Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery

Bhowmik, N.; Barker, J.W.; Gaus, Y.F.A.; Breckon, T.P.

Abstract

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade RCNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of ∼ 76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.

Citation

Bhowmik, N., Barker, J., Gaus, Y., & Breckon, T. (2022, June). Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery. Presented at 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, Louisiana

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
• Start Date: Jun 19, 2022
• End Date: Jun 20, 2022
• Acceptance Date: Apr 11, 2022
• Online Publication Date: Aug 23, 2022
• Publication Date: 2022-06
• Deposit Date: May 4, 2022
• Publicly Available Date: Jun 25, 2022
• Publisher: Institute of Electrical and Electronics Engineers
• ISBN: 9781665487405
• DOI: https://doi.org/10.1109/cvprw56347.2022.00052
• Public URL: https://durham-repository.worktribe.com/output/1137238