• Corpus ID: 2762417

Marine Animal Detection and Recognition with Advanced Deep Learning Models

  title={Marine Animal Detection and Recognition with Advanced Deep Learning Models},
  author={Peiqin Zhuang and Linjie Xing and Yanlin Liu and Sheng Guo and Yu Qiao},
  booktitle={Conference and Labs of the Evaluation Forum},
This paper summarizes SIATMMLAB’s contributions in SEACLEF2017 task [1. [] Key Method In Automatic Fish Identification and Species Recognition task, we exploited different frameworks to detect the proposal boxes of foreground fish, then fine-tuned a pre-trained neural network to classify the fish. In Automatic Frame-level Salmon Identification task, we utilized the BN-Inception [2] network to identify whether a video frame contains salmons or not.

Figures and Tables from this paper

A Novel Detection Refinement Technique for Accurate Identification of Nephrops norvegicus Burrows in Underwater Imagery

From experiment results, it is demonstrated that the proposed framework effectively suppresses false positives and recovers missed detections obtained from generic detectors, and the mean average precision (mAP) gained a 10% increase with the proposed refinement technique.

Class-Aware Fish Species Recognition Using Deep Learning for an Imbalanced Dataset

The fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network, and a class-aware loss function is proposed to solve the class imbalance problem of the dataset.


A scheme for segmenting fish image and measuring fish morphological features indicators based on R-CNN is proposed, which focuses on fish recognition for investigating fish species in a natural lake to help protect the original environment.

Multi-stream fish detection in unconstrained underwater videos by the fusion of two convolutional neural network detectors

This paper proposes two new fusion approaches that exploit two convolutional neural network streams to merge both appearance and motion information for automatic fish detection that significantly improve the fish detection performances on the LifeClef 2015 Fish benchmark dataset.

The Impact of Data Augmentations on Deep Learning-Based Marine Object Classification in Benthic Image Transects

The effect of data augmentation in the context of taxonomic classification in underwater, i.e., benthic images, is investigated and it is concluded that in the case of small marine image datasets, background knowledge, and heuristics should sometimes be applied to design an effective data Augmentation method.

Deep Learning-based Image Data Processing and Archival System for Object Detection of Endangered Species

This study builds a system with a deep learning module that collects the image data of endangered animals, processes the data, and saves the data automatically, and addresses two problems faced in previous studies.

FFDet: a Fully Convolutional Network for Coral Reef Fish Detection by Layer Fusion

Experimental results show that FFDet not only outperforms SSD in performance by sacrificing only a little efficiency, but also better than another two popular end-to-end deep models in both detection performance and speed, especially on detecting large-sized fishes.

MulTNet: A Multi-Scale Transformer Network for Marine Image Segmentation toward Fishing

A novel multi-scale transformer network (MulTNet) is proposed for improving the segmentation accuracy of marine animals, and it simultaneously possesses the merits of a convolutional neural network (CNN) and a transformer.

Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance

An automated image classification method for 11 endangered parrot species included in CITES to classify 11 endangered species of parrots using convolutional neural networks to protect endangered species.



SeaCLEF 2016: Object Proposal Classification for Fish Detection in Underwater Videos

This working note describes the results of CVG Jena Fulda team for the fish recognition task in SeaCLEF 2016 and shows that classification of background subtraction proposals works much better for fish detection thanbackground subtraction on its own.

Fish Identification in Underwater Video with Deep Convolutional Neural Network: SNUMedinfo at LifeCLEF Fish task 2015

This paper describes the participation at the LifeCLEF Fish task 2015, where foreground detection method with selective search is applied and deep convolutional neural network is used to classify fish species per win- dow.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs

A multi-resolution CNN architecture that captures visual content and structure at multiple levels is proposed and two knowledge guided disambiguation techniques to deal with the problem of label ambiguity are designed.

Locally Supervised Deep Hybrid Model for Scene Recognition

This paper proposes a novel locally supervised deep hybrid model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition, and proposes an efficient Fisher Convolutional vector (FCV) that successfully rescues the orderless mid-level semantic information of scene image.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

LifeCLEF 2017 Lab Overview: Multimedia Species Identification Challenges

The LifeCLEF lab proposes to evaluate challenges around 3 tasks related to multimedia information retrieval and fine-grained classification problems in 3 domains based on large volumes of real-world data.

SSD: Single Shot MultiBox Detector

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

ParseNet: Looking Wider to See Better

This work presents a technique for adding global context to deep convolutional networks for semantic segmentation, and achieves state-of-the-art performance on SiftFlow and PASCAL-Context with small additional computational cost over baselines.