This is a pedestrian detection interface based on Python + flask framework. Pedestrian object detection model is a yolov3 detection model pre-trained on COCO dataset. This is the background function implementation code for single picture detection supporting front-end custom Web.
python 3.6
tensorflow 1.4.0
keras 2.3.1
matplotlib 3.1.1
opencv-python 4.1.1.26
Pillow 6.2.0
flask 1.1.1
requests 2.22.0
gevent 1.4.0
PedestrianDetection
|__ PedestrianDetectionFunc
| |__ Data
| | |__ coco_classes.txt
| | |__ yolo_anchors.txt
| | |__ model.h5
| |__ Model
| | |__ model.py
| |__ Utils
| | |__ utils.py
| |__ PedestrianDetectionClass.py
| |__ PedestrianDetectionModel.py
|__ PedestrianDetectionMain.py
|__ TestCode.py
|__ VerifyResult.py
|__ Person.jpg
cd PedestrianDetection
python PedestrianDetectionMain.pyPedestrianDetection Net Ready
* Serving Flask app "PedestrianDetectionMain" (lazy loading)
* Environment: production
WARNING: This is a development server. Do not use it in a production deployment.
Use a production WSGI server instead.
* Debug mode: off
* Running on http://localhost:8086/ (Press CTRL+C to quit)
python TestCode.py{"result": "success", "box": ["class_name score left top right bottom"], "time": "xxxms"}
{'result': 'error', 'msg': 'System is busy,try later', 'errorcode': '10004'}
python VerifyResult.py{"result": "success", "box": ["person 1.00 40 51 203 369"], "time": "116.90ms"}
