YOLOv5小目標(biāo)切圖檢測的思路與方法
前言
當(dāng)我們在檢測較大分辨率的圖片時,對小目標(biāo)的檢測效果一直是較差的,所以就有了下面幾種方法:
- 將圖片壓縮成大尺寸進(jìn)行訓(xùn)練( 想法:沒顯存,搞不來)
- 添加小檢測頭(想法:P5模型還有點用,P6模型完全沒用)
- 添加一些檢測模型和玄學(xué)機制(想法:你要是寫論文就去看看知*吧,只需要在最后面加一句:已達(dá)到工業(yè)檢測要求)
- 切圖檢測(想法:比較耗時,過程也比較繁瑣,可以嘗試)
切圖檢測
思路:
- 將原圖切成你想要的數(shù)量
- 將切成的小圖進(jìn)行訓(xùn)練,得到模型
- 將你需要檢測的圖片切成小圖,用模型檢測,并得到每張圖目標(biāo)位置的信息,保存在對應(yīng)圖片的txt文件
- 將所有txt文件融合,得到1個txt文件,并在原圖上顯示
一:切塊
# -*- coding:utf-8 -*- import os import matplotlib.pyplot as plt import cv2 import numpy as np def divide_img(img_path, img_name, save_path): imgg = img_path + img_name img = cv2.imread(imgg) # img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB) h = img.shape[0] w = img.shape[1] n = int(np.floor(h * 1.0 / 1000)) + 1 m = int(np.floor(w * 1.0 / 1000)) + 1 print('h={},w={},n={},m={}'.format(h, w, n, m)) dis_h = int(np.floor(h / n)) dis_w = int(np.floor(w / m)) num = 0 for i in range(n): for j in range(m): num += 1 print('i,j={}{}'.format(i, j)) sub = img[dis_h * i:dis_h * (i + 1), dis_w * j:dis_w * (j + 1), :] cv2.imwrite(save_path + '{}_{}.bmp'.format(name, num), sub) if __name__ == '__main__': img_path = r'G:\1/' save_path = r'G:\3/' img_list = os.listdir(img_path) for name in img_list: divide_img(img_path, name, save_path)
使用模型檢測后得到:
二:融合txt文件
import os from cv2 import cv2 # 保存所有圖片的寬高 # todo: img_info={'name': [w_h, child_w_h, mix_row_w_h, mix_col_w_h]} img_info = {} all_info = {} # 初始化img_info def init(big_images_path, mix_percent, rows, cols): image_names = os.listdir(big_images_path) for img_name in image_names: big_path = big_images_path + '\\' + img_name # print(big_path) img = cv2.imread(big_path) size = img.shape[0:2] w = size[1] h = size[0] child_width = int(w) // cols child_height = int(h) // rows mix_row_width = int(child_width * mix_percent * 2) mix_row_height = child_height mix_col_width = child_width mix_col_height = int(child_height * mix_percent * 2) # 根據(jù)img保存w和h img_info[img_name.split('.')[0]] = [w, h, child_width, child_height, mix_row_width, mix_row_height, mix_col_width, mix_col_height] # 讀取所有檢測出來的 小圖片的label def get_label_info(labels_path, mix_percent, rows, cols): labels = os.listdir(labels_path) for label in labels: # print(label) # todo: type: 0正常, 1row, 2col # 判斷該label屬于哪一張圖片 cur_label_belong = label.split('_')[0] cur_big_width = img_info[cur_label_belong][0] cur_big_height = img_info[cur_label_belong][1] # 融合區(qū)域距離邊界的一小部分寬高 cur_row_width_step = img_info[cur_label_belong][2] * (1 - mix_percent) cur_col_height_step = img_info[cur_label_belong][3] * (1 - mix_percent) # 文件名給予數(shù)據(jù) # child_type = [] # child_num = [] # label內(nèi)容給予數(shù)據(jù) child_class_index = [] child_x = [] child_y = [] child_width = [] child_height = [] type = -1 num = -1 class_index = -1 x = 0.0 y = 0.0 width = 0.0 height = 0.0 # print(f'{label}') # 讀取所有需要的數(shù)據(jù) f = open(labels_path + '\\' + label, 'r') lines = f.read() # print(lines) f.close() contents = lines.split('\n')[:-1] # print(contents) for content in contents: content = content.split(' ') # print(content) class_index = int(content[0]) x = float(content[1]) y = float(content[2]) width = float(content[3]) height = float(content[4]) pass # print(class_index, x, y, width, height) assert class_index != -1 or x != -1.0 or y != -1.0 or width != -1.0 or height != -1.0, \ f'class_index:{class_index}, x:{x}, y:{y}, width:{width}, height:{height}' # 轉(zhuǎn)換成 數(shù)據(jù) 坐標(biāo), 并根據(jù)不同的num進(jìn)行處理 num = label.split('_')[-1].split('.')