Object Detection in Rainy Condition from Video Using YOLO Based Deep Learning Model

Video surveillance is one of the primary and practical actions to prevent criminal and terrorist attacks. Nowadays all public areas are under video surveillance. Most of the surveillance cameras are installed in open spaces. However, the video data captured by the surveillance camera can be affected by the weather condition. In this paper, we are concentrating on the video data captured by surveillance cameras in rainy situation. We have proposed a deep learning-based method to detect object in rainy situations from videos. However, object detection in deep learning is the ubiquitous research topic in computer vision and analysis. Much work has been done in that area. However, deep learning-based object detection in rainy condition remains untouched. We have applied our proposed method for both daytime and nighttime. The method produces excellent results in all conditions.

[1]  Haiying Xia,et al.  Single Image Rain Removal via a Simplified Residual Dense Network , 2018, IEEE Access.

[2]  Song Wang,et al.  Pedestrian Detection Based on YOLO Network Model , 2018, 2018 IEEE International Conference on Mechatronics and Automation (ICMA).

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Xu Wang,et al.  Pedestrian Detection for Transformer Substation Based on Gaussian Mixture Model and YOLO , 2016, 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC).

[5]  Michael S. Langer,et al.  A Spectral-particle hybrid method for rendering falling snow , 2004, Rendering Techniques.

[6]  Shree K. Nayar,et al.  Vision and Rain , 2007, International Journal of Computer Vision.

[7]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Sachin Sakhare,et al.  Image processing techniques for object tracking in video surveillance- A survey , 2015, 2015 International Conference on Pervasive Computing (ICPC).

[9]  Min-Te Sun,et al.  A YOLO-Based Traffic Counting System , 2018, 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI).

[10]  Qinghua Hu,et al.  Progressive Image Deraining Networks: A Better and Simpler Baseline , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[12]  Chuan-Kai Yang,et al.  Cat’s Nose Recognition Using You Only Look Once (Yolo) and Scale-Invariant Feature Transform (SIFT) , 2018, 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).

[13]  José María Martínez Sanchez,et al.  Abandoned Object Detection in Video-Surveillance: Survey and Comparison , 2018, Sensors.

[14]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[16]  Karen Andsager,et al.  Laboratory Measurements of Axis Ratios for Large Raindrops , 1999 .

[17]  Wang Yang,et al.  Real-time face detection based on YOLO , 2018, 2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII).

[18]  Wei Fang,et al.  A novel YOLO-Based real-time people counting approach , 2017, 2017 International Smart Cities Conference (ISC2).

[19]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[20]  Vishal M. Patel,et al.  Image De-Raining Using a Conditional Generative Adversarial Network , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[21]  Niniane Wang,et al.  Rendering falling rain and snow , 2004, SIGGRAPH '04.

[22]  Xinghao Ding,et al.  Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal , 2016, IEEE Transactions on Image Processing.