Vehicle Detection Using Deep Learning Technique in Tunnel Road Environments

In recent years, technology advancement has led to an enormous increase in the amount of satellite data. The availability of huge datasets of remote sensing measurements to be processed, and the increasing need for near-real-time data analysis for operational uses, has fostered the development of fast, efficient-retrieval algorithms. Deep learning techniques were recently applied to satellite data for retrievals of target quantities. Forward models (FM) are a fundamental part of retrieval code development and mission design, as well. Despite this, the application of deep learning techniques to radiative transfer simulations is still underexplored. The DeepLIM project, described in this work, aimed at testing the feasibility of the application of deep learning techniques at the design of the retrieval chain of an upcoming satellite mission. The Land Surface Temperature Mission (LSTM) is a candidate for Sentinel 9 and has, as the main target, the need, for the agricultural community, to improve sustainable productivity. To do this, the mission will carry a thermal infrared sensor to retrieve land-surface temperature and evapotranspiration rate. The LSTM land-surface temperature retrieval chain is used as a benchmark to test the deep learning performances when applied to Earth observation studies. Starting from aircraft campaign data and state-of-the-art FM simulations with the DART model, deep learning techniques are used to generate new spectral features. Their statistical behavior is compared to the original technique to test the generation performances. Then, the high spectral resolution simulations are convolved with LSTM spectral response functions to obtain the radiance in the LSTM spectral channels. Simulated observations are analyzed using two state-of-the-art retrieval codes and deep learning-based algorithms. The performances of deep learning algorithms show promising results for both the production of simulated spectra and target parameters retrievals, one of the main advances being the reduction in computational costs.

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

Research on Vehicle Detection and Recognition Technology Based on Artificial Intelligence

At the current stage, the rapid Development of autonomous driving has made object detection in traffic scenarios a vital research task. Object detection is the most critical and challenging task in computer vision. Deep learning, with its powerful feature extraction capabilities, has found widespread applications in safety, military, and medical fields, and in recent years has expanded into the field of transportation, achieving significant breakthroughs. This survey is based on the theory of deep learning. It systematically summarizes the Development and current research status of object detection algorithms, and compare the characteristics, advantages and disadvantages of the two types of algorithms. With a focus on traffic signs, vehicle detection, and pedestrian detection, it summarizes the applications and research status of object detection in traffic scenarios, highlighting the strengths, limitations, and applicable scenarios of various methods. It introduces techniques for optimizing object detection algorithms, summarizes commonly used object detection datasets and traffic scene datasets, along with evaluation criteria, and performs comparative analysis of the performance of deep learning algorithms. Finally, it concludes the development trends of object detection algorithms in traffic scenarios, providing research directions for intelligent transportation and autonomous driving.

There are various means of monitoring traffic situations on roads. Due to the rise of artificial intelligence (AI) based image processing technology, there is a growing interest in developing traffic monitoring systems using camera vision data. This study provides a method for deriving traffic information using a camera installed at an intersection to improve the monitoring system for roads. The method uses a deep-learning-based approach (YOLOv4) for image processing for vehicle detection and vehicle type classification. Lane-by-lane vehicle trajectories are estimated by matching the detected vehicle locations with the high-definition map (HD map). Based on the estimated vehicle trajectories, the traffic volumes of each lane-by-lane traveling direction and queue lengths of each lane are estimated. The performance of the proposed method was tested with thousands of samples according to five different evaluation criteria: vehicle detection rate, vehicle type classification, trajectory prediction, traffic volume estimation, and queue length estimation. The results show a 99% vehicle detection performance with less than 20% errors in classifying vehicle types and estimating the lane-by-lane travel volume, which is reasonable. Hence, the method proposed in this study shows the feasibility of collecting detailed traffic information using a camera installed at an intersection. The approach of combining AI and HD map techniques is the main contribution of this study, which shows a high chance of improving current traffic monitoring systems.

Vehicle detection from very-high-resolution satellite imagery has received increasing interest during the last few years. In this article, we propose an automatic system for operational traffic monitoring using very-high-resolution optical satellite imagery (0.5–0.6 m resolution) of small highways with low traffic density and a range of different illumination conditions, including cloud-shadowed, hazy, and partially cloudy conditions. The proposed system includes cloud and cloud shadow detection, road detection, and vehicle detection, classification, and counting. The main part of the system is vehicle detection, which is constructed using an elliptical blob detection strategy followed by region growing and feature extraction steps. Vehicular objects are separated from non-vehicular objects using a K-nearest-neighbour classifier, with various classical features used for pattern recognition, as well as some proposed application-specific features, and are also classified according to vehicle size. The fully automatic processing chain has been validated on a selection of satellite scenes from different parts of Norway, including imagery with large amounts of cloud, fog, cloud shadows, and similar conditions that complicate image interpretation. The overall vehicle detection rate was 85.4% and the false detection rate was 9.2%. Overall, this demonstrates the potential of operational traffic monitoring using very-high-resolution satellites.

