The Appropriate Image Enhancement Method for Underwater Object Detection

Underwater datasets usually have blurred objects, low contrast, and color distortion, which seriously restrict the performance of the target detector on it. It is very important to use data enhancement methods to improve the original dataset. In this paper 7 target detection models are trained on Trash-ICRA19 underwater datasets, namely Faster-RCNN, SSD, YOLO V1-V5. Through comparison, it is found that YOLOV5 has the best performance with 79.7 AP and 138.89 FPS. Then three methods about data enhancement are adopted to improve the UDD underwater datasets, namely Underwater Dark Channel Prior(UDCP), Contrast-Limited Adaptive Histogram Equalization(CLAHE), and Relative Global Histogram Stretching(RGHS). Comprehensive comparison found that CLAHE and RGHS can have a better recovery effect. Finally, the YOLOV5 model is re-trained on the enhanced UDD underwater dataset. Compared with visual results, these enhancement methods can make the detector better distinguish between objects and backgrounds.

[1]  Zeming Li,et al.  YOLOX: Exceeding YOLO Series in 2021 , 2021, ArXiv.

[2]  Long Chen,et al.  Underwater object detection using Invert Multi-Class Adaboost with deep learning , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[3]  Hong-Yuan Mark Liao,et al.  YOLOv4: Optimal Speed and Accuracy of Object Detection , 2020, ArXiv.

[4]  Li Wen,et al.  Reveal of Domain Effect: How Visual Restoration Contributes to Object Detection in Aquatic Scenes , 2020, ArXiv.

[5]  Xing Liu,et al.  UDD: An Underwater Open-sea Farm Object Detection Dataset for Underwater Robot Picking , 2020, ArXiv.

[6]  Zhaohui Zheng,et al.  Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression , 2019, AAAI.

[7]  Haitao Zhu,et al.  UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing , 2019, ArXiv.

[8]  S. Kwong,et al.  An Underwater Image Enhancement Benchmark Dataset and Beyond , 2019, IEEE Transactions on Image Processing.

[9]  Junaed Sattar,et al.  Toward a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection , 2018, IEEE Robotics and Automation Letters.

[10]  Joseph Redmon,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[11]  Shu Liu,et al.  Path Aggregation Network for Instance Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Wei Song,et al.  Shallow-Water Image Enhancement Using Relative Global Histogram Stretching Based on Adaptive Parameter Acquisition , 2018, MMM.

[13]  Jie Li,et al.  WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images , 2017, IEEE Robotics and Automation Letters.

[14]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Serge J. Belongie,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[18]  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.

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

[20]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Aaron C. Courville,et al.  Generative adversarial networks , 2014, Commun. ACM.

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

[23]  Ying-Ching Chen,et al.  Underwater Image Enhancement by Wavelength Compensation and Dehazing , 2012, IEEE Transactions on Image Processing.

[24]  A. Frid,et al.  Predicting ecological consequences of marine top predator declines. , 2008, Trends in ecology & evolution.

[25]  M. Ali Akber Dewan,et al.  A Dynamic Histogram Equalization for Image Contrast Enhancement , 2007, IEEE Transactions on Consumer Electronics.

[26]  Mohinder Malhotra.  Single Image Haze Removal Using Dark Channel Prior , 2016 .

[27]  Andrew Rova,et al.  One Fish, Two Fish, Butterfish, Trumpeter: Recognizing Fish in Underwater Video , 2007, MVA.