Pretrained Neural Network Models for Guo 2018 study - TensorFlow format

Guo, Tiancheng (Durham University, UK); Breckon, Toby (Durham University, UK)

Actions

Collections

This file is in the following collections:

On The Impact Of Varying Region Proposal Strategies For Raindrop Detection And Classification Using Convolutional Neural Networks - Supporting Materials

Pretrained Neural Network Models for Guo 2018 study - TensorFlow format Open Access

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 important 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 by considering three varying region proposal approaches with secondary classification via a number of novel convolutional neural network architecture variants. This is verified over an extensive dataset with in-frame raindrop annotation to achieve maximal 0.95 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. | Cited in: n The Impact Of Varying Region Proposal Strategies For Raindrop Detection And Classification Using Convolutional Neural Networks (T. Guo, S. Akcay, P. Adey, T.P. Breckon), In Proc. International Conference on Image Processing, IEEE, pp. 3413-3417, 2018. | This collection contains supporting materials in the form of the pre-trained network models and image data used in the study.

Descriptions

Resource type: Dataset
Contributors: Creator: Guo, Tiancheng ¹
Data collector: Guo, Tiancheng ¹
Data curator: Guo, Tiancheng ¹
Contact person: Breckon, Toby ¹
Data curator: Breckon, Toby ¹
Editor: Breckon, Toby ¹

¹ Durham University, UK
Funder
Research methods
Other description
Keyword: Computer vision
Raindrop detection
Rain detection
Rain removal
Rain noise removal
Rain interference
Scene context
Raindrop saliency
Rain classification
Convolutional neural network (CNN)
Deep learning
Subject: Computer vision
Rain and rainfall
Neural networks (Computer science)
Computer Science
Engineering
Location
Language
Cited in
Identifier: ark:/32150/r23j333226h
doi:10.15128/r23j333226h
Rights: MIT Licence (MIT)
Publisher: Durham University
Date Created

File Details

Depositor: T. Breckon
Date Uploaded: 25 November 2018, 16:11:54
Date Modified: 29 November 2018, 12:11:57
Audit Status: Audits have not yet been run on this file.
Related Files: guo-raindrop-detection-dataset-2018.zip
Characterization: File format: zip (ZIP Format)

Mime type: application/zip

File size: 300038803

Last modified: 2018:11:27 23:14:31+00:00

Filename: guo-raindrop-detection-pretrained-model-2018.zip

Original checksum: ea691f2538f1d2e0de57a108b4285173

Activity of users you follow
User Activity	Date
User T. Breckon has updated Pretrained Neural Network Models for Guo 2018 study - TensorFlow format	almost 6 years ago
User N. Syrotiuk has updated Pretrained Neural Network Models for Guo 2018 study - TensorFlow format	almost 6 years ago
User N. Syrotiuk has updated Pretrained Neural Network Models for Guo 2018 study - TensorFlow format	almost 6 years ago
User N. Syrotiuk has updated Pretrained Neural Network Models for Guo 2018 study - TensorFlow format	almost 6 years ago
User T. Breckon has updated Pretrained Neural Network Models for Guo 2018 study - TensorFlow format	almost 6 years ago
User T. Breckon has deposited guo-raindrop-detection-pretrained-model-2018.zip	almost 6 years ago