Bi-RDNet: Performance Enhancement for Remote Sensing Scene Classification with Rotational Duplicate Layers

Akkul, Erdem Safa; Arican, Berk; Töreyi̇n, Behçet Uğur

doi:10.1007/978-3-030-88113-9_54

Cited by 1 publication

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Time and memory reduction in RS images for the classification worked by Akkul et al 9 Their duplicate layers allow up to 128× memory reduction, and their partial decompression strategy provides ∼2.6× faster processing time. Byju et al 10 use transposed convolution layers on JPEG2000 sub-bands to generate the fully decompressed image in the RSSC task.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Compressed domain classification of remote sensing scene images based on sub-band data fusion

Arican

Akkul²,

Çarkacioğlu³

et al. 2022

Image and Signal Processing for Remote Sensing XXVIII

View full text Add to dashboard Cite

Storing and processing Remote Sensing (RS) images require large amounts of memory space and computing resources. Consequently, RS images are compressed and stored in various compression formats, such as JPEG2000. However, the processing of RS images for machine interpretation and understanding still necessitates the deployment of an image decompression stage in its entirety, followed by a computationally demanding image analysis pipeline. The image analysis stage is commonly composed of machine learning techniques, such as Deep Convolutional Neural Network (DCNN) models. Classification of remote sensing images is among the most common image analysis tasks. In the scope of this paper, we propose a sub-band image based classification method for the Remote Sensing Scene Classification (RSSC) task in the JPEG2000 compressed domain. The proposed approach exploits the already available sub-band image coefficients to classify RS images without needing for full decompression. Our study shows that our method increases the high frequency information in the LL sub-band and allows the image to contain more detail, leading to improved classifier performance while taking advantage of the partial decompression method.

show abstract

Section: Related Workmentioning

confidence: 99%

“…11 RS images can be stored in a compressed domain with the JPEG2000 algorithm. Studies 9,10 have shown that in this compressed environment, DCNN models can be fed with partially decompressed images without full decompression. Partial decompression leads to higher throughput since the time required for decompression is saved.…”

Section: Introductionmentioning

confidence: 99%