[0] # 圖片尾號 命名: xxxx_x.jpg xxxx_mix_row_xx.jpg xxxx_mix_col_xx.jpg cur_img_width = 0 cur_img_height = 0 distance_x = 0 distance_y = 0 small_image_width = img_info[cur_label_belong][2] small_image_height = img_info[cur_label_belong][3] if label.find('mix_row') != -1: # type = 1. distance_x = int(num) % (cols-1) distance_y = int(num) // (rows-1) cur_img_width = img_info[cur_label_belong][4] cur_img_height = img_info[cur_label_belong][5] # row x 加上step x = x * cur_img_width + cur_row_width_step + distance_x * small_image_width y = y * cur_img_height + distance_y * cur_img_height elif label.find('mix_col') != -1: # type = 2 distance_x = int(num) % cols distance_y = int(num) // rows cur_img_width = img_info[cur_label_belong][6] cur_img_height = img_info[cur_label_belong][7] # col y 加上step print(f'x:{x}, y:{y}, cur_img_width:{cur_img_width}, cur_img_height:{cur_img_height}') x = x * cur_img_width + distance_x * cur_img_width y = y * cur_img_height + cur_col_height_step + distance_y * small_image_height print(f'x:{x}, y:{y}, height:{cur_col_height_step}') else: # type = 0 distance_x = int(num) % cols distance_y = int(num) // rows cur_img_width = img_info[cur_label_belong][2] cur_img_height = img_info[cur_label_belong][3] # 小圖片內(nèi), 無需加上 step x = x * cur_img_width + distance_x * cur_img_width y = y * cur_img_height + distance_y * cur_img_height assert cur_img_width != 0 or cur_img_height != 0 or distance_x != 0 or distance_y != 0, \ f'cur_img_width:{cur_img_width}, cur_img_height:{cur_img_height}, distance_x:{distance_x}, distance_y:{distance_y}' assert x < cur_big_width and y < cur_big_height, f'{label}, {content}\nw:{cur_big_width}, h:{cur_big_height}, x:{x}, y:{y}' width = width * cur_img_width height = height * cur_img_height assert x != 0.0 or y != 0.0 or width != 0.0 or height != 0.0, f'x:{x}, y:{y}, width:{width}, height:{height}' # child_type.append(type) # child_num.append(num) child_class_index.append(class_index) child_x.append(x) child_y.append(y) child_width.append(width) child_height.append(height) # todo: 所有信息 根據(jù) cur_label_belong 存儲在all_info中 for index, x, y, width, height in zip(child_class_index, child_x, child_y, child_width, child_height): if cur_label_belong not in all_info: all_info[cur_label_belong] = [[index, x, y, width, height]] else: all_info[cur_label_belong].append([index, x, y, width, height]) child_class_index.clear() child_x.clear() child_y.clear() child_width.clear() child_height.clear() # print((all_info['0342'])) # todo: 轉(zhuǎn)成 yolo 格式, 保存 def save_yolo_label(yolo_labels_path): for key in all_info: # img_path = r'G:\Unity\code_project\other_project\data\joint\big_images' + '\\' + key + '.JPG' # img = cv2.imread(img_path) yolo_label_path = yolo_labels_path + '\\' + key + '.txt' cur_big_width = img_info[key][0] cur_big_height = img_info[key][1] content = '' i = 0 for index, x, y, width, height in all_info[key]: # print(all_info[key][i]) x = x / cur_big_width y = y / cur_big_height width = width / cur_big_width height = height / cur_big_height assert x < 1.0 and y < 1.0 and width < 1.0 and height < 1.0, f'{key} {i}\n{all_info[key][i]}\nx:{x}, y:{y}, width:{width}, height:{height}' content += f'{index} {x} {y} {width} {height}\n' i += 1 with open(yolo_label_path, 'w') as f: f.write(content) def joint_main(big_images_path=r'G:\3', labels_path=r'G:\5', yolo_labels_path=r'G:\6', mix_percent=0.2, rows=4, cols=4): print(f'融合圖片, 原圖片路徑:{big_images_path}\n小圖檢測的txt結(jié)果路徑:{labels_path}\n數(shù)據(jù)融合后txt結(jié)果路徑:{yolo_labels_path}') init(big_images_path, mix_percent, rows, cols) get_label_info(labels_path, mix_percent, rows, cols) save_yolo_label(yolo_labels_path) joint_main()
三:原圖顯示
# -*- coding: utf-8 -*- import os from PIL import Image from PIL import ImageDraw, ImageFont from cv2 import cv2 def draw_images(images_dir, txt_dir, box_dir, font_type_path): font = ImageFont.truetype(font_type_path, 50) if not os.path.exists(box_dir): os.makedirs(box_dir) # num = 0 # 設(shè)置顏色 all_colors = ['red', 'green', 'yellow', 'blue', 'pink', 'black', 'skyblue', 'brown', 'orange', 'purple', 'gray', 'lightpink', 'gold', 'brown', 'black'] colors = {} for file in os.listdir(txt_dir): print(file) image = os.path.splitext(file)[0].replace('xml', 'bmp') + '.bmp' # 轉(zhuǎn)換成cv2讀取,防止圖片載入錯誤 img = cv2.imread(images_dir + '/' + image) TURN = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) img = Image.fromarray(TURN) # img.show() if img.mode == "P": img = img.convert('RGB') w, h = img.size tag_path = txt_dir + '/' + file with open(tag_path) as f: for line in f: line_parts = line.split(' ') # 根據(jù)不同的 label 保存顏色 if line_parts[0] not in colors.keys(): colors[line_parts[0]] = all_colors[len(colors.keys())] color = colors[line_parts[0]] draw = ImageDraw.Draw(img) x = (float(line_parts[1]) - 0.5 * float(line_parts[3])) * w y = (float(line_parts[2]) - 0.5 * float(line_parts[4])) * h xx = (float(line_parts[1]) + 0.5 * float(line_parts[3])) * w yy = (float(line_parts[2]) + 0.5 * float(line_parts[4])) * h draw.rectangle([x - 10, y - 10, xx, yy], fill=None, outline=color, width=5) # num += 1 del draw img.save(box_dir + '/' + image) # print(file, num) # print(colors) def draw_main(box_dir=r'G:\5', txt_dir=r'G:\6', image_source_dir=r'G:\3'): font_type_path = 'C:/Windows/Fonts/simsun.ttc' print(f'標(biāo)注框, 數(shù)據(jù)來源: {txt_dir}\n 被標(biāo)注圖片: {image_source_dir}\n 結(jié)果保存路徑: {box_dir}') draw_images(image_source_dir, txt_dir, box_dir, font_type_path) draw_main()
效果對比:(上YOLOv5檢測,下YOLOv5+切圖檢測)
參考:
https://blog.csdn.net/qq_43622870/article/details/124984295
總結(jié)
到此這篇關(guān)于YOLOv5小目標(biāo)切圖檢測的思路與方法的文章就介紹到這了,更多相關(guān)YOLOv5小目標(biāo)切圖檢測內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家!
相關(guān)文章
Python接口自動化之cookie、session應(yīng)用詳解
本文主要介紹cookie、session原理及在自動化過程中如何利用cookie、session保持會話狀態(tài)的應(yīng)用,有需要的朋友可以參考下,希望可以有所幫助2021-08-08python Event事件、進(jìn)程池與線程池、協(xié)程解析
這篇文章主要介紹了python Event事件、進(jìn)程池與線程池、協(xié)程解析,文中通過示例代碼介紹的非常詳細(xì),對大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價值,需要的朋友可以參考下2019-10-10Python統(tǒng)計文本詞匯出現(xiàn)次數(shù)的實例代碼
這篇文章主要介紹了Python統(tǒng)計文本詞匯出現(xiàn)次數(shù),這種問題在統(tǒng)計文本詞匯的次數(shù)時經(jīng)常會遇到,今天給大家分享解決方案,通過實例代碼給大家講解,需要的朋友可以參考下2020-02-02解決Python 使用h5py加載文件,看不到keys()的問題
今天小編就為大家分享一篇解決Python 使用h5py加載文件,看不到keys()的問題,具有很好的參考價值,希望對大家有所幫助。一起跟隨小編過來看看吧2019-02-02