In this paper, we proposed image processing technique for automatic real time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurred in the tunnel, it is necessary to have a system to minimize and to discover the incident as fast as possible. However it is impossible to keep the human observation of Closed-Circuit Television (CCTV) in tunnel for 24 hour. So if the fire and smoke detection system through image processing can warn fire state, it will be very convenient, and it can be possible to minimize damage even when people is not in front of monitor. The fire and smoke detection is different from the forest fire detection as there are elements such as car and tunnel lights and others that are different from the forest environment so that an indigenous algorithm has to be developed. The two algorithms proposed in this paper, are able to detect the exact position, at the earlier stage of incident. In addition, by comparing properties of each algorithm throughout experiment, we have proved the validity and efficiency of proposed algorithm

New luminescent coatings are increasingly being used in highway tunnels to address inadequate internal lighting conditions. However, there is currently a lack of scientifically reliable methods to evaluate the effectiveness of these paints in improving lighting conditions, reducing driver psychological stress, and quantifying these impacts. This study utilized new luminescent coatings to improve tunnel lighting conditions, conducting real-vehicle tests to measure drivers’ physiological parameters including pupil diameter and heart rate. It examined the mechanisms through which variations in lighting conditions within highway tunnels affect the psychological workload of drivers. A hierarchical analysis–fuzzy comprehensive evaluation (AHP-FCE) method was adopted to develop a quantitative evaluation system for highway tunnel driving psychological load. The results indicate that variations in tunnel lighting substantially influence the psychological workload experienced by drivers during operation. The new luminescent coatings effectively enhanced tunnel lighting conditions, increasing average brightness and illuminance by 37.71% and 40.95%, respectively. Following lighting improvements, pupil diameter variation rates during tunnel entry and exit phases decreased by 35.37% and 10.06%, respectively, while heart rate variation rates decreased by 12.50% and 4.36%. Quantitative analysis of driver mental load revealed a comprehensive score of 0.6230 before lighting enhancement, which decreased to 0.2702 after improvements. This research introduces an innovative integrative framework that combines physiological parameter monitoring with the AHP-FCE method to quantitatively assess the psychological workload experienced by drivers in tunnel environments. This approach addresses a significant gap in the literature concerning the quantitative relationship between tunnel lighting optimization and drivers’ psychological workload responses.

In order to solve the problem that vehicle detection rate can be affected in complex scenarios, authors put forward the adaptive method based on GMM which sets up and updates the background and use the average neighbourhood based on HSV fast shadow elimination algorithm which improves the speed of shadow elimination. For occluded vehicles, authors use the recognition algorithm based on Kalman Filter which blocks vehicle identification, then authors adopts pyramid hierarchical search algorithm based on the template matching which segments the occluded vehicles. The experimental results show that the algorithm is simple and effective and the detection rate of vehicle is 97%, which meets the requirements of vehicle detection completely.

We present a novel method for vehicle detection and classification in aerial imagery. First, change detection analyzes a pair of mutually aligned images captured at the same location but at different time instants to generate vehicle proposals. Next, a trained Convolutional Neural Network (CNN) classifier is applied to (1) determine if a proposal truly contains a vehicle, and (2) classify any vehicle present into major categories. Experimental results using infrared (IR) data demonstrate the efficacy of our method: vehicle detection rate is over 99%; light-duty vehicles (e.g. sedan) are classified with 89% accuracy, medium-duty vehicles (e.g., van and pickup) with 79% and heavy-duty vehicles (e.g., trucks and buses) with 73% accuracies. The classification performance difference among different vehicle types is attributed to the size of training samples available in each category. Our system can process data at video rate making it feasible for real-time traffic monitoring.

