圖像識別實驗過程（一）背景和介紹

研究背景

英文原文：

Nearly half of the world depends on seafood for their main source of protein. In the Western and Central Pacific, where 60% of the world’s tuna is caught, illegal, unreported, and unregulated fishing practices are threatening marine ecosystems, global seafood supplies and local livelihoods. The Nature Conservancy is working with local, regional and global partners to preserve this fishery for the future.

Currently, the Conservancy is looking to the future by using cameras to dramatically scale the monitoring of fishing activities to fill critical science and compliance monitoring data gaps. Although these electronic monitoring systems work well and are ready for wider deployment, the amount of raw data produced is cumbersome and expensive to process manually.

The Conservancy is inviting the Kaggle community to develop algorithms to automatically detect and classify species of tunas, sharks and more that fishing boats catch, which will accelerate the video review process. Faster review and more reliable data will enable countries to reallocate human capital to management and enforcement activities which will have a positive impact on conservation and our planet.

Machine learning has the ability to transform what we know about our oceans and how we manage them. You can be part of the solution.

中文翻譯：

 

傳統圖像識別與目標檢測的研究現狀：

基於卷積神經網絡的圖像識別與目標檢測的研究現狀：

 

本文采用的技術框架：

基於caffe的Faster-RCNN

 

數據集介紹

本文中的數據集是世界天然保護協會（The Nature Conservancy）收集的漁船監控畫面，已經人工的根據圖片中魚的種類進行分類。以下圖：

 

 介紹圖像包括哪些類的魚

圖像重命名

Faster R-CNN提供訓練數據集格式有PASCAL VOC和Microsoft COCO。本文選擇將數據集製做成標準的PASCAL VOC 2007格式來進行訓練。

雖然圖片名稱對訓練沒有影響，可是圖片數量不少時好的命名可讓數據不那麼混亂。按照VOC2007格式，如「100001.jpg」,對數據集圖片進行重名。

python 重命名圖片代碼：

#coding=utf-8  
  
import os

dictOfFish={
    'ALB':'100000',
    'BET':'200000',
    'DOL':'300000',
    'LAG':'400000',
    'NoF':'500000',
    'OTHER':'600000',
    'SHARK':'700000',
    'YFT':'800000'
}
for key in dictOfFish:
    a=os.listdir("./origin/"+key) 
    count=1
    for x in a:
        oldname="./origin/"+key+"/"+x
        newname="./origin/"+key+"/"+str(int(dictOfFish[key])+count)+".jpg"
        os.rename(oldname,newname)
        count+=1