Improved Raindrop Detection using Combined Shape and Saliency Descriptors with Scene Context Isolation

Webster, D.D.; Breckon, T.P.

Abstract

The presence of raindrop induced image distortion has a significant negative impact on the performance of a wide range of all-weather visual sensing applications including within the increasingly import contexts of visual surveillance and vehicle autonomy. A key part of this problem is robust raindrop detection such that the potential for performance degradation in effected image regions can be identified. Here we address the problem of raindrop detection in colour video imagery using an extended feature descriptor comprising localised shape, saliency and texture information isolated from the overall scene context. This is verified within a bag of visual words feature encoding framework using Support Vector Machine and Random Forest classification to achieve notable 86% detection accuracy with minimal false positives compared to prior work. Our approach is evaluated under a range of environmental conditions typical of all-weather automotive visual sensing applications.

Citation

Webster, D., & Breckon, T. (2015). Improved Raindrop Detection using Combined Shape and Saliency Descriptors with Scene Context Isolation. In Proc. Int. Conf. on Image Processing (4376-4380). https://doi.org/10.1109/ICIP.2015.7351633

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: Proceedings of IEEE International Conference on Image Processing
• Start Date: Sep 27, 2015
• End Date: Sep 30, 2015
• Publication Date: 2015
• Deposit Date: Oct 4, 2015
• Publicly Available Date: Oct 13, 2015
• Publisher: Institute of Electrical and Electronics Engineers
• Pages: 4376-4380
• Book Title: Proc. Int. Conf. on Image Processing
• DOI: https://doi.org/10.1109/ICIP.2015.7351633
• Keywords: raindrop detection, rain detection, rain removal, rain noise removal, rain interference, scene context, raindrop saliency, rain classification
• Public URL: https://durham-repository.worktribe.com/output/1151972
• Publisher URL: https://breckon.org/toby/publications/papers/webster15raindrop.pdf
• Related Public URLs: http://breckon.eu/toby/publications/papers/webster15raindrop.pdf