ตรวจจับป้ายทะเบียนรถ Car License Plate Recognition ด้วย NVIDIA DeepStream SDK - test1
ตรวจจับป้ายทะเบียนรถ Car License Plate Recognition
ด้วย Deep Stream SDK บน NVIDIA Jetson
DeepStream เป็น SDK สำหรับทำ AI Video Analytics
• Jetpack SDK 4.4.1
• DeepStream SDK 5.0
• Python 3.6.9
Machine Learning. ใช้ 3 Models
1.TrafficCamNet Model ( 4 classes Car, Persons, Road signs and Bicycles. )
2.LPD Model ( car license plate detection )
3.LPR Model ( car license plate recognization ) เป็นป้ายทะเบียน US.
Python Source Code
https://github.com/amphancm/deepstrea...
มาเรียนรู้กันได้ใน...
คอร์สอบรม Computer Vision, Machine Learning, AI on NVIDIA Jetson
รายละเอียด
https://goo.gl/forms/gihWTQZgrtRgeFuw2
สอบถาม :
อดุลย์ นันทะแก้ว 081-6452400
LINE : adunnan
FaceBook : / adun.nantakaew
Youtube Thai : / @softpowergroupnetthailand
Youtube EN : / @androidcontrol
Web Blog : http://raspberrypi4u.blogspot.com/
Web Blog : http://microcontrollerkits.blogspot.com/
License Plate Detection (LPDNet) Model
Model Overview
The models described in this card detect one or more license plate objects from a car image and return a box around each object, as well as an lpd label for each object. Two kinds of pretrained LPD models are delivered --- one is trained on a NVIDIA-owned US license plate dataset and another is trained on a public Chinese City Parking dataset(CCPD).
Model Architecture
These models are based on NVIDIA DetectNet_v2 detector with ResNet18 as feature extractor. This architecture, also known as GridBox object detection, uses bounding-box regression on a uniform grid on the input image. Gridbox system divides an input image into a grid which predicts four normalized bounding-box parameters (xc, yc, w, h) and confidence value per output class.
The raw normalized bounding-box and confidence detections needs to be post-processed by a clustering algorithm such as DBSCAN or NMS to produce final bounding-box coordinates and category labels.
License Plate Recognition (LPRNet) Model
Model Overview
The model described in this card is license plate recognition network, which aims to recognize characters in license plates from cropped RGB license plate images. Two pretrained LPRNet models are delivered --- one is trained on a NVIDIA-owned US license plate dataset and another is trained on a Chinese license plate dataset.
Model Architecture
This model is a sequence classification model with a ResNet backbone. And it will take the image as network input and produce sequence output.