Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Enhancement and Detection of Objects in Underwater Images Using Image Super-Resolution and Effective Object Detection Model


Affiliations
1 Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India
 

It is imperative to build an automatic underwater object recognition system in place to reduce the costs of underwater inspections as well as the associated risks. An effective method of detecting underwater objects from underwater images of aquatic after enhancing them using the Image Super-resolution technique is proposed in this study. The proposed approach comprises of two major sections, Underwater Image Enhancement, and Object detection. To enhance the underwater images, a lightweight Reduced Cascading Residual Network (RCARN) is proposed that imposes the Image Super-resolution technique. Later, the enhanced images generated by the RCARN model are supplied for the object detection process, where a significant object detection model, YOLOv3 is employed in this study. To improve its performance, this YOLOv3 is trained on one of the largest datasets, the COCO data, followed by being fine-tuned using enhanced Underwater images. The dataset utilized in this work contains 6 classes of underwater objects namely dolphin, jellyfish, octopus, seahorse, starfish, and turtle. All these images are actual real field images collected from various sources. With this proposed approach, a better overall ACS and mAP of 95.44% and 75.33% are achieved here, which are improved by ∼8.75% and ∼15%, respectively when compared to actual collected low-resolution images.

Keywords

CNN, Computer Vision, Deep Learning, Image Enhancement, Object Detection, Underwater Objects.
User
Notifications
Font Size

  • Yang M, Hu J, Li C, Rohde G, Du Y & Hu K, An in-depth survey of underwater image enhancement and restoration, IEEE Access, 7 (2019) 123638–123657.

  • Er M J & Jie C, Research challenges, recent advances and benchmark datasets in deep-learning-based underwater marine object detection: A review (2022), TechRxiv. Preprint, Availble: https://doi.org/10.36227/techrxiv.19350389.v2.

  • Jagatheswari S & Viswanathan R, Image magnification and demagnification using fuzzy lattice morphological transformation, Asian J Res Soc Sci Humanit, 6(8) (2016) 614–628.

  • Huang G, Liu Z, Van Der Maaten L & Weinberger K Q, Densely connected convolutional networks, Proc of the IEEE Conf On Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, 4700–4708.

  • Liu R, Jiang Z, Yang S & Fan X, Twin adversarial contrastive learning for underwater image enhancement and beyond, IEEE Trans Image Process, 31 (2022) 4922–4936.

  • Guo Y, Li H & Zhuang P, Underwater image enhancement using a multiscale dense generative adversarial network, IEEE J Ocean Eng, 45(3) (2019) 862–870.

  • Yeh C H, Huang C H & Kang LW, Multi-scale deep residual learning-based single image haze removal via image decomposition, IEEE Trans Image Process, 29 (2019) 3153–3167.

  • Huo G, Wu Z & Li J, Underwater object classification in side scan sonar images using deep transfer learning and semisynthetic training data, IEEE Access, 8 (2020) 47407–47418.

  • Fang F, Li J & Zeng T, Soft-edge assisted network for single image super-resolution, IEEE Trans Image Process, 29 (2020) 4656–4668.

  • Deepika P & Pabitha P, Evaluation of convolutional neural network architecture for feasibility analysis on fetal abdomen and brain images, J Med Imaging Health Inform, 11(10) (2021) 2573–2583.

  • Chen K H, Shou T D, Li J K H, & Tsai C M, Vehicles detection on expressway via deep learning: Single shot multibox object detector, in IEEE Int Conf Machine Learn Cybernet (ICMLC), 2 (2018) 467–473.

  • Swarna Priya R M, Gunavathi C & Aarthy S L, Estimating the distance of a human from an object using 3d image reconstruction, in Informat Syst Design Intel Appl, Springer, Singapore, 2019, 235–243.

  • HS R K & Bhat D, A novel method to recognize object in images using convolution neural networks, in IEEE Int Conf Intel Comput Control Syst (ICCS) 2019, 425–430.

  • ZhaoZ Q, Zheng P, Xu S T, and Wu X, Object detection with deep learning: A review, IEEE Trans Neural Netw Learn Syst, 30(11) (2019) 3212–3232.

  • Emera I & Sandor M, Creation of farmers' awareness on fall armyworms pest detection at early stage in rwanda using deep learning, in IEEE 8th Int Congress Adv Appl Informat (IIAI-AAI) (Toyama, Japan) 2019, 538–541.

  • Yao G, Lei T & Zhong J, A review of convolutional-neural-network-based action recognition, Pattern Recognit Lett, 118 (2019) 14–22.

  • Huang J, Qin F, Zheng X, Cheng Z, Yuan Z, Zhang W & Huang Q, Improving multi-label classification with missing labels by learning label-specific features, Inf Sci, 492 (2019) 124–146.

  • Jalal A, Salman A, Mian A, Shortis M & hafait F, Fish detection and species classification in underwater environments using deep learning with temporal information, Ecol Inform, 57 (2020) 101088.

  • Shen, Z Y, Han SY, Fu LC, Hsiao P Y, Lau Y C & Chang S J, Deep convolution neural network with scene-centric and object-centric information for object detection, Image Vis Comput, 85 (2019) 14–25.

