Image Dehazing for Object Recognition using Faster RCNN

Object recognition in hazy conditions is quite difficult due to illumination variance. The challenge arises in finding out features from such images. Herein, we have proposed the method to deal with such images. The input image needs to be dehazed before applying the recognition algorithms. On the other hand, dehazing a non-hazy image makes it dark resulting in loss of features. Hence, a decision is to be made whether or not the image should be dehazed before recognition. Also, for a very dense haze, even dehazing doesn’t help in object recognition. In order to tackle this issue, this paper presents a novel method to quantitatively estimate the amount of haze in the image – also termed as haze degree – using dark channel prior of the input images. We compared our values with the existing method using FRIDA dataset. The estimated haze degree is used to decide whether input image need to be dehazed or not. We use DehazeNet and Faster RCNN for dehazing and recognition, respectively. We test our method on real time hazy images to set a threshold on haze degree to classify the image as light, moderate or densely hazed. We used the Static Scenes dataset from Color Hazy Images for Comparison (CHIC) database to obtain the threshold values.

[1]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[2]  Jean-Baptiste Thomas,et al.  A Color Image Database for Haze Model and Dehazing Methods Evaluation , 2016, ICISP.

[3]  Younggun Cho,et al.  Estimation of ambient light and transmission map with common convolutional architecture , 2016, OCEANS 2016 MTS/IEEE Monterey.

[4]  Uthai Phommasak,et al.  Detecting Foggy Images and Estimating the Haze Degree Factor , 2014 .

[5]  Xiaoou Tang,et al.  Single Image Haze Removal Using Dark Channel Prior , 2011 .

[6]  Jian-Jiun Ding,et al.  Haze detection and haze degree estimation using dark channels and contrast histograms , 2015, 2015 10th International Conference on Information, Communications and Signal Processing (ICICS).

[7]  Xiaorun Li,et al.  Fast image dehazing using guided filter , 2015, 2015 IEEE 16th International Conference on Communication Technology (ICCT).

[8]  Raanan Fattal,et al.  Single image dehazing , 2008, ACM Trans. Graph..

[9]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[10]  Nishchal K. Verma,et al.  Future image frame generation using Artificial Neural Network with selected features , 2012, 2012 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

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

[14]  Guosheng Lin,et al.  Deep convolutional neural fields for depth estimation from a single image , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  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.

[16]  Nishchal K. Verma,et al.  Object identification for inventory management using convolutional neural network , 2016, 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.