperspectral Imaging (HSI) range from 395 − 1000 nm. A spectral preserve fusion technique has been proposed to spatially enhance the HSI images while preserving the spectral information. Furthermore, to automatically detect the spoilage, Principal Component Analysis (PCA) followed by K-means and SVM has been used. The proposed approach can detect the spoilage almost 24 hours before it started appearing or visible to a naked eye with 98.13% accuracy on test data. Furthermore, the trained model has been validated through external dataset and detected the spoilage almost a day before it started appearing visually.

show abstract

Critical class oriented active learning for hyperspectral image classification

Cited by 6 publications

References 9 publications

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

Synergistic Use of Sentinel-1 and Sentinel-2 Time Series for Poplar Plantations Monitoring at Large Scale

Prediction of Microbial Spoilage and Shelf-Life of Bakery Products Through Hyperspectral Imaging

Contact Info

Product

Resources

About