Evaluation Method of Deep Learning-Based Embedded Systems for Traffic Sign Detection

Abstract

Traffic Sign Detection (TSD) is a complex and fundamental task for developing autonomous vehicles; it is one of the most critical visual perception problems since failing in this task may cause accidents. This task is fundamental in decision-making and involves different internal conditions such as the internal processing system or external conditions such as weather, illumination, and complex backgrounds. At present, several works are focused on the development of algorithms based on deep learning; however, there is no information on a methodology based on descriptive statistical analysis with results from a solid experimental framework, which helps to make decisions to choose the appropriate algorithms and hardware. This work intends to cover that gap. We have implemented some combinations of deep learning models (MobileNet v1 and ResNet50 v1) in a combination of the Single Shot Multibox Detector (SSD) algorithm and the Feature Pyramid Network (FPN) component for TSD in a standardized dataset (LISA), and we have tested it on different hardware architectures (CPU, GPU, TPU, and Embedded System). We propose a methodology and the evaluation method to measure two types of performance. The results show that the use of TPU allows achieving a processing training time 16.3 times faster than GPU and better results in terms of precision detection for one combination.

Performance Evaluation of Deep Learning Algorithm Using High-End Media Processing Board in Real-Time Environment

“…The Xavier AGX hardware accelerator selection depends on the data characteristics such as size, quantity, and application. This information provides assistance in selecting the right combination based on the data Properties in [40]. for the training set that will negatively impact the samples for each class.…”

Image recoloring using generative adversarial neural networks

“…This is because its main tool, convolution, applies a mask to an image, where each output pixel is a linear combination of the input defined by the kernel size, which serves as a layer model to extract features from the image by applying different filters or affine transformations to the image. 7 Convolution takes advantage of three important ideas that can help improve a machine learning system: sparse interactions, parameter sharing, and equivariant representations.…”

Malware classification through image processing with a convolutional neural network

“…The weights of the network are represented via kernels, these are subsets of neurons which can be seen as a matrix that slides across the image, which can extract features from the input image, the kernel itself overlaps a square amount of neurons, each pixel is multiplied by the value of the kernel, and the sum of the results would give the value of the middle pixel. 7 This process is repeated until our 2D matrix of neurons becomes into a smaller matrix of features, this process is called a 2D convolution.…”