Optoelectronic systems for automatic vehicle counting and classification in rest areas

The rapid advancement in the field of deep learning and high performance computing has highly augmented the scope of video-based vehicle counting system. In this paper, the authors deploy several state-of-the-art object detection and tracking algorithms to detect and track different classes of vehicles in their regions of interest (ROI). The goal of correctly detecting and tracking vehicles’ in their ROI is to obtain an accurate vehicle count. Multiple combinations of object detection models coupled with different tracking systems are applied to access the best vehicle counting framework. The models’ addresses challenges associated to different weather conditions, occlusion and low-light settings and efficiently extracts vehicle information and trajectories through its computationally rich training and feedback cycles. The automatic vehicle counts resulting from all the model combinations are validated and compared against the manually counted ground truths of over 9 h’ traffic video data obtained from the Louisiana Department of Transportation and Development. Experimental results demonstrate that the combination of CenterNet and Deep SORT, and YOLOv4 and Deep SORT produced the best overall counting percentage for all vehicles.

Over the last decade, the number of automobiles has skyrocketed. There are more than one billion active automobiles in the universe, including 70–80 million in India. Handling such traffic conditions and providing enough parking spaces is a difficult task. Vehicle counting and classification on congested routes will assist authorities in obtaining traffic flow data as well as understanding and studying traffic patterns, allowing for the most efficient traffic management. As a result, the aim of this work is that a cost-effective vision-based vehicle counting and classification system that is mainly implemented in OpenCV utilising Python programming and some methods of image processing.KeywordsTraffic managementVehicle countingVehicle classificationComputer visionCost-effective

At present, the automatic classification of vehicles on roads is mostly based on image recognition, and there are defects in adaptability under non-line-of-sight environments. In this paper, based on the similarity of the integration of the ecosystem model and multi-neural network model, an artificial neural network group (BNNG) algorithm was proposed. The vehicle’s driving acoustic signal was taken as the research object, and it was calculated using the Artificial Neural Network (BNNG) algorithm to achieve automatic classification and recognition of vehicle models. Through experimental tests, it is shown that under non-line-of-sight environments, the accuracy of vehicle classification can be improved, and the misrecognition rate of similar models can be greatly reduced. This provided a new method for the automatic classification and identification of vehicles on roads, which was of great significance to monitor vehicle safety in non-line-of-sight environments.

Using video in traffic monitoring is one of the most active research domains in the computer vision community. TrafficMonitor, a system that employs a hybrid approach for automatic vehicle tracking and classification on highways using a simple stationary calibrated camera, is presented. The proposed system consists of three modules: vehicle detection, vehicle tracking, and vehicle classification. Moving vehicles are detected by an enhanced Gaussian mixture model background estimation algorithm. The design includes a technique to resolve the occlusion problem by using a combination of two-dimensional proximity tracking algorithm and the Kanade–Lucas–Tomasi feature tracking algorithm. The last module classifies the shapes identified into five vehicle categories: motorcycle, car, van, bus, and truck by using three-dimensional templates and an algorithm based on histogram of oriented gradients and the support vector machine classifier. Several experiments have been performed using both real and simulated traffic in order to validate the system. The experiments were conducted on GRAM-RTM dataset and a proper real video dataset which is made publicly available as part of this work.

Vehicle Tracking and Counting through Image Processing is an efficient system for real-time vehicle detection, classification, and counting using the powerful combination of YOLO and OpenCV. The System uses the application of machine learning in the domain of image processing for vehicle tracking and counting. OpenCV in this system is used to process the video feed or images and provide real-time visualization of the vehicles for detection. The system uses advanced computer vision techniques such as contour detection, image segmentation, and feature extraction to accurately locate and recognize individual vehicles in a scene. The detected vehicles are classified into various categories, including cars, trucks, motorcycles, and bicycles (Two & four wheelers) using the trained YOLO model. In addition to detection and classification the count of vehicles is also noted down. The primary objective of this system is to track the vehicles, distinguish and count them. This system can be used in – Traffic Signal Management and Parking Lot Monitoring. Keywords: - YOLO, OpenCV, Python, CVAT

This paper provides a review of a 3-year research program on the feasibility of using airborne LiDAR (Light Detection and Ranging) and imagery collected simultaneously over transportation corridors for estimation of traffic flow parameters such as: (1) vehicle counts, (2) vehicle classification, (3) velocity per vehicle category, and (4) intersection movement patterns. This work is conducted by The National Consortium for Remote Sensing in Transportation-Flows (NCRST-F), led by The Ohio State University, supported by the U.S. Department of Transportation and the National Aeronautics and Space Administration (NASA). The major focus is on improving the efficiency of transportation systems by integration of remotely sensed data with traditional ground data to monitor and manage traffic flows.

This paper explores the feasibility of using a lowcost embedded ARM-based system for real-time vehicle detection, classification and counting through image processing algorithms with the aim of knowing information about vehicular traffic in different roads and highways to improve the management of mobility and the functioning of cities. This paper proposes the implementation of a low cost system to identify and classify vehicles using an Embedded ARM based platform (ODROID XU-4) with Ubuntu operating system. The algorithms used are based on the Open-source library (Intel OpenCV) and implemented in Python programming language. The experimentation carried out proved that the efficiency of the algorithm implemented was 95.35%, but it can be improved by increasing the training sample.