Recently, deep learning techniques, specifically semantic segmentation, have been employed to extract visual features from street images, a dimension that has received limited attention in the investigation of the connection between subjective and objective road environment perception. This study is dedicated to exploring and comprehending the factors influencing commuters’ perceptions of the road environment, with the aim of bridging the gap in interpreting environmental quality in Thailand. Semantic segmentation was applied to identify visual objects, expressed as a percentage of pixels represented in 14,812 street images from the Bangkok Metropolitan Region. Subjective road environment perception was assessed through a questionnaire, with a total of 3600 samples collected. Both sets of data were converted to average values per grid, with a grid size of 500 × 500 square meters, resulting in a total of 631 grids with data points. Finally, a multiple linear regression model was employed to analyze the relationship between the ratios of objects obtained from street images via semantic segmentation and human sensory perception of the road environment. The findings from this analysis indicate that the attributes of distinct object classes have a notable impact on individuals’ perceptions of the road environment. Visual elements such as infrastructure, construction, nature, and vehicles were identified as influential factors in shaping the perception of the road environment. However, human and object features did not exhibit statistical significance in this regard. Furthermore, when examining different road environments, which can be categorized into urban, community, and rural contexts, it becomes evident that these contexts distinctly affect the perceptions of various road environments. Consequently, gaining a comprehensive understanding of how street environments are perceived is crucial for the design and planning of neighborhoods and urban communities, facilitating the creation of safer and more enjoyable living environments.

Vehicle detection is an important component in unmanned driving systems. This paper presents a real-time vehicle detection method under complex road conditions to solve the problem of real-time detection of road vehicles in automatic driving. Firstly using yolo network to build a deeper depth neural network, which is used to identify and score the vehicles in the image. Then, using the dynamic threshold method to remove some false candidate boxes, and using the Gauss attenuation function to filter the overlapping candidate boxes. The loss function normalized by the change rate is used to train the neural network, and the batch normalization layer is used to correct the input data of the network to avoid data deviation during the training process. Finally, a full convolution layer is added at the end of the network layer to transform the two-dimensional data into one-dimensional data and output the final recognition results. It is verified that this method improves the efficiency and accuracy of real-time vehicle detection, it can effectively detect vehicles on roads with complex backgrounds, and satisfy the real-time requirements of road vehicle detection.

Deep learning-based classification and detection algorithms have emerged as a powerful tool for vehicle detection in intelligent transportation systems. The limitations of the number of high-quality labeled training samples makes the single vehicle detection methods incapable of accomplishing acceptable accuracy in road vehicle detection. This paper presents detection and classification of vehicles on publicly available datasets by utilizing the YOLO-v5 architecture. This paper’s findings utilize the concept of transfer learning through fine tuning the weights of the pre-trained YOLO-v5 architecture. To employ the concept of transfer learning, extensive data sets of images and videos of the congested traffic patterns were collected by the authors. These datasets were made more comprehensive by pointing various attributes, for instance high- and low-density traffic patterns, occlusions, and different weather circumstances. All of these gathered datasets were manually annotated. Ultimately, the improved YOLO-v5 structure becomes accustomed to any difficult traffic patterns. By fine-tuning the pre-trained network through our datasets, our proposed YOLO-v5 has exceeded several other traditional vehicle detection methods in terms of detection accuracy and execution time. Detailed simulations performed on the PKU, COCO, and DAWN datasets demonstrate the effectiveness of the proposed method in various challenging situations.

This study presents a Level of Detail 2 building reconstruction approach for open and occluded areas from stereo-satellite imagery. The approach combines deep learning techniques, and digital surface models with model-driven methodology. The best performance of deep learning algorithms (U-Net, FCN, and Mask R-CNN) for building boundary segmentation was selected and then integrated with model-driven technique for the purpose of accurate geometric building fitting employing digital surface model (DSM) generated by semi global matching. The Reconstructed model was refined by utilizing OpenStreetMap library and graph cut optimization method. The suggested methodology is tested on the GeoEye-1 satellite imagery dataset for Erbil City, which is validated with ground truth data. The proposed algorithm presented promising results, it is shown that the model can predict building heights for ridge and eave to a mean absolute error of 0.70 m, and in the occluded area was approximately 1.0 m. Meanwhile, the computed root mean square error are shown to be within 0.9 m for the ridge and eave, which is essentially small. While for occluded area it was approximately 1.2 m and 0.8 m for ridge and eave heights, respectively. This indicates that the predicted values are close to real values. Furthermore, most of the building’s roofs were correctly classified in both open and occluded areas. These findings underline the effectiveness of the model-driven deep learning approach in producing reliable and accurate LoD2 building reconstructions, a precondition for detailed urban analysis and 3D city modeling.

Automated segmentation of chronic stroke lesion using efficient U-Net architecture