How AI used to detect Parking Space

How to AI is used in Detecting Parking space

During the recent “Sembang AIoT Episode 34” on January 26, organized by AIoTmission and Axiomtek, we explored the expanded applications of AIoT in the realm of Smart Parking.

The session commenced with an overview of the AI4S program and starter kit, showcasing its utilization in one of the Digital Transformation and Smart Manufacturing initiatives hosted by MPC, Intel, and MIDA.

A comprehensive explanation of the Axiomtek AI Suite (AIS) followed, delving into its functionalities and objectives in generating AI models deployable in production processes. The emphasis was on reducing manpower in specific processes and enhancing overall operational efficiency.


Productive through digitalization
Axiomtek AIS

Axiomtek Industrial AI suite was used as a teaching hands on kit in the program. The AI4S program (also known as Artificial
Intelligence for SMEs), is an Artificial
Intelligence (AI) based machine vision system. It is a three-way partnership, among Malaysia Productivity Corporation (MPC), Malaysian Investment Development Authority (MIDA) and Intel Malaysia. This booklet is a compilation of end-users’ Proof-of-Concepts (PoCs) projects as a result of the experiential training provided to the participants

The Axiomtek AI starter kit is a completed starter kit featuring a high-performance
Intel® Core™-based AI edge platform on standard Tower based industrial PC system  with high-computing
GPU/VPU support, a high-resolution camera, and built-in Axiomtek AI suite (AIS)
based on Tensorflow Framework, Intel® Edge Software Hub for Industrial and
Intel® OpenVINO™. This application-ready package enables users or manufacturers to
ease the development of vision applications within automation. The hardware
platform, IPC-AIS-524, is a 7 slots industrial system with LGA1151 socket
9th gen Intel® Core™ i7  processor. It comes with front-access I/O and adequate PCIe and PCI Slots. The Axiomtek AI Suite (AIS) is based on
Intel® Edge Software Hub for Industrial to implement from deep-learning training
to inference. It comes with web apps design and intuitive user interfaces,
helping the users deploy AI without coding.

Smart parking with Vision AI - The parking Space Detection

Demonstration of smart parking with vision AI

There are several models suitable for Parking space detection:- 

Convolutional Neural Networks (CNNs): CNNs are particularly effective for image recognition tasks, making them suitable for parking space detection in smart parking systems. They can analyze images or video feeds from cameras placed in parking areas to identify and classify available and occupied parking spaces.

YOLO (You Only Look Once): YOLO is a real-time object detection system that could be employed for smart parking applications. YOLO can quickly process images and accurately detect and locate multiple objects, including vehicles in parking spaces, in a single pass.

Faster R-CNN (Region-based Convolutional Neural Network): Faster R-CNN is another popular choice for object detection tasks. It’s known for its accuracy and ability to precisely locate objects within an image. This model could be adapted for identifying and monitoring parking spaces in real-time.

Benefits of Smart Parking using AI:

Optimized Parking Management: AI-powered smart parking solutions enhance parking management by providing real-time information about parking space availability. This helps drivers find parking spots quickly, reducing traffic congestion and fuel consumption.

Reduced Traffic and Emissions: Efficient parking space detection contributes to the overall reduction of traffic congestion as drivers spend less time searching for parking. This, in turn, leads to a decrease in vehicle emissions, promoting a more environmentally friendly and sustainable urban environment.

Improved City Planning: The data collected from smart parking systems can be analyzed to gain insights into parking patterns, peak usage times, and demand trends. City planners can use this information to make informed decisions about urban infrastructure, optimize parking layouts, and create more efficient transportation systems within smart cities.

A Live demo on the AI parking Space detection was performed with one of the AIoT appliances with deep learning AI model detecting the parking space with vehicle counting capability. 

To watch us in the live session:-