This paper describes the 1990 test of an automatic vehicle classification (AVC) system employing an inductance detector loop and photoelectric sensors emitting infrared-spectrum light beams, which were reflected off commonly used raised traffic lane markers. The passing of a vehicle activated the sensors. Signals from the activation go through a special microprocessor into a personal computer for interpretation, display, and recording. Vehicle speed and axle patterns are inferred from the pattern of the photoelectric beam interruptions. The system is tested several times at a high-speed (50–65 mph) Oklahoma turnpike site by comparing the automatic classifications with classifications by a person. The researchers use computer printouts and written field observations to evaluate the number and type of errors. An error is said to occur when the automatic vehicle classification does not agree with the classification by the observer. The evaluation shows that the first-generation AVC system correctly classifies about 95% of 1,736 observed vehicles. Further analysis of the raw data and the errors found therein suggests that, with modifications, the AVC system can correctly classify about 97–98% of the vehicles. Snow or heavy rain does not occur during the tests, so ability to classify in these conditions is not evaluated.

Problems related to determining traffic noise characteristics are discussed in the context of automatic dynamic noise analysis based on noise level measurements and traffic prediction models. The obtained analytical results provide the second goal of the study, namely automatic vehicle counting and classification. Several traffic prediction models are presented and compared to the results of in-situ noise level measurements. Synchronized audio recordings were made to determine Sound Quality parameters describing the nature of acquired sound signals. Video recordings and information about the traffic structure using commercially available automatic vehicle detection methods were also collected in order to create ground truth data used for the experiments.

In this paper we describe holonic organization of a multi agent system for automatic vehicle classification in a road toll system. Classification of vehicles in road toll systems is based on physical vehicle features and in this paper we focus on axle counting as the first discriminant feature for class determination. Our system relies on two main sensors—video camera and depth sensor. Video image and depth image processing is performed in several holons. The results from individual holons are fused into the final decision on a number of axles of a passing vehicle. We show that fusion of results from individual holons gives more precise results than individual holons. Holonic organization of the system aids scalability and simplifies inclusion of new sensors and new algorithms.

The application of computer vision in transportation engineering has facilitated real-time traffic flow optimization, vehicle counting, anomaly detection, and ameliorated transportation safety. Most vision systems are, however, developed through a supervised learning process, which can be data hungry and costly because it requires manual annotation of objects from a variety of sources. The general rule of thumb for building accurate and transferrable vision models has been to increase the quality, diversity, and quantity of the annotated datasets used in model training. This paper presents a simple, yet efficient active learning framework that significantly reduces the number of annotations needed to build a state-of-the-art vehicle detection and classification model. To achieve this, we first leverage a vision transformer that generates embeddings rich with information needed to quantify the similarity and diversity between images in a two-dimensional embedding space. To select which images from the embedding space should be annotated, we propose a scoring and sampling strategy that minimizes class imbalance and model uncertainty through an iterative process. The latest iteration of the You Only Look Once (YOLO) model, YOLOv8, is used as the active learner. We compare the efficacy of our proposed active learning methods with models developed at much higher sampling rates using the mean average precision. The models developed were also integrated with tracking algorithms to evaluate differences in accuracy for vehicle counts and their practical implications for direction counts.

In the work presented here, signal processing techniques are used for condition monitoring of boring tool using acoustic signals. To accomplish this work, 108 experimental runs are performed to diagnose the tool life of the boring operation, by using two different sensor data. The acoustic signals are captured from the tool which is performing boring operation on mild steel materials. The acoustic signature being the main signal for study, vibration signals have also been measured for comparison. Four sets of boring experiments were performed. After the data had been collected for all runs of boring operation, signal processing methods are applied for doing the analysis of captured signal. The acoustic signals are captured from the boring tool and further analyzed by using learning-based methods for determining the condition of boring tool.

A quantitative assessment protocol was developed to evaluate potential signal processing methods for THz NDE of spray‐on foam insulation. Automated feature extraction methods were developed to replicate the important visual classification characteristics used by inspectors and a new merit assessment approach was developed to identify the most promising combination of signal processing algorithms. Through application of the protocol to test data, several signal processing methods were found to improve the discrimination of defects.

Passenger car units in saturation flows: Concept, definition, derivation

Intelligent transportation systems (ITS) are the integration of information and communications technologies with applications which are significant in traffic control and management. The increased number of on road vehicles in urban areas urges the need of development of automated methods for traffic management. Vehicle identification, classification and analysis enable the intelligent transportation systems to make decisions. In this paper, an automated method for video analysis for vehicle identification using a modified Region based Convolution Neural Network (RCNN) has been proposed. The traffic videos collected by CCTV cameras installed on the roads are analyzed for vehicle identification in a given frame. The pretrained google net is used to extract features. These features are used by the Region based Convolution Neural Network for vehicle identification. The vehicles are identified using probability score computed using intersection of objects (IoU). The identified vehicles are classified into ten different vehicle classes. The proposed network concatenates features from previous layers to reduce loss and consequently improve the vehicle identification accuracy. The vehicle identification method is further extended for vehicle counting and behavioral analysis. The vehicle counting information can be used for congestion control in smart cities. The behavioral analysis includes computation of speed of vehicles. The speed information is useful for traffic law enforcement in smart cities. The proposed method is applied on MIO-TCD vehicle dataset and EBVT video dataset. The results are calculated using three different metrics namely average accuracy, mean precision and mean recall. Obtained results are also compared with other state of the art methods. The results show significant improvement and thus the method can be effectively used for video analysis.