使用ImageAI快速构建常见对象检测应用

OpenCV学堂

发布于 2019-12-09 16:58:40

9700

发布于 2019-12-09 16:58:40

文章被收录于专栏：贾志刚-OpenCV学堂贾志刚-OpenCV学堂

微信公众号：OpenCV学堂 关注获取更多计算机视觉与深度学习知识

ImageAI介绍

纯Python的快速对象检测训练与测试平台，基于tensorflow+opencv构建，支持

RetinaNet
YOLOv3
TinyYOLOv3

在COCO数据集上预训练模型的调用，同时支持自定义对象训练与导出。支持

图像分类
对象检测
视频对象检测与跟踪

安装ImageAI

ImageAI的后台依赖tensorflow框架与keras，所以需要首先安装tensoflow，当前还不支持tensorflow2.0版本

tensorflow 1.4.x以上版本
opencv-python

安装imageai，只需要执行如下命令行即可

pip install imageai

代码演示

1. 图像分类

from imageai.Prediction import ImagePrediction
import os

execution_path = os.getcwd()

prediction = ImagePrediction()
prediction.setModelTypeAsResNet()
prediction.setModelPath(os.path.join(execution_path, "resnet50_weights_tf_dim_ordering_tf_kernels.h5"))
prediction.loadModel()

predictions, probabilities = prediction.predictImage(os.path.join(execution_path, "1.jpg"), result_count=5 )
for eachPrediction, eachProbability in zip(predictions, probabilities):
    print(eachPrediction , " : " , eachProbability)

图像

运行输出:

convertible : 52.459555864334106 sports_car : 37.61284649372101 pickup : 3.1751200556755066 car_wheel : 1.817505806684494 minivan : 1.7487050965428352

2. 对象检测

from imageai.Detection import ObjectDetection
import os

execution_path = os.getcwd()

detector = ObjectDetection()
detector.setModelTypeAsYOLOv3()
detector.setModelPath( os.path.join(execution_path , "yolo.h5"))
detector.loadModel()
detections = detector.detectObjectsFromImage(input_image=os.path.join(execution_path , "image2.jpg"), output_image_path=os.path.join(execution_path , "image2new.jpg"), minimum_percentage_probability=30)

for eachObject in detections:
    print(eachObject["name"] , " : ", eachObject["percentage_probability"], " : ", eachObject["box_points"] )
    print("--------------------------------")

运行输出: