Abstract
Machine learning algorithms based on convolutional neural networks (CNNs) have recently been explored in a myriad of object detection applications. Nonetheless, many devices with limited computation resources and strict power consumption constraints are not suitable to run such algorithms designed for high-performance computers. Hence, a novel smartphone-based architecture intended for portable and constrained systems is designed and implemented to run CNN-based object recognition in real time and with high efficiency. The system is designed and optimised by leveraging the integration of the best of its kind from the state-of-the-art machine learning platforms including OpenCV, TensorFlow Lite, and Qualcomm Snapdragon informed by empirical testing and evaluation of each candidate framework in a comparable scenario with a high demanding neural network. The final system has been prototyped combining the strengths from these frameworks and led to a new machine learning-based object recognition execution environment embedded in a smartphone with advantageous performance compared with the previous frameworks.
Highlights
Artificial Intelligence (AI) has gained momentum in recent years in light of the huge potential in a wide range of applications, and there is an emerging trend to run machine learning in lightweight, embedded systems, such as smartphones for high mobility, low cost, rapid deployment and other benefits
The machine learning algorithm deployed for testing is YOLOv3
The results were obtained from the thread related to object recognition process which is specialised for recognition of small objects
Summary
Artificial Intelligence (AI) has gained momentum in recent years in light of the huge potential in a wide range of applications, and there is an emerging trend to run machine learning in lightweight, embedded systems, such as smartphones for high mobility, low cost, rapid deployment and other benefits. The computational power of smartphones has drastically increased in the past few years and they are comparable with desktop computers available some years ago. Running such CNN models on mobile devices is still challenging owing to the limited computing power and energy available [12]. CNN models run on high performance computing servers due to hardware requirements and are not available to operate on smartphones To overcome these issues, there is a vital need for a machine learning framework suitable for smartphones to perform computing-intensive computer vision tasks, such as object recognition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