  • Malhotra P and Garg E, Object Detection Techniques: A Comparison, in IEEE 7th Int Conf Smart Structures Syst (ICSSS) (Chennai, India) 2020, 1–4.

  • Fang W, Wang L & Ren P, Tinier-YOLO: A real-time object detection method for constrained environments, IEEE Access, 8 (2019) 1935–1944.

  • Garcia-Dominguez M, Dominguez C, Heras J, Mata E & Pascual V, FrImCla: a framework for image classification using traditional and transfer learning techniques, IEEE Access, 8 (2020) 53443–53455.

  • Li R, Wang R, Zhang J, Xie C, Liu L, Wang F, Chen H, Chen T, Hu H, Jia X & Hu M. An effective data augmentation strategy for CNN-based pest localization and recognition in the field. IEEE Access, 7 (2019) 160274–160283.

  • Das S, Sharma R, Gourisaria M K, Rautaray S S & Pandey M A, Model for probabilistic prediction of paddy crop disease using convolutional neural network, in Intelligent and Cloud Computing edited by D Mishra, R Buyya, P Mohapatra, S P (Series: Smart Innovation, Systems and Technologies, Springer, Singapore) 2021, 194.

  • Hastie T, Tibshirani R & Friedman J, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Springer Science & Business Media) 2009, 219–223.

  • Li C, Guo C, Ren W, Cong R, Hou J, Kwong S & Tao D, An underwater image enhancement benchmark dataset and beyond, IEEE IEEE Trans Image Process, 29 (2019) 4376–4389.

  • Ronneberger O, Fischer P & Brox T, U-Net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention – MICCAI, Lecture Notes in Computer Science edited by N Navab, J Hornegger, W Wells & A Frangi (Springer, Cham) (9351) 2015, 234-241.

  • Ahn N, Kang B & Sohn K A, Fast, accurate, and lightweight super-resolution with cascading residual network, Proc European Conf Comput Vis (ECCV), 2018, 252–268.

  • Li W, Liu K, Yan L, Cheng F, Lv Y & Zhang L, FRD-CNN: Object detection based on small-scale convolutional neural networks and feature reuse, Sci Rep, 9(1) (2019) 1–12.

  • Lohia A, Kadam K D, Joshi R R & Bongale A M, Bibliometric analysis of one-stage and two-stage object detection, Libr Philos Pract, 4910, (2021) 1–32.

  • Jiang L & Li X, An efficient and accurate object detection algorithm and its application, in IEEE 5th Informat Technol Mechatron Eng Conf (ITOEC) (Chongqing, China) 2020, 656–661.

  • Yulin T, Jin S, Bian, G & Zhang Y, Shipwreck target recognition in side-scan sonar images by improved YOLOv3 model based on transfer learning, IEEE Access, 8 (2020) 173450–173460.

  • Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M & Berg A C, Imagenet large scale visual recognition challenge, Int J Comput Vis, 115(3) (2015) 211–252.

  • Everingham M, Van Gool L, Williams C K, Winn J & Zisserman A, The pascal visual object classes (voc) challenge, Int J Comput Vis, 88(2) (2010) 303–338.

  • Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P & Zitnick C L, Microsoft coco: Common objects in context, in European conference on computer vision, (Springer, Cham) 2014, 740–755.

  • Sahu B & Mishra D Performance of feed forward neural network for a Novel Feature Selection Approach, Int J Comput Sci Inf Tec, 2(4) (2011) 1414–1419.


Abstract Views: 89

PDF Views: 59




  • Enhancement and Detection of Objects in Underwater Images Using Image Super-Resolution and Effective Object Detection Model

Abstract Views: 89  |  PDF Views: 59

Authors

R. Arumuga Arun
Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India
S. Umamaheswari
Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India
B. Nafesha
Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India
V. Makesh Arvindan
Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India
Vengam Udaya Kumar
Anna University-MIT Campus, Chennai 600 044, Tamil Nadu, India

Abstract


It is imperative to build an automatic underwater object recognition system in place to reduce the costs of underwater inspections as well as the associated risks. An effective method of detecting underwater objects from underwater images of aquatic after enhancing them using the Image Super-resolution technique is proposed in this study. The proposed approach comprises of two major sections, Underwater Image Enhancement, and Object detection. To enhance the underwater images, a lightweight Reduced Cascading Residual Network (RCARN) is proposed that imposes the Image Super-resolution technique. Later, the enhanced images generated by the RCARN model are supplied for the object detection process, where a significant object detection model, YOLOv3 is employed in this study. To improve its performance, this YOLOv3 is trained on one of the largest datasets, the COCO data, followed by being fine-tuned using enhanced Underwater images. The dataset utilized in this work contains 6 classes of underwater objects namely dolphin, jellyfish, octopus, seahorse, starfish, and turtle. All these images are actual real field images collected from various sources. With this proposed approach, a better overall ACS and mAP of 95.44% and 75.33% are achieved here, which are improved by ∼8.75% and ∼15%, respectively when compared to actual collected low-resolution images.

Keywords


CNN, Computer Vision, Deep Learning, Image Enhancement, Object Detection, Underwater Objects.

References