Traffic Scene Analysis and Classification using Deep Learning

Abstract

In this study, we aim to use new deep-learning tools and convolutional neural networks for traffic analysis. ResNeXt architecture, one of the most potent architectures and has attracted much attention in various fields, has been proposed to examine the scene, and classify it into three categories: cars, bikes (bicycles/motorcycles), and pedestrians. Previous studies have focused more on one type of classification and reported only human-facial recognition or vehicle detection. In contrast, the proposed method uses precise architecture to perform the classification of three classes. The proposed plan has been implemented in several steps: the first stage is to divide the critical objects. In the next step, the characteristics of the obtained objects are extracted to classify the process into three classes. Experiments have been conducted on different and essential datasets such as high-traffic, low-quality, real-time scenes. Essential evaluation criteria such as accuracy, sensitivity, and specificity show that the performance of the proposed method has improved compared to the methods being compared. The accuracy criterion reached more than 92%, sensitivity about 89%, and specially to 90.25%. The proposed method can be used to implement intelligent cities, public safety, and metropolitan decisions and use the results in urban management, predictive modeling of lost data management, sequential data management, and generalizability.

Investigating Hostile Post Detection in Gujarati: A Machine Learning Approach

“…We are also working on two classes: hostile and nonhostile. Since we are getting comparatively good results for the Logistic regression method (36)(37)(38)(39). We have also compared the result of Bag-of-Words and TF-IDF feature extraction methods.…”

“…Figure 1 shows basic approaches used for hostile post-detection. Mainly these approaches are divided into two major categories: (i) Machine Learning based (23)(24)(25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35) and (ii) Deep Learning based (5,6,(27)(28)(29)(34)(35)(36)(37)(38). Machine learning-based approach is categorized into two subparts:(i) Supervised machine learning based and (ii) Unsupervised machine learning based (27,(30)(31)(32)37).…”

Res2Net-based multi-scale and multi-attention model for traffic scene image classification

“…However, the fusion of local and global features in this dual network form will increase complexity and computational costs. Z. Dorrani [ 41 ] presented an approach to traffic scene analysis and classification using deep learning and convolutional neural networks. The study utilized the ResNeXt architecture, a powerful framework that has garnered significant attention across various fields.…”

Enhanced Autoregressive Integrated Moving Average Model for Anomaly Detection in Power Plant Operations

“…In the rapidly evolving field of industrial automation and monitoring, the analysis of sensory time-series data plays a fundamental role in ensuring the efficiency and reliability of machinery and systems (1,2). Meanwhile, one of the important applications of data analysis by various artificial intelligence algorithms that can be seen in daily life is the prediction of transport traffic and routing based on the shortest possible time to reach the destination (3)(4)(5). In addition, in the past few years, in order to study the corona virus and its spread in the world, time series analysis methods were also used to analyze the speed of transmission, progress and even treatment time (6